chore: retire docs-to-skills and make single compact user skill by miyoungc · Pull Request #5699 · NVIDIA/NemoClaw

miyoungc · 2026-06-23T23:03:27Z

Summary

This PR retires the generated docs-to-skills pipeline and replaces the expanded generated user skill catalog with one compact nemoclaw-user-guide skill. The guide routes AI agents to canonical NemoClaw documentation through the docs MCP server, llms.txt, and variant-specific Markdown pages while keeping contributor and maintainer skills intact.

Changes

Remove scripts/docs-to-skills.py, the generated .agents/skills/nemoclaw-user-* trees, generated root skills/nemoclaw-user-* exports, and generated catalog metadata.
Add nemoclaw-user-guide as the single customer-facing user skill under .agents/skills/, with matching evals and a hard-copy root skills/nemoclaw-user-guide catalog publication copy.
Refresh the root catalog copy through NVSkills signing and document the hard-copy catalog refresh flow.
Update the AI Agent Docs page with the starter prompt button, the NemoClaw docs MCP server URL, Claude Code/Cursor setup guidance, llms.txt, and specific .md docs routes without the deprecated llms-full.txt path.
Update agent guides, contributor docs, PR/issue guidance, catalog signing notes, and CI/static checks to reference Markdown/MCP docs routing instead of generated user-skill refreshes.
Retarget the skill frontmatter test to validate checked-in SKILL.md files, guard the single root skills/ catalog surface, and verify the catalog copy matches the .agents/skills/nemoclaw-user-guide source files while allowing NVSkills signing artifacts.

Type of Change

Code change (feature, bug fix, or refactor)
Code change with doc updates
Doc only (prose changes, no code sample modifications)
Doc only (includes code sample changes)

Verification

Signed-off-by: Miyoung Choi miyoungc@nvidia.com

Summary by CodeRabbit

New Features
- Introduced nemoclaw-user-guide for consolidated AI-agent documentation routing via an MCP docs server, with fallback to Markdown indexing.
Documentation
- Updated terminology from “Agent Skills” to “AI Agent Docs” across user-facing materials.
- Refreshed docs refresh/release workflow and the Verified Skills catalog publishing guidance.
Deprecations/Removals
- Removed several user-focused skills and their related documentation/evaluation content, consolidating guidance into the user guide.
Refactor
- Streamlined the workflow to prioritize canonical Markdown docs sources.

copy-pr-bot · 2026-06-23T23:03:31Z

Auto-sync is disabled for draft pull requests in this repository. Workflows must be run manually.

Contributors can view more details about this message here.

coderabbitai · 2026-06-23T23:03:58Z

📝 Walkthrough

Walkthrough

Removes the scripts/docs-to-skills.py generation pipeline and all individually generated nemoclaw-user-* skills. Introduces a single hand-authored nemoclaw-user-guide skill that routes AI agents to canonical NemoClaw Markdown documentation via an MCP docs server. Renames "Agent Skills" to "AI Agent Docs" across the docs site and updates contributor guidance, CI hooks, skills guide, and the skills/ catalog accordingly.

Changes

Replace docs-to-skills pipeline with nemoclaw-user-guide MCP skill

Layer / File(s)	Summary
New nemoclaw-user-guide skill in both .agents and skills `.agents/skills/nemoclaw-user-guide/SKILL.md`, `.agents/skills/nemoclaw-user-guide/evals/evals.json`, `skills/nemoclaw-user-guide/SKILL.md`, `skills/nemoclaw-user-guide/evals/evals.json`, `skills/nemoclaw-user-guide/BENCHMARK.md`, `skills/nemoclaw-user-guide/skill-card.md`, `skills/nemoclaw-user-guide/skill.oms.sig`	Creates `nemoclaw-user-guide` skill defining MCP docs server retrieval order, starting pages, task routing, user-assistance rules, and response requirements. Adds six eval cases. Updates BENCHMARK.md to a PASS verdict with 5 tasks, updates skill-card.md with doc-routing use case and evaluation metrics, and replaces the DSSE signature bundle.
Remove old skill evaluation and benchmark artifacts `.agents/skills/nemoclaw-user-configure-security/evals/evals.json`, `.agents/skills/nemoclaw-user-manage-sandboxes/references/messaging-channels.md`, `skills/nemoclaw-user-deploy-remote/BENCHMARK.md`, `skills/nemoclaw-user-get-started/BENCHMARK.md`	Clears remaining evaluation definitions and benchmark reports from deleted individual user-skill directories in both `.agents/skills/` and `skills/`.
Update pre-commit and CI hooks for skill frontmatter validation `.pre-commit-config.yaml`, `.github/actions/ci-static-checks/action.yaml`	Removes the `docs-to-skills-dry-run` pre-commit hook, updates `spdx-headers` hook file pattern to exclude the deleted script, narrows `test-skills-yaml` hook trigger to skills frontmatter paths, and renames the CI step to "Run skill frontmatter tests".
Rewrite agent-skills page and rename Agent Skills to AI Agent Docs `docs/resources/agent-skills.mdx`, `docs/_components/StarterPromptButton.tsx`, `docs/index.mdx`, `docs/index.yml`, `docs/about/overview.mdx`, `docs/about/release-notes.mdx`, `docs/get-started/prerequisites.mdx`, `docs/get-started/quickstart.mdx`, `fern/fern.config.json`	Rewrites `agent-skills.mdx` to describe MCP docs server configuration, `StarterPromptButton` setup, and optional sparse-checkout of `nemoclaw-user-guide`. Renames "Agent Skills" to "AI Agent Docs" throughout. Removes `llms-full.txt` bullet. Updates homepage card and keywords. Bumps Fern to `5.50.5`.
Update contributor, maintainer, and agent documentation `AGENTS.md`, `CONTRIBUTING.md`, `docs/AGENTS.md`, `docs/CONTRIBUTING.md`, `skills/README.md`, `.github/catalog-skills-signing-flow.md`, `.github/ISSUE_TEMPLATE/bug_report.yml`	Updates AGENTS.md and CONTRIBUTING.md to remove docs-to-skills references and document skill frontmatter validation. Rewrites docs/AGENTS.md and docs/CONTRIBUTING.md to reflect Markdown-first approach and when to update `nemoclaw-user-guide`. Rewrites `skills/README.md` and `catalog-skills-signing-flow.md` for manual `nemoclaw-user-guide` catalog workflow. Updates bug report template.
Consolidate agent skills guide and contributor workflow `.agents/skills/nemoclaw-skills-guide/SKILL.md`, `.agents/skills/nemoclaw-contributor-update-docs/SKILL.md`, `.agents/skills/nemoclaw-maintainer-day/SKILL.md`, `.agents/skills/nemoclaw-contributor-create-pr/SKILL.md`	Consolidates `nemoclaw-user-*` bucket to a single `nemoclaw-user-guide` entry and updates role matrices. Updates `nemoclaw-contributor-update-docs` to conditionally update `nemoclaw-user-guide/SKILL.md` only when routing guidance changes, and adjusts PR labeling rules. Updates maintainer-day commit hygiene and contributor-create-pr hook evidence.

Estimated code review effort

🎯 3 (Moderate) | ⏱️ ~25 minutes

Possibly related PRs

NVIDIA/NemoClaw#607: Directly related — this PR removes the scripts/docs-to-skills.py generator and its docs-to-skills-dry-run pre-commit hook that PR #607 originally introduced.
NVIDIA/NemoClaw#2131: Directly related — PR #2131 overhauled scripts/docs-to-skills.py and the resulting nemoclaw-user-* skill output structure, which this PR deletes entirely.
NVIDIA/NemoClaw#4744: Related — both PRs directly modify .agents/skills/nemoclaw-user-* evaluation datasets and the pre-commit hook behavior for docs-to-skills workflow.

Suggested labels

documentation, area: docs

Suggested reviewers

ericksoa
prekshivyas

Poem

🐰 Hippity-hop, the old scripts are gone,
No more generating skills from docs at dawn!
One guide to rule them all, via MCP it flows,
llms.txt as fallback when the server snoozes,
Markdown routes for every AI that knows —
The rabbit approves: less pipeline, more prose! 🌿

🚥 Pre-merge checks | ✅ 5

✅ Passed checks (5 passed)

Check name	Status	Explanation
Description Check	✅ Passed	Check skipped - CodeRabbit’s high-level summary is enabled.
Title check	✅ Passed	The pull request title clearly summarizes the main objective: retiring the docs-to-skills pipeline and consolidating user skills into a single compact skill.
Docstring Coverage	✅ Passed	No functions found in the changed files to evaluate docstring coverage. Skipping docstring coverage check.
Linked Issues check	✅ Passed	Check skipped because no linked issues were found for this pull request.
Out of Scope Changes check	✅ Passed	Check skipped because no linked issues were found for this pull request.

_{✏️ Tip: You can configure your own custom pre-merge checks in the settings.}

✨ Finishing Touches

🧪 Generate unit tests (beta)

Create PR with unit tests
Commit unit tests in branch refactor-user-skills

_{Comment @coderabbitai help to get the list of available commands.}

github-actions · 2026-06-23T23:04:05Z

🌿 Preview your docs: https://nvidia-preview-pr-5699.docs.buildwithfern.com/nemoclaw

github-code-quality · 2026-06-23T23:04:05Z

Code Coverage Overview

Languages: TypeScript

TypeScript / code-coverage/plugin

The overall coverage in the refactor-user-skills branch is 96%. Coverage data for the main branch is not yet available.

Show a code coverage summary of the most covered files.

File	`main`	`refactor-user-skills` 442c25a	+/-
`nemoclaw/src/se...cret-scanner.ts`	—	100%	—
`nemoclaw/src/commands/slash.ts`	—	100%	—
`nemoclaw/src/li...bprocess-env.ts`	—	100%	—
`nemoclaw/src/bl...eprint/state.ts`	—	98%	—
`nemoclaw/src/onboard/config.ts`	—	98%	—
`nemoclaw/src/bl...int/snapshot.ts`	—	97%	—
`nemoclaw/src/bl...print/runner.ts`	—	95%	—
`nemoclaw/src/co...ration-state.ts`	—	94%	—
`nemoclaw/src/bl...ate-networks.ts`	—	94%	—
`nemoclaw/src/index.ts`	—	94%	—

TypeScript / code-coverage/cli

The overall coverage in the refactor-user-skills branch is 46%. Coverage data for the main branch is not yet available.

Show a code coverage summary of the most covered files.

File	`main`	`refactor-user-skills` 442c25a	+/-
`src/lib/state/o...oard-session.ts`	—	91%	—
`src/lib/inference/local.ts`	—	76%	—
`src/lib/sandbox/config.ts`	—	72%	—
`src/lib/actions...dbox/rebuild.ts`	—	67%	—
`src/lib/onboard/preflight.ts`	—	64%	—
`src/lib/actions...licy-channel.ts`	—	56%	—
`src/lib/state/sandbox.ts`	—	55%	—
`src/lib/onboard...er-gpu-patch.ts`	—	50%	—
`src/lib/policy/index.ts`	—	49%	—
`src/lib/onboard.ts`	—	18%	—

_{Updated June 24, 2026 01:34 UTC
Code Coverage is in Public Preview. Learn more and provide us with your feedback.}

github-actions · 2026-06-23T23:05:05Z

E2E Advisor Recommendation

Required E2E: None
Optional E2E: None

Workflow run

Full advisor summary

E2E Recommendation Advisor

Base: origin/main
Head: HEAD
Confidence: high

Required E2E

None. No E2E is recommended. The diff is limited to documentation, agent-skill content/catalog artifacts, docs generation/signing guidance, CI/static-check configuration, and a unit test for skill frontmatter. It does not modify installer/onboarding implementation, onboarding machine live-slice orchestration or resume/repair states, sandbox lifecycle, credentials, network policy enforcement, inference routing code, deployment code, or real assistant runtime behavior. Existing static checks, docs build, skill validation, and targeted unit tests are the appropriate coverage.

Optional E2E

None.

New E2E recommendations

None.

github-actions · 2026-06-23T23:05:06Z

Vitest E2E Scenario Recommendation

Required Vitest E2E scenarios: None
Optional Vitest E2E scenarios: None

Workflow run

Full Vitest E2E advisor summary

Vitest E2E Scenario Advisor

Base: origin/main
Head: HEAD
Confidence: high

Required Vitest E2E scenarios

None. No Vitest scenario E2E dispatch is required because the PR changes documentation, agent/skill content, generated skill artifacts, docs tooling/static-check configuration, and tests outside test/e2e-scenario. It does not change the Vitest scenario workflow, registry, runtime support, live scenario tests, fixtures, manifests, or onboarding state-machine behavior.

Optional Vitest E2E scenarios

None.

Relevant changed files

None.

github-actions · 2026-06-23T23:07:20Z

PR Review Advisor — No blocking findings

Merge posture: No blocking advisor findings
Primary next action: Add or justify PRA-T1 and any related test follow-ups.
Open items: 0 required · 0 warnings · 1 suggestion · 1 test follow-up
Since last review: 0 prior items resolved · 0 still apply · 1 new item found

Action checklist

PRA-T1 Add or justify test follow-up: Add a negative activation eval for the broad user-guide skill
PRA-1 In-scope improvement: Add a negative activation eval for the broad user-guide skill in skills/nemoclaw-user-guide/BENCHMARK.md:47

Findings index

ID	Severity	Category	Location	Required action
`PRA-1`	Improvement	tests	`skills/nemoclaw-user-guide/BENCHMARK.md:47`	Add one local negative or decoy eval for `nemoclaw-user-guide`, such as a contributor PR-creation request that should select `nemoclaw-contributor-create-pr` or a maintainer review request that should not select the user guide, then refresh the benchmark summary to include the negative-task count.

Review findings by urgency: 0 required fixes, 0 items to resolve/justify, 1 in-scope improvement

⚠️ Resolve or justify before merge

Investigate these in the current review; either fix them, explain why they are not applicable, or document the accepted risk.

None.

💡 In-scope improvements

These are lower-risk, not throwaway. Prefer fixing them in this PR when they are local to changed code; defer only with rationale or a linked follow-up.

`PRA-1` Improvement — Add a negative activation eval for the broad user-guide skill

Location: skills/nemoclaw-user-guide/BENCHMARK.md:47
Category: tests
Problem: The new `nemoclaw-user-guide` intentionally replaces ten narrower user skills with one broad routing skill, but the checked-in benchmark records five positive activation tasks and zero negative tasks. The positive evals cover install, MCP setup, Hermes routing, local inference, and network-policy troubleshooting, but they do not prove the broad trigger wording stays out of contributor, maintainer, code-review, or unrelated documentation workflows.
Impact: An over-broad catalog skill can be selected for the wrong workflow and route an agent to end-user docs when a contributor or maintainer skill should own the task, reducing answer quality and possibly bypassing stricter workflow guidance in those dedicated skills.
Suggested action: Add one local negative or decoy eval for `nemoclaw-user-guide`, such as a contributor PR-creation request that should select `nemoclaw-contributor-create-pr` or a maintainer review request that should not select the user guide, then refresh the benchmark summary to include the negative-task count.
Expected follow-up: Prefer a current-PR fix when local to changed code; defer only with rationale or linked follow-up.
Verification: Read `skills/nemoclaw-user-guide/evals/evals.json` and `skills/nemoclaw-user-guide/BENCHMARK.md`; the shortest check is that at least one eval exercises a non-user-guide expected skill or `expected_skill: null`, and the benchmark no longer says `Negative tasks: 0 tasks`.
Missing regression test: Add an NVSkills eval named for the behavior, for example `nemoclaw-user-guide-does-not-handle-contributor-pr-workflow`, with a prompt about creating or reviewing a PR and an expected outcome that does not activate `nemoclaw-user-guide`.
Done when: The local improvement is applied, or the PR notes why it should be deferred.
Evidence: `skills/nemoclaw-user-guide/evals/evals.json` contains five entries, all with `expected_skill: "nemoclaw-user-guide"`; `skills/nemoclaw-user-guide/BENCHMARK.md` says `Positive tasks: 5 tasks where the skill was expected to activate` and `Negative tasks: 0 tasks where no skill was expected`.

Test follow-ups to resolve or justify

If these cover changed behavior, prefer adding them in this PR; otherwise state why existing coverage is enough or link the follow-up.

PRA-T1 Add a negative activation eval for the broad user-guide skill — Add one local negative or decoy eval for `nemoclaw-user-guide`, such as a contributor PR-creation request that should select `nemoclaw-contributor-create-pr` or a maintainer review request that should not select the user guide, then refresh the benchmark summary to include the negative-task count.

Since last review details

Current findings, using the urgency labels above:

`PRA-1` Improvement — Add a negative activation eval for the broad user-guide skill

Location: skills/nemoclaw-user-guide/BENCHMARK.md:47
Category: tests
Problem: The new `nemoclaw-user-guide` intentionally replaces ten narrower user skills with one broad routing skill, but the checked-in benchmark records five positive activation tasks and zero negative tasks. The positive evals cover install, MCP setup, Hermes routing, local inference, and network-policy troubleshooting, but they do not prove the broad trigger wording stays out of contributor, maintainer, code-review, or unrelated documentation workflows.
Impact: An over-broad catalog skill can be selected for the wrong workflow and route an agent to end-user docs when a contributor or maintainer skill should own the task, reducing answer quality and possibly bypassing stricter workflow guidance in those dedicated skills.
Suggested action: Add one local negative or decoy eval for `nemoclaw-user-guide`, such as a contributor PR-creation request that should select `nemoclaw-contributor-create-pr` or a maintainer review request that should not select the user guide, then refresh the benchmark summary to include the negative-task count.
Expected follow-up: Prefer a current-PR fix when local to changed code; defer only with rationale or linked follow-up.
Verification: Read `skills/nemoclaw-user-guide/evals/evals.json` and `skills/nemoclaw-user-guide/BENCHMARK.md`; the shortest check is that at least one eval exercises a non-user-guide expected skill or `expected_skill: null`, and the benchmark no longer says `Negative tasks: 0 tasks`.
Missing regression test: Add an NVSkills eval named for the behavior, for example `nemoclaw-user-guide-does-not-handle-contributor-pr-workflow`, with a prompt about creating or reviewing a PR and an expected outcome that does not activate `nemoclaw-user-guide`.
Done when: The local improvement is applied, or the PR notes why it should be deferred.
Evidence: `skills/nemoclaw-user-guide/evals/evals.json` contains five entries, all with `expected_skill: "nemoclaw-user-guide"`; `skills/nemoclaw-user-guide/BENCHMARK.md` says `Positive tasks: 5 tasks where the skill was expected to activate` and `Negative tasks: 0 tasks where no skill was expected`.

Workflow run details

This is an automated, non-binding review; it still expects maintainers and agents to respond to each required or warning item. Treat suggestions as current-PR improvements when they touch changed code; defer only with maintainer rationale or a linked follow-up. A human maintainer must make the final merge decision.

miyoungc · 2026-06-23T23:12:08Z

/nvskills-ci

miyoungc · 2026-06-23T23:48:58Z

/nvskills-ci

miyoungc · 2026-06-24T00:00:17Z

/nvskills-ci

Signed-off-by: nvskills-svc-account <svc-nvskills-signing@nvidia.com>

copy-pr-bot · 2026-06-24T00:11:12Z

This pull request requires additional validation before any workflows can run on NVIDIA's runners.

Pull request vetters can view their responsibilities here.

Contributors can view more details about this message here.

…o refactor-user-skills

miyoungc · 2026-06-24T01:04:08Z

/nvskills-ci

miyoungc · 2026-06-24T01:14:20Z

/nvskills-ci

miyoungc · 2026-06-24T01:14:44Z

merge after NVSKills CI finishes.

coderabbitai

Actionable comments posted: 6

🤖 Prompt for all review comments with AI agents

Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.

Inline comments:
In @.agents/skills/nemoclaw-user-guide/SKILL.md:
- Around line 1-6: The file SKILL.md is missing the required SPDX license header
comment at the very beginning. Add an SPDX license header using HTML comments
(format: <!-- SPDX-License-Identifier: Apache-2.0 -->) before the existing YAML
frontmatter that starts with the three dashes. This header must be placed on the
first line of the file to comply with the coding guidelines for Markdown files.

In `@skills/nemoclaw-user-guide/BENCHMARK.md`:
- Around line 1-6: The BENCHMARK.md file is missing the required SPDX license
header comment that must be included at the beginning of the file. Add the SPDX
license header as an HTML comment block at the very top of the BENCHMARK.md
file, before the existing markdown content that starts with "# Evaluation
Report". Ensure the header follows the standard SPDX format for Markdown files
using HTML comment syntax.

In `@skills/nemoclaw-user-guide/skill-card.md`:
- Around line 22-26: Remove the repository link entry from the skill card
Markdown file that violates the policy against linking to third-party code
repositories. Specifically, delete the line containing the NVIDIA OpenShell
GitHub repository link at https://github.com/NVIDIA/OpenShell, while keeping the
other official NVIDIA documentation references (NemoClaw AI Documentation Index,
OpenClaw User Guide Home, and Hermes User Guide Home) intact in the list.
- Around line 1-4: The skill-card.md file is missing the required SPDX license
header at the beginning of the file. Add an SPDX license header in HTML comment
format at the very top of the file, before the existing "## Description:"
content. The header should follow the format specified in your coding guidelines
for Markdown files using HTML comments to declare the license information.

In `@skills/nemoclaw-user-guide/SKILL.md`:
- Around line 1-6: The SKILL.md file is missing the mandatory SPDX license
header. Add HTML comment-formatted SPDX license header at the very beginning of
the file, before the existing YAML front matter (before the first ---). Use HTML
comments (<!-- -->) to wrap the SPDX license identifier and copyright
information according to the coding guidelines for Markdown files, ensuring the
Apache-2.0 license is properly declared.

In `@skills/nemoclaw-user-guide/skill.oms.sig`:
- Line 1: The DSSE payload in the signature bundle contains outdated digests for
the resources SKILL.md and evals/evals.json that no longer match their current
file contents. Regenerate the bundle by re-running the signing and bundling
process that creates this file to ensure all resource digests in the payload are
recalculated and match the actual current state of these files. This will update
the incorrect digest values in the payload while maintaining the proper bundle
structure and signatures.

🪄 Autofix (Beta)

Fix all unresolved CodeRabbit comments on this PR:

Push a commit to this branch (recommended)
Create a new PR with the fixes

ℹ️ Review info

⚙️ Run configuration

Configuration used: Path: .coderabbit.yaml

Review profile: CHILL

Plan: Enterprise

Run ID: 618b2880-395a-4c09-b44f-0db0ae81bbfd

📥 Commits

Reviewing files that changed from the base of the PR and between 9ad9b5d and dd7dba3.

⛔ Files ignored due to path filters (2)

.agents/skills/nemoclaw-user-overview/references/images/nemoclaw-highlevel-component-diagram.png is excluded by !**/*.png
skills/nemoclaw-user-overview/references/images/nemoclaw-highlevel-component-diagram.png is excluded by !**/*.png

📒 Files selected for processing (162)

.agents/skills/nemoclaw-contributor-create-pr/SKILL.md
.agents/skills/nemoclaw-contributor-update-docs/SKILL.md
.agents/skills/nemoclaw-maintainer-day/SKILL.md
.agents/skills/nemoclaw-skills-guide/SKILL.md
.agents/skills/nemoclaw-user-agent-skills/SKILL.md
.agents/skills/nemoclaw-user-agent-skills/evals/evals.json
.agents/skills/nemoclaw-user-configure-inference/SKILL.md
.agents/skills/nemoclaw-user-configure-inference/evals/evals.json
.agents/skills/nemoclaw-user-configure-inference/references/inference-options.md
.agents/skills/nemoclaw-user-configure-inference/references/set-up-sub-agent.md
.agents/skills/nemoclaw-user-configure-inference/references/switch-inference-providers.md
.agents/skills/nemoclaw-user-configure-inference/references/tool-calling-reliability.md
.agents/skills/nemoclaw-user-configure-security/SKILL.md
.agents/skills/nemoclaw-user-configure-security/evals/evals.json
.agents/skills/nemoclaw-user-configure-security/references/best-practices.md
.agents/skills/nemoclaw-user-configure-security/references/credential-storage.md
.agents/skills/nemoclaw-user-configure-security/references/openclaw-controls.md
.agents/skills/nemoclaw-user-deploy-remote/SKILL.md
.agents/skills/nemoclaw-user-deploy-remote/evals/evals.json
.agents/skills/nemoclaw-user-deploy-remote/references/brev-web-ui.md
.agents/skills/nemoclaw-user-deploy-remote/references/install-openclaw-plugins.md
.agents/skills/nemoclaw-user-deploy-remote/references/sandbox-hardening.md
.agents/skills/nemoclaw-user-get-started/SKILL.md
.agents/skills/nemoclaw-user-get-started/evals/evals.json
.agents/skills/nemoclaw-user-get-started/references/prerequisites.md
.agents/skills/nemoclaw-user-get-started/references/quickstart-hermes.md
.agents/skills/nemoclaw-user-get-started/references/windows-preparation.md
.agents/skills/nemoclaw-user-guide/SKILL.md
.agents/skills/nemoclaw-user-guide/evals/evals.json
.agents/skills/nemoclaw-user-manage-policy/SKILL.md
.agents/skills/nemoclaw-user-manage-policy/evals/evals.json
.agents/skills/nemoclaw-user-manage-policy/references/approve-network-requests.md
.agents/skills/nemoclaw-user-manage-policy/references/integration-policy-examples.md
.agents/skills/nemoclaw-user-manage-sandboxes/SKILL.md
.agents/skills/nemoclaw-user-manage-sandboxes/evals/evals.json
.agents/skills/nemoclaw-user-manage-sandboxes/references/backup-restore.md
.agents/skills/nemoclaw-user-manage-sandboxes/references/install-plugins-hermes.md
.agents/skills/nemoclaw-user-manage-sandboxes/references/messaging-channels.md
.agents/skills/nemoclaw-user-manage-sandboxes/references/runtime-controls.md
.agents/skills/nemoclaw-user-manage-sandboxes/references/workspace-files.md
.agents/skills/nemoclaw-user-monitor-sandbox/SKILL.md
.agents/skills/nemoclaw-user-monitor-sandbox/evals/evals.json
.agents/skills/nemoclaw-user-overview/SKILL.md
.agents/skills/nemoclaw-user-overview/evals/evals.json
.agents/skills/nemoclaw-user-overview/references/ecosystem-hermes.md
.agents/skills/nemoclaw-user-overview/references/ecosystem.md
.agents/skills/nemoclaw-user-overview/references/how-it-works.md
.agents/skills/nemoclaw-user-overview/references/overview.md
.agents/skills/nemoclaw-user-overview/references/release-notes.md
.agents/skills/nemoclaw-user-reference/SKILL.md
.agents/skills/nemoclaw-user-reference/evals/evals.json
.agents/skills/nemoclaw-user-reference/references/architecture.md
.agents/skills/nemoclaw-user-reference/references/cli-selection-guide.md
.agents/skills/nemoclaw-user-reference/references/commands.md
.agents/skills/nemoclaw-user-reference/references/network-policies.md
.agents/skills/nemoclaw-user-reference/references/troubleshooting.md
.github/ISSUE_TEMPLATE/bug_report.yml
.github/actions/ci-static-checks/action.yaml
.github/catalog-skills-signing-flow.md
.pre-commit-config.yaml
AGENTS.md
CONTRIBUTING.md
docs/AGENTS.md
docs/CONTRIBUTING.md
docs/_components/StarterPromptButton.tsx
docs/about/overview.mdx
docs/about/release-notes.mdx
docs/get-started/prerequisites.mdx
docs/get-started/quickstart.mdx
docs/index.mdx
docs/index.yml
docs/resources/agent-skills.mdx
fern/fern.config.json
scripts/docs-to-skills.py
skills/README.md
skills/catalog-metadata.json
skills/nemoclaw-user-agent-skills/BENCHMARK.md
skills/nemoclaw-user-agent-skills/SKILL.md
skills/nemoclaw-user-agent-skills/evals/evals.json
skills/nemoclaw-user-agent-skills/references/agent-skills.md
skills/nemoclaw-user-agent-skills/skill-card.md
skills/nemoclaw-user-agent-skills/skill.oms.sig
skills/nemoclaw-user-configure-inference/BENCHMARK.md
skills/nemoclaw-user-configure-inference/SKILL.md
skills/nemoclaw-user-configure-inference/evals/evals.json
skills/nemoclaw-user-configure-inference/references/inference-options.md
skills/nemoclaw-user-configure-inference/references/set-up-sub-agent.md
skills/nemoclaw-user-configure-inference/references/switch-inference-providers.md
skills/nemoclaw-user-configure-inference/references/tool-calling-reliability.md
skills/nemoclaw-user-configure-inference/skill-card.md
skills/nemoclaw-user-configure-inference/skill.oms.sig
skills/nemoclaw-user-configure-security/BENCHMARK.md
skills/nemoclaw-user-configure-security/SKILL.md
skills/nemoclaw-user-configure-security/evals/evals.json
skills/nemoclaw-user-configure-security/references/best-practices.md
skills/nemoclaw-user-configure-security/references/credential-storage.md
skills/nemoclaw-user-configure-security/references/openclaw-controls.md
skills/nemoclaw-user-configure-security/skill-card.md
skills/nemoclaw-user-configure-security/skill.oms.sig
skills/nemoclaw-user-deploy-remote/BENCHMARK.md
skills/nemoclaw-user-deploy-remote/SKILL.md
skills/nemoclaw-user-deploy-remote/evals/evals.json
skills/nemoclaw-user-deploy-remote/references/brev-web-ui.md
skills/nemoclaw-user-deploy-remote/references/install-openclaw-plugins.md
skills/nemoclaw-user-deploy-remote/references/sandbox-hardening.md
skills/nemoclaw-user-deploy-remote/skill-card.md
skills/nemoclaw-user-deploy-remote/skill.oms.sig
skills/nemoclaw-user-get-started/BENCHMARK.md
skills/nemoclaw-user-get-started/SKILL.md
skills/nemoclaw-user-get-started/evals/evals.json
skills/nemoclaw-user-get-started/references/prerequisites.md
skills/nemoclaw-user-get-started/references/quickstart-details.md
skills/nemoclaw-user-get-started/references/quickstart-hermes.md
skills/nemoclaw-user-get-started/references/windows-preparation.md
skills/nemoclaw-user-get-started/skill-card.md
skills/nemoclaw-user-get-started/skill.oms.sig
skills/nemoclaw-user-guide/BENCHMARK.md
skills/nemoclaw-user-guide/SKILL.md
skills/nemoclaw-user-guide/evals/evals.json
skills/nemoclaw-user-guide/skill-card.md
skills/nemoclaw-user-guide/skill.oms.sig
skills/nemoclaw-user-manage-policy/BENCHMARK.md
skills/nemoclaw-user-manage-policy/SKILL.md
skills/nemoclaw-user-manage-policy/evals/evals.json
skills/nemoclaw-user-manage-policy/references/approve-network-requests.md
skills/nemoclaw-user-manage-policy/references/customize-network-policy-details.md
skills/nemoclaw-user-manage-policy/references/integration-policy-examples.md
skills/nemoclaw-user-manage-policy/skill-card.md
skills/nemoclaw-user-manage-policy/skill.oms.sig
skills/nemoclaw-user-manage-sandboxes/BENCHMARK.md
skills/nemoclaw-user-manage-sandboxes/SKILL.md
skills/nemoclaw-user-manage-sandboxes/evals/evals.json
skills/nemoclaw-user-manage-sandboxes/references/backup-restore.md
skills/nemoclaw-user-manage-sandboxes/references/lifecycle-details.md
skills/nemoclaw-user-manage-sandboxes/references/messaging-channels.md
skills/nemoclaw-user-manage-sandboxes/references/runtime-controls.md
skills/nemoclaw-user-manage-sandboxes/references/workspace-files.md
skills/nemoclaw-user-manage-sandboxes/skill-card.md
skills/nemoclaw-user-manage-sandboxes/skill.oms.sig
skills/nemoclaw-user-monitor-sandbox/BENCHMARK.md
skills/nemoclaw-user-monitor-sandbox/SKILL.md
skills/nemoclaw-user-monitor-sandbox/evals/evals.json
skills/nemoclaw-user-monitor-sandbox/skill-card.md
skills/nemoclaw-user-overview/BENCHMARK.md
skills/nemoclaw-user-overview/SKILL.md
skills/nemoclaw-user-overview/evals/evals.json
skills/nemoclaw-user-overview/references/ecosystem.md
skills/nemoclaw-user-overview/references/how-it-works.md
skills/nemoclaw-user-overview/references/overview.md
skills/nemoclaw-user-overview/references/release-notes.md
skills/nemoclaw-user-overview/skill-card.md
skills/nemoclaw-user-overview/skill.oms.sig
skills/nemoclaw-user-reference/SKILL.md
skills/nemoclaw-user-reference/evals/evals.json
skills/nemoclaw-user-reference/references/architecture.md
skills/nemoclaw-user-reference/references/cli-selection-guide.md
skills/nemoclaw-user-reference/references/commands.md
skills/nemoclaw-user-reference/references/network-policies.md
skills/nemoclaw-user-reference/references/troubleshooting.md
skills/nemoclaw-user-reference/skill.oms.sig
src/lib/messaging/AGENTS.md
test/skills-frontmatter.test.ts

💤 Files with no reviewable changes (101)

.agents/skills/nemoclaw-user-deploy-remote/references/sandbox-hardening.md
.agents/skills/nemoclaw-user-overview/evals/evals.json
skills/nemoclaw-user-manage-policy/evals/evals.json
.agents/skills/nemoclaw-user-manage-policy/references/approve-network-requests.md
.agents/skills/nemoclaw-user-reference/references/cli-selection-guide.md
.agents/skills/nemoclaw-user-monitor-sandbox/SKILL.md
.agents/skills/nemoclaw-user-monitor-sandbox/evals/evals.json
.agents/skills/nemoclaw-user-get-started/SKILL.md
skills/nemoclaw-user-get-started/references/prerequisites.md
skills/catalog-metadata.json
skills/nemoclaw-user-agent-skills/SKILL.md
skills/nemoclaw-user-manage-policy/references/customize-network-policy-details.md
skills/nemoclaw-user-manage-policy/references/approve-network-requests.md
skills/nemoclaw-user-agent-skills/evals/evals.json
skills/nemoclaw-user-configure-inference/skill-card.md
skills/nemoclaw-user-get-started/references/quickstart-hermes.md
skills/nemoclaw-user-manage-policy/skill-card.md
.agents/skills/nemoclaw-user-manage-sandboxes/references/runtime-controls.md
.agents/skills/nemoclaw-user-agent-skills/SKILL.md
.agents/skills/nemoclaw-user-manage-policy/evals/evals.json
skills/nemoclaw-user-deploy-remote/references/brev-web-ui.md
skills/nemoclaw-user-configure-inference/BENCHMARK.md
skills/nemoclaw-user-get-started/skill-card.md
skills/nemoclaw-user-agent-skills/BENCHMARK.md
.agents/skills/nemoclaw-user-manage-policy/SKILL.md
.agents/skills/nemoclaw-user-overview/references/ecosystem.md
.agents/skills/nemoclaw-user-reference/references/architecture.md
skills/nemoclaw-user-manage-policy/SKILL.md
.agents/skills/nemoclaw-user-reference/references/troubleshooting.md
.agents/skills/nemoclaw-user-reference/references/network-policies.md
.agents/skills/nemoclaw-user-overview/references/how-it-works.md
.agents/skills/nemoclaw-user-overview/references/overview.md
skills/nemoclaw-user-deploy-remote/skill-card.md
.agents/skills/nemoclaw-user-configure-security/references/best-practices.md
.agents/skills/nemoclaw-user-configure-inference/references/set-up-sub-agent.md
skills/nemoclaw-user-agent-skills/skill-card.md
.agents/skills/nemoclaw-user-overview/SKILL.md
skills/nemoclaw-user-deploy-remote/references/sandbox-hardening.md
skills/nemoclaw-user-configure-inference/references/inference-options.md
.agents/skills/nemoclaw-user-get-started/references/prerequisites.md
skills/nemoclaw-user-get-started/evals/evals.json
skills/nemoclaw-user-configure-security/references/best-practices.md
.agents/skills/nemoclaw-user-reference/evals/evals.json
skills/nemoclaw-user-get-started/SKILL.md
.agents/skills/nemoclaw-user-manage-sandboxes/references/workspace-files.md
skills/nemoclaw-user-manage-policy/BENCHMARK.md
skills/nemoclaw-user-get-started/skill.oms.sig
skills/nemoclaw-user-deploy-remote/SKILL.md
.agents/skills/nemoclaw-user-configure-inference/references/tool-calling-reliability.md
skills/nemoclaw-user-configure-security/evals/evals.json
.agents/skills/nemoclaw-user-configure-inference/SKILL.md
skills/nemoclaw-user-configure-security/skill-card.md
.agents/skills/nemoclaw-user-deploy-remote/references/brev-web-ui.md
.agents/skills/nemoclaw-user-manage-sandboxes/references/messaging-channels.md
skills/nemoclaw-user-manage-policy/references/integration-policy-examples.md
.agents/skills/nemoclaw-user-manage-sandboxes/evals/evals.json
skills/nemoclaw-user-deploy-remote/references/install-openclaw-plugins.md
.agents/skills/nemoclaw-user-get-started/evals/evals.json
.agents/skills/nemoclaw-user-configure-security/evals/evals.json
skills/nemoclaw-user-configure-inference/SKILL.md
skills/nemoclaw-user-manage-sandboxes/BENCHMARK.md
.agents/skills/nemoclaw-user-configure-inference/references/inference-options.md
skills/nemoclaw-user-configure-inference/evals/evals.json
skills/nemoclaw-user-deploy-remote/BENCHMARK.md
skills/nemoclaw-user-deploy-remote/evals/evals.json
.agents/skills/nemoclaw-user-configure-security/SKILL.md
.agents/skills/nemoclaw-user-deploy-remote/evals/evals.json
.agents/skills/nemoclaw-user-deploy-remote/SKILL.md
skills/nemoclaw-user-get-started/references/windows-preparation.md
skills/nemoclaw-user-configure-inference/references/set-up-sub-agent.md
.agents/skills/nemoclaw-user-manage-sandboxes/references/install-plugins-hermes.md
skills/nemoclaw-user-configure-inference/skill.oms.sig
.agents/skills/nemoclaw-user-get-started/references/windows-preparation.md
skills/nemoclaw-user-configure-inference/references/switch-inference-providers.md
skills/nemoclaw-user-configure-security/references/openclaw-controls.md
skills/nemoclaw-user-get-started/BENCHMARK.md
skills/nemoclaw-user-agent-skills/references/agent-skills.md
skills/nemoclaw-user-configure-security/SKILL.md
.agents/skills/nemoclaw-user-configure-security/references/credential-storage.md
.agents/skills/nemoclaw-user-configure-inference/evals/evals.json
skills/nemoclaw-user-configure-security/references/credential-storage.md
skills/nemoclaw-user-configure-security/BENCHMARK.md
.agents/skills/nemoclaw-user-reference/SKILL.md
.agents/skills/nemoclaw-user-overview/references/release-notes.md
.agents/skills/nemoclaw-user-configure-security/references/openclaw-controls.md
skills/nemoclaw-user-get-started/references/quickstart-details.md
skills/nemoclaw-user-configure-security/skill.oms.sig
.agents/skills/nemoclaw-user-get-started/references/quickstart-hermes.md
skills/nemoclaw-user-agent-skills/skill.oms.sig
.agents/skills/nemoclaw-user-manage-policy/references/integration-policy-examples.md
skills/nemoclaw-user-manage-policy/skill.oms.sig
.agents/skills/nemoclaw-user-configure-inference/references/switch-inference-providers.md
.agents/skills/nemoclaw-user-deploy-remote/references/install-openclaw-plugins.md
.agents/skills/nemoclaw-user-overview/references/ecosystem-hermes.md
skills/nemoclaw-user-configure-inference/references/tool-calling-reliability.md
skills/nemoclaw-user-deploy-remote/skill.oms.sig
docs/_components/StarterPromptButton.tsx
.agents/skills/nemoclaw-user-manage-sandboxes/SKILL.md
.agents/skills/nemoclaw-user-manage-sandboxes/references/backup-restore.md
.agents/skills/nemoclaw-user-agent-skills/evals/evals.json
scripts/docs-to-skills.py

Signed-off-by: nvskills-svc-account <svc-nvskills-signing@nvidia.com>

coderabbitai

♻️ Duplicate comments (1)

skills/nemoclaw-user-guide/skill-card.md (1)
1-4: 📐 Maintainability & Code Quality | 🟡 Minor | ⚡ Quick win

Add the required SPDX license header to the Markdown file.

This file is still missing the mandatory SPDX license header comments at the very top. As per coding guidelines, all Markdown files must include an SPDX license header using HTML comments.
Suggested fix
+
+
+
 ## Description: <br>
🤖 Prompt for AI Agents
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.

In `@skills/nemoclaw-user-guide/skill-card.md` around lines 1 - 4, The
skill-card.md file is missing the mandatory SPDX license header that must appear
at the very beginning of the file. Add an SPDX license header using HTML comment
syntax at the top of the file, before the "## Description:" section. The header
should follow your project's standard SPDX license format as defined in your
coding guidelines and should be placed before any other content in the Markdown
file.
Source: Coding guidelines

🤖 Prompt for all review comments with AI agents

Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.

Duplicate comments:
In `@skills/nemoclaw-user-guide/skill-card.md`:
- Around line 1-4: The skill-card.md file is missing the mandatory SPDX license
header that must appear at the very beginning of the file. Add an SPDX license
header using HTML comment syntax at the top of the file, before the "##
Description:" section. The header should follow your project's standard SPDX
license format as defined in your coding guidelines and should be placed before
any other content in the Markdown file.

ℹ️ Review info

⚙️ Run configuration

Configuration used: Path: .coderabbit.yaml

Review profile: CHILL

Plan: Enterprise

Run ID: d57f6a44-283f-4c4b-a380-756b57fb550a

📥 Commits

Reviewing files that changed from the base of the PR and between dd7dba3 and 442c25a.

📒 Files selected for processing (3)

skills/nemoclaw-user-guide/BENCHMARK.md
skills/nemoclaw-user-guide/skill-card.md
skills/nemoclaw-user-guide/skill.oms.sig

✅ Files skipped from review due to trivial changes (1)

skills/nemoclaw-user-guide/BENCHMARK.md

🚧 Files skipped from review as they are similar to previous changes (1)

skills/nemoclaw-user-guide/skill.oms.sig

) ## Summary Adds the canonical launch-claims matrix for NemoClaw at \`docs/reference/platform-support.mdx\`, driven by \`ci/platform-matrix.json\` through a hardened generator. Single source of truth for what NemoClaw supports today. ## Related Issue Closes #4630. **Supersedes #5345** (closed; that branch carried a heavy docs-to-skills regen tangle that became untenable after main retired the docs-to-skills system in #5699). ## Why a new PR #5345 was open for two weeks while main moved significantly. The most disruptive change was #5699 (\"retire docs-to-skills\") which deleted the regeneration tool and the entire user-skill tree this PR's pre-restart branch was modifying. Reconciling against the new structure would have required reverting half the PR's value and re-baselining against current main. Branching fresh off main is the cleaner path. The audit, evidence, and advisor-loop work from #5345 carries forward through this PR's content — only the diff history was reset. ## What this lands - **\`ci/platform-matrix.json\`** — expanded to cover platforms, providers, agents, integrations, deployment paths, capabilities, and out-of-scope items. Every status follows the declared vocabulary (\`Tested\` / \`Tested with limitations\` / \`Experimental\` / \`Deferred\` / \`Unsupported\` / \`Hermes only\`). Rows carry file:line evidence citations. - **\`docs/reference/platform-support.mdx\`** — new canonical page rendered from the JSON through sentinel-comment regeneration. Includes a project-status block and an Owners section reflecting the engineering-owner model (no separate product-owner role today). - **\`scripts/generate-platform-docs.py\`** — hardened generator: - \`_validate_matrix\` rejects missing required keys, unknown statuses, and placeholder owner values (\`TBD\`, \`TODO\`, \`FIXME\`, \`see PR review\`, empty) - \`_escape_cell\` escapes pipes, newlines, HTML control characters, and MDX expression braces in every emitted cell - Full table generators for agents, capabilities, integrations, deployment paths, out-of-scope, and the canonical platform/provider tables; partial views for prerequisites and inference-options - **\`docs/get-started/prerequisites.mdx\` + \`docs/inference/inference-options.mdx\`** — partial tables re-rendered from the JSON so onboarding-time docs use the same vocabulary. - **\`test/generate-platform-docs.test.ts\`** — regression coverage for escaping, status vocabulary, placeholder owner rejection, partial-vs-full deferred filtering, owners-block shape, agent-ID resolution against installed manifests, out-of-scope LangChain exception scoping, and file:line citation existence. ## Verification - \`npx vitest run test/generate-platform-docs.test.ts\` — 13/13 pass - \`python3 scripts/generate-platform-docs.py --check\` — all files in sync - Generator and tests verified against current \`main\` after rebase ## Type of Change - [ ] Code change (feature, bug fix, or refactor) - [ ] Code change with doc updates - [x] Doc only (prose changes, no code sample modifications) - [ ] Doc only (includes code sample changes) ## Advisor state 0 required findings. 2 advisory warnings on deeper matrix schema validation — not pursuing; the right form is a JSON Schema, tracking as follow-up.  ## Summary by CodeRabbit * **Documentation** * Added the “Platform Support and Launch Claims” reference page with a shared status vocabulary and expanded, JSON-driven launch matrices (agents, platforms, providers, integrations, deployment paths, capabilities), including out-of-scope items and caveats/blockers guidance. * Refined platform/inference documentation to better reflect validated adapter paths, API shapes, and supported distro/runtime assumptions (e.g., Linux|Docker). * **Tests** * Expanded generator end-to-end/regression coverage for table escaping, matrix validation, output variants, and repository consistency checks. * **Chores** * Updated the platform-matrix sync pre-commit trigger when the generated platform-support docs change.  --------- Signed-off-by: Charan Jagwani <cjagwani@nvidia.com>

## Summary Refresh the docs for the v0.0.67 release using the GitHub announcement and release-range commit scan. ## Changes - Add v0.0.67 release notes for onboarding recovery, Discord proxy behavior, OpenClaw agent apply deletion, and compact AI-agent docs routing. - Clarify `onboard --resume` repair checks in the OpenClaw and Hermes command references. - Clarify Discord's managed proxy path and `agents apply` delete behavior in the relevant docs pages. ## Source Summary - #5699 -> `docs/resources/agent-skills.mdx`, `docs/about/release-notes.mdx`: Reflects the compact `nemoclaw-user-guide` docs-routing skill and canonical MCP/Markdown docs entry points. - #5571 -> `docs/manage-sandboxes/messaging-channels.mdx`, `docs/about/release-notes.mdx`: Documents Discord using the managed proxy path instead of a rejected per-account proxy. - #5704 -> `docs/about/release-notes.mdx`: Captures the WhatsApp policy assertion hardening in the release note context. - Follow-up commit `46ead831e` -> `docs/reference/commands.mdx`, `docs/reference/commands-nemohermes.mdx`, `docs/about/release-notes.mdx`: Documents resume repair checks across later nonterminal onboarding phases. - Follow-up commit `ee0725a32` -> `docs/reference/commands.mdx`, `docs/about/release-notes.mdx`: Documents that `agents apply` uses OpenClaw's confirmation-skipping delete mode for orphan agents. ## Type of Change - [ ] Code change (feature, bug fix, or refactor) - [ ] Code change with doc updates - [x] Doc only (prose changes, no code sample modifications) - [ ] Doc only (includes code sample changes) ## Verification - [x] PR description includes the DCO sign-off declaration and every commit appears as `Verified` in GitHub - [x] Git hooks passed during commit and push, or `npx prek run --from-ref main --to-ref HEAD` passes - [x] Targeted tests pass for changed behavior - [ ] Full `npm test` passes (broad runtime changes only) - [ ] Tests added or updated for new or changed behavior - [x] No secrets, API keys, or credentials committed - [x] Docs updated for user-facing behavior changes - [ ] `npm run docs` builds without warnings (doc changes only) - [x] Doc pages follow the [style guide](https://github.com/NVIDIA/NemoClaw/blob/main/docs/CONTRIBUTING.md) (doc changes only) - [ ] New doc pages include SPDX header and frontmatter (new pages only) Verification run: - `bash test/e2e/e2e-cloud-experimental/check-docs.sh --only-cli` passed. - `npm run docs` passed with the pre-existing Fern light-mode accent contrast warning: `The contrast ratio between the accent color and the background color for light mode is 2.41:1. It should be at least 3:1.` --- Signed-off-by: Miyoung Choi <miyoungc@nvidia.com>  ## Summary by CodeRabbit * **Documentation** * Added release notes for v0.0.67 covering onboarding recovery, messaging reliability, OpenClaw agent workflows, and AI-agent documentation routing. * Clarified Discord channel requirements, including routing through the top-level managed proxy. * Updated onboarding resume guidance to note rerunning preflight, gateway, provider, and sandbox repair checks. * Refined CLI command reference details for orphan-agent deletion behavior and how interactive flags affect prompts vs. deletion.

…IA#5699)  ## Summary This PR retires the generated docs-to-skills pipeline and replaces the expanded generated user skill catalog with one compact `nemoclaw-user-guide` skill. The guide routes AI agents to canonical NemoClaw documentation through the docs MCP server, `llms.txt`, and variant-specific Markdown pages while keeping contributor and maintainer skills intact. ## Changes - Remove `scripts/docs-to-skills.py`, the generated `.agents/skills/nemoclaw-user-*` trees, generated root `skills/nemoclaw-user-*` exports, and generated catalog metadata. - Add `nemoclaw-user-guide` as the single customer-facing user skill under `.agents/skills/`, with matching evals and a hard-copy root `skills/nemoclaw-user-guide` catalog publication copy. - Refresh the root catalog copy through NVSkills signing and document the hard-copy catalog refresh flow. - Update the AI Agent Docs page with the starter prompt button, the NemoClaw docs MCP server URL, Claude Code/Cursor setup guidance, `llms.txt`, and specific `.md` docs routes without the deprecated `llms-full.txt` path. - Update agent guides, contributor docs, PR/issue guidance, catalog signing notes, and CI/static checks to reference Markdown/MCP docs routing instead of generated user-skill refreshes. - Retarget the skill frontmatter test to validate checked-in `SKILL.md` files, guard the single root `skills/` catalog surface, and verify the catalog copy matches the `.agents/skills/nemoclaw-user-guide` source files while allowing NVSkills signing artifacts. ## Type of Change - [ ] Code change (feature, bug fix, or refactor) - [x] Code change with doc updates - [ ] Doc only (prose changes, no code sample modifications) - [ ] Doc only (includes code sample changes) ## Verification  - [ ] PR description includes the DCO sign-off declaration and every commit appears as `Verified` in GitHub - [x] Git hooks passed during commit and push, or `npx prek run --from-ref main --to-ref HEAD` passes - [x] Targeted tests pass for changed behavior - [ ] Full `npm test` passes (broad runtime changes only) - [x] Tests added or updated for new or changed behavior - [x] No secrets, API keys, or credentials committed - [x] Docs updated for user-facing behavior changes - [ ] `npm run docs` builds without warnings (doc changes only) - [x] Doc pages follow the [style guide](https://github.com/NVIDIA/NemoClaw/blob/main/docs/CONTRIBUTING.md) (doc changes only) - [ ] New doc pages include SPDX header and frontmatter (new pages only) ---  Signed-off-by: Miyoung Choi <miyoungc@nvidia.com>  ## Summary by CodeRabbit * **New Features** * Introduced `nemoclaw-user-guide` for consolidated AI-agent documentation routing via an MCP docs server, with fallback to Markdown indexing. * **Documentation** * Updated terminology from “Agent Skills” to “AI Agent Docs” across user-facing materials. * Refreshed docs refresh/release workflow and the Verified Skills catalog publishing guidance. * **Deprecations/Removals** * Removed several user-focused skills and their related documentation/evaluation content, consolidating guidance into the user guide. * **Refactor** * Streamlined the workflow to prioritize canonical Markdown docs sources.  --------- Signed-off-by: nvskills-svc-account <svc-nvskills-signing@nvidia.com> Co-authored-by: nvskills-svc-account <svc-nvskills-signing@nvidia.com> Signed-off-by: Hadar Cohen <hacohen@redhat.com>

…IA#5699)  ## Summary This PR retires the generated docs-to-skills pipeline and replaces the expanded generated user skill catalog with one compact `nemoclaw-user-guide` skill. The guide routes AI agents to canonical NemoClaw documentation through the docs MCP server, `llms.txt`, and variant-specific Markdown pages while keeping contributor and maintainer skills intact. ## Changes - Remove `scripts/docs-to-skills.py`, the generated `.agents/skills/nemoclaw-user-*` trees, generated root `skills/nemoclaw-user-*` exports, and generated catalog metadata. - Add `nemoclaw-user-guide` as the single customer-facing user skill under `.agents/skills/`, with matching evals and a hard-copy root `skills/nemoclaw-user-guide` catalog publication copy. - Refresh the root catalog copy through NVSkills signing and document the hard-copy catalog refresh flow. - Update the AI Agent Docs page with the starter prompt button, the NemoClaw docs MCP server URL, Claude Code/Cursor setup guidance, `llms.txt`, and specific `.md` docs routes without the deprecated `llms-full.txt` path. - Update agent guides, contributor docs, PR/issue guidance, catalog signing notes, and CI/static checks to reference Markdown/MCP docs routing instead of generated user-skill refreshes. - Retarget the skill frontmatter test to validate checked-in `SKILL.md` files, guard the single root `skills/` catalog surface, and verify the catalog copy matches the `.agents/skills/nemoclaw-user-guide` source files while allowing NVSkills signing artifacts. ## Type of Change - [ ] Code change (feature, bug fix, or refactor) - [x] Code change with doc updates - [ ] Doc only (prose changes, no code sample modifications) - [ ] Doc only (includes code sample changes) ## Verification  - [ ] PR description includes the DCO sign-off declaration and every commit appears as `Verified` in GitHub - [x] Git hooks passed during commit and push, or `npx prek run --from-ref main --to-ref HEAD` passes - [x] Targeted tests pass for changed behavior - [ ] Full `npm test` passes (broad runtime changes only) - [x] Tests added or updated for new or changed behavior - [x] No secrets, API keys, or credentials committed - [x] Docs updated for user-facing behavior changes - [ ] `npm run docs` builds without warnings (doc changes only) - [x] Doc pages follow the [style guide](https://github.com/NVIDIA/NemoClaw/blob/main/docs/CONTRIBUTING.md) (doc changes only) - [ ] New doc pages include SPDX header and frontmatter (new pages only) ---  Signed-off-by: Miyoung Choi <miyoungc@nvidia.com>  ## Summary by CodeRabbit * **New Features** * Introduced `nemoclaw-user-guide` for consolidated AI-agent documentation routing via an MCP docs server, with fallback to Markdown indexing. * **Documentation** * Updated terminology from “Agent Skills” to “AI Agent Docs” across user-facing materials. * Refreshed docs refresh/release workflow and the Verified Skills catalog publishing guidance. * **Deprecations/Removals** * Removed several user-focused skills and their related documentation/evaluation content, consolidating guidance into the user guide. * **Refactor** * Streamlined the workflow to prioritize canonical Markdown docs sources.  --------- Signed-off-by: nvskills-svc-account <svc-nvskills-signing@nvidia.com> Co-authored-by: nvskills-svc-account <svc-nvskills-signing@nvidia.com>

… (NVIDIA#5712) ## Summary Adds the canonical launch-claims matrix for NemoClaw at \`docs/reference/platform-support.mdx\`, driven by \`ci/platform-matrix.json\` through a hardened generator. Single source of truth for what NemoClaw supports today. ## Related Issue Closes NVIDIA#4630. **Supersedes NVIDIA#5345** (closed; that branch carried a heavy docs-to-skills regen tangle that became untenable after main retired the docs-to-skills system in NVIDIA#5699). ## Why a new PR NVIDIA#5345 was open for two weeks while main moved significantly. The most disruptive change was NVIDIA#5699 (\"retire docs-to-skills\") which deleted the regeneration tool and the entire user-skill tree this PR's pre-restart branch was modifying. Reconciling against the new structure would have required reverting half the PR's value and re-baselining against current main. Branching fresh off main is the cleaner path. The audit, evidence, and advisor-loop work from NVIDIA#5345 carries forward through this PR's content — only the diff history was reset. ## What this lands - **\`ci/platform-matrix.json\`** — expanded to cover platforms, providers, agents, integrations, deployment paths, capabilities, and out-of-scope items. Every status follows the declared vocabulary (\`Tested\` / \`Tested with limitations\` / \`Experimental\` / \`Deferred\` / \`Unsupported\` / \`Hermes only\`). Rows carry file:line evidence citations. - **\`docs/reference/platform-support.mdx\`** — new canonical page rendered from the JSON through sentinel-comment regeneration. Includes a project-status block and an Owners section reflecting the engineering-owner model (no separate product-owner role today). - **\`scripts/generate-platform-docs.py\`** — hardened generator: - \`_validate_matrix\` rejects missing required keys, unknown statuses, and placeholder owner values (\`TBD\`, \`TODO\`, \`FIXME\`, \`see PR review\`, empty) - \`_escape_cell\` escapes pipes, newlines, HTML control characters, and MDX expression braces in every emitted cell - Full table generators for agents, capabilities, integrations, deployment paths, out-of-scope, and the canonical platform/provider tables; partial views for prerequisites and inference-options - **\`docs/get-started/prerequisites.mdx\` + \`docs/inference/inference-options.mdx\`** — partial tables re-rendered from the JSON so onboarding-time docs use the same vocabulary. - **\`test/generate-platform-docs.test.ts\`** — regression coverage for escaping, status vocabulary, placeholder owner rejection, partial-vs-full deferred filtering, owners-block shape, agent-ID resolution against installed manifests, out-of-scope LangChain exception scoping, and file:line citation existence. ## Verification - \`npx vitest run test/generate-platform-docs.test.ts\` — 13/13 pass - \`python3 scripts/generate-platform-docs.py --check\` — all files in sync - Generator and tests verified against current \`main\` after rebase ## Type of Change - [ ] Code change (feature, bug fix, or refactor) - [ ] Code change with doc updates - [x] Doc only (prose changes, no code sample modifications) - [ ] Doc only (includes code sample changes) ## Advisor state 0 required findings. 2 advisory warnings on deeper matrix schema validation — not pursuing; the right form is a JSON Schema, tracking as follow-up.  ## Summary by CodeRabbit * **Documentation** * Added the “Platform Support and Launch Claims” reference page with a shared status vocabulary and expanded, JSON-driven launch matrices (agents, platforms, providers, integrations, deployment paths, capabilities), including out-of-scope items and caveats/blockers guidance. * Refined platform/inference documentation to better reflect validated adapter paths, API shapes, and supported distro/runtime assumptions (e.g., Linux|Docker). * **Tests** * Expanded generator end-to-end/regression coverage for table escaping, matrix validation, output variants, and repository consistency checks. * **Chores** * Updated the platform-matrix sync pre-commit trigger when the generated platform-support docs change.  --------- Signed-off-by: Charan Jagwani <cjagwani@nvidia.com>

## Summary Refresh the docs for the v0.0.67 release using the GitHub announcement and release-range commit scan. ## Changes - Add v0.0.67 release notes for onboarding recovery, Discord proxy behavior, OpenClaw agent apply deletion, and compact AI-agent docs routing. - Clarify `onboard --resume` repair checks in the OpenClaw and Hermes command references. - Clarify Discord's managed proxy path and `agents apply` delete behavior in the relevant docs pages. ## Source Summary - NVIDIA#5699 -> `docs/resources/agent-skills.mdx`, `docs/about/release-notes.mdx`: Reflects the compact `nemoclaw-user-guide` docs-routing skill and canonical MCP/Markdown docs entry points. - NVIDIA#5571 -> `docs/manage-sandboxes/messaging-channels.mdx`, `docs/about/release-notes.mdx`: Documents Discord using the managed proxy path instead of a rejected per-account proxy. - NVIDIA#5704 -> `docs/about/release-notes.mdx`: Captures the WhatsApp policy assertion hardening in the release note context. - Follow-up commit `46ead831e` -> `docs/reference/commands.mdx`, `docs/reference/commands-nemohermes.mdx`, `docs/about/release-notes.mdx`: Documents resume repair checks across later nonterminal onboarding phases. - Follow-up commit `ee0725a32` -> `docs/reference/commands.mdx`, `docs/about/release-notes.mdx`: Documents that `agents apply` uses OpenClaw's confirmation-skipping delete mode for orphan agents. ## Type of Change - [ ] Code change (feature, bug fix, or refactor) - [ ] Code change with doc updates - [x] Doc only (prose changes, no code sample modifications) - [ ] Doc only (includes code sample changes) ## Verification - [x] PR description includes the DCO sign-off declaration and every commit appears as `Verified` in GitHub - [x] Git hooks passed during commit and push, or `npx prek run --from-ref main --to-ref HEAD` passes - [x] Targeted tests pass for changed behavior - [ ] Full `npm test` passes (broad runtime changes only) - [ ] Tests added or updated for new or changed behavior - [x] No secrets, API keys, or credentials committed - [x] Docs updated for user-facing behavior changes - [ ] `npm run docs` builds without warnings (doc changes only) - [x] Doc pages follow the [style guide](https://github.com/NVIDIA/NemoClaw/blob/main/docs/CONTRIBUTING.md) (doc changes only) - [ ] New doc pages include SPDX header and frontmatter (new pages only) Verification run: - `bash test/e2e/e2e-cloud-experimental/check-docs.sh --only-cli` passed. - `npm run docs` passed with the pre-existing Fern light-mode accent contrast warning: `The contrast ratio between the accent color and the background color for light mode is 2.41:1. It should be at least 3:1.` --- Signed-off-by: Miyoung Choi <miyoungc@nvidia.com>  ## Summary by CodeRabbit * **Documentation** * Added release notes for v0.0.67 covering onboarding recovery, messaging reliability, OpenClaw agent workflows, and AI-agent documentation routing. * Clarified Discord channel requirements, including routing through the top-level managed proxy. * Updated onboarding resume guidance to note rerunning preflight, gateway, provider, and sandbox repair checks. * Refined CLI command reference details for orphan-agent deletion behavior and how interactive flags affect prompts vs. deletion.

chore: retire docs-to-skills and make single compact user skill

bc1357c

chore: add evals

453aa55

miyoungc added v0.0.67 area: skills Skills, agent behaviors, prompts, or skill packaging labels Jun 23, 2026

chore: try hard copy

b6e1083

Attach NVSkills validation signatures

578b9da

Signed-off-by: nvskills-svc-account <svc-nvskills-signing@nvidia.com>

miyoungc added 3 commits June 23, 2026 17:40

chore: more clean-up

458799c

Merge branch 'refactor-user-skills' of github.com:NVIDIA/NemoClaw int…

d77881c

…o refactor-user-skills

test(skills): guard catalog user guide copy

b3dff3a

miyoungc marked this pull request as ready for review June 24, 2026 01:04

docs: minor edits

dd7dba3

coderabbitai Bot reviewed Jun 24, 2026

View reviewed changes

Attach NVSkills validation signatures

442c25a

Signed-off-by: nvskills-svc-account <svc-nvskills-signing@nvidia.com>

coderabbitai Bot reviewed Jun 24, 2026

View reviewed changes

jyaunches approved these changes Jun 24, 2026

View reviewed changes

miyoungc merged commit 1aa03d6 into main Jun 24, 2026
43 of 44 checks passed

miyoungc deleted the refactor-user-skills branch June 24, 2026 01:44

This was referenced Jun 24, 2026

docs(platform): publish canonical platform support matrix (#4630) #5712

Merged

docs(platform): publish canonical platform support matrix (#4630) #5345

Closed

miyoungc mentioned this pull request Jun 24, 2026

docs: refresh release notes for v0.0.67 #5749

Merged

14 tasks

Uh oh!

Conversation

miyoungc commented Jun 23, 2026 • edited by coderabbitai Bot Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Summary

Changes

Type of Change

Verification

Summary by CodeRabbit

Uh oh!

copy-pr-bot Bot commented Jun 23, 2026

Uh oh!

coderabbitai Bot commented Jun 23, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Walkthrough

Changes

Estimated code review effort

Possibly related PRs

Suggested labels

Suggested reviewers

Poem

Uh oh!

github-actions Bot commented Jun 23, 2026

Uh oh!

github-code-quality Bot commented Jun 23, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Code Coverage Overview

TypeScript / code-coverage/plugin

TypeScript / code-coverage/cli

Uh oh!

github-actions Bot commented Jun 23, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

E2E Advisor Recommendation

E2E Recommendation Advisor

Required E2E

Optional E2E

New E2E recommendations

Uh oh!

github-actions Bot commented Jun 23, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Vitest E2E Scenario Recommendation

Vitest E2E Scenario Advisor

Required Vitest E2E scenarios

Optional Vitest E2E scenarios

Relevant changed files

Uh oh!

github-actions Bot commented Jun 23, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

PR Review Advisor — No blocking findings

Action checklist

Findings index

⚠️ Resolve or justify before merge

💡 In-scope improvements

PRA-1 Improvement — Add a negative activation eval for the broad user-guide skill

PRA-1 Improvement — Add a negative activation eval for the broad user-guide skill

Uh oh!

miyoungc commented Jun 23, 2026

Uh oh!

miyoungc commented Jun 23, 2026

Uh oh!

miyoungc commented Jun 24, 2026

Uh oh!

copy-pr-bot Bot commented Jun 24, 2026

Uh oh!

miyoungc commented Jun 24, 2026

Uh oh!

miyoungc commented Jun 24, 2026

Uh oh!

miyoungc commented Jun 24, 2026

Uh oh!

coderabbitai Bot left a comment

Choose a reason for hiding this comment

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

coderabbitai Bot left a comment

miyoungc commented Jun 23, 2026 •

edited by coderabbitai Bot

Loading

coderabbitai Bot commented Jun 23, 2026 •

edited

Loading

github-code-quality Bot commented Jun 23, 2026 •

edited

Loading

github-actions Bot commented Jun 23, 2026 •

edited

Loading

github-actions Bot commented Jun 23, 2026 •

edited

Loading

github-actions Bot commented Jun 23, 2026 •

edited

Loading

`PRA-1` Improvement — Add a negative activation eval for the broad user-guide skill

`PRA-1` Improvement — Add a negative activation eval for the broad user-guide skill