Skip to content

feat(skills): complete maintainer skill set and extend aiq-research - #277

Merged
AjayThorve merged 4 commits into
NVIDIA-AI-Blueprints:developfrom
efajardo-nv:devskills-remaining
Jun 16, 2026
Merged

feat(skills): complete maintainer skill set and extend aiq-research#277
AjayThorve merged 4 commits into
NVIDIA-AI-Blueprints:developfrom
efajardo-nv:devskills-remaining

Conversation

@efajardo-nv

@efajardo-nv efajardo-nv commented Jun 16, 2026

Copy link
Copy Markdown
Collaborator

Overview

Adds the remaining AI-Q maintainer Agent Skills and extends the aiq-research
consumer skill, completing the maintainer skill set started in #269.

  • aiq-add-tool: maintainer skill for adding a general-purpose NAT-function
    tool under sources/FunctionBaseConfig schema, @register_function,
    wiring into an agent's tools list, and tests.
  • aiq-release-qa: maintainer skill for choosing and running the right
    validation (Python, frontend, docs, evals) for the surfaces a change touches,
    grounded in AGENTS.md and CONTRIBUTING.md.
  • aiq-prepare-pr: maintainer skill for branch scoping, DCO sign-off,
    filling the PR template with real evidence, and the copy-pr-bot CI/merge flow.
    Reuses aiq-release-qa for validation rather than duplicating.
  • aiq-research: adds report ask/redo follow-up usage to the consumer
    skill, reusing the existing auth, polling, and report-retrieval flow (no new
    helper-script commands).

Each maintainer skill is a real directory under .agents/skills/ with a
.claude/skills/ compatibility symlink. No deployed-product behavior changes —
these are guidance for coding agents working in the repo.

Validation

$ uv run python scripts/validate_skills.py .agents/skills
Skill validation passed: 6 skill(s) OK.

$ uv run pytest tests/test_agent_skills.py -q
4 passed

$ uv run pre-commit run --files <changed skill files>
Detect secrets...........................................................Passed
Validate agent skills....................................................Passed
Markdown Link Check......................................................Passed
  • I ran the relevant local checks or explained why they are not applicable.
  • I added or updated tests for behavior changes. (validator/pytest cover skill structure; skills are static markdown, no runtime code added)
  • I updated documentation for user-facing or contributor-facing changes. (the skills are the contributor-facing docs; canonical docs under docs/source/ unchanged)
  • I confirmed this PR does not include secrets, credentials, or internal-only data.
  • I certify this contribution under the Developer Certificate of Origin (DCO) and signed my commits with git commit -s or an equivalent sign-off.

Related Issues

Summary by CodeRabbit

Release Notes

Documentation

  • Added end-to-end guides for creating AI-Q tools, including setup patterns, testing practices, and integration workflows
  • New pull request preparation documentation with validation checklists and requirements
  • Added release QA validation reference covering backend, frontend, documentation, and evaluation checks
  • Enhanced research workflow with follow-up and refinement capabilities

Adds the aiq-add-tool Agent Skill (SKILL.md + nat-function-pattern and testing
references) covering the NAT function package pattern, config schema,
@register_function flow, agent tools wiring, and tests. Builds on the
devskills-foundation scaffolding.

Signed-off-by: Eli Fajardo <efajardo@nvidia.com>
Add a maintainer skill that helps a coding agent choose and run the right
validation checks (Python, frontend, docs, evals) for the surfaces a change
touches, grounded in AGENTS.md and CONTRIBUTING.md. Implements DEVSKILLS-5
(AIQ-3438).

Signed-off-by: Eli Fajardo <efajardo@nvidia.com>
Add a maintainer skill covering branch scoping, DCO sign-off, filling the PR
template with real validation evidence, and the copy-pr-bot CI/merge flow.
Reuses aiq-release-qa for validation rather than duplicating commands.
Implements DEVSKILLS-6 (AIQ-3439).

Signed-off-by: Eli Fajardo <efajardo@nvidia.com>
Document follow-up usage for the aiq-research consumer skill: answering
questions about a returned report (ask) and re-running with a refined query
(redo), reusing the existing auth, polling, and report-retrieval flow.
Implements DEVSKILLS-7 (AIQ-3440).

Signed-off-by: Eli Fajardo <efajardo@nvidia.com>
@copy-pr-bot

copy-pr-bot Bot commented Jun 16, 2026

Copy link
Copy Markdown

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.

@coderabbitai

coderabbitai Bot commented Jun 16, 2026

Copy link
Copy Markdown

Review Change Stack

Walkthrough

Adds three new agent skill directories under .agents/skills/ (aiq-release-qa, aiq-add-tool, aiq-prepare-pr), each with a primary SKILL.md and reference docs, plus .claude/skills/ symlinks pointing to them. Also extends skills/aiq-research/SKILL.md with a Step 6 follow-up workflow covering Ask and Redo flows.

Changes

New Agent Skills and Symlink Wiring

Layer / File(s) Summary
aiq-release-qa skill and validation matrix
.agents/skills/aiq-release-qa/SKILL.md, .agents/skills/aiq-release-qa/references/validation-matrix.md
SKILL.md defines surface detection, scoped Ruff/pytest/npm validation commands, pass criteria, common mistakes, and related skill links. validation-matrix.md covers one-time setup, backend, UI, docs, evals, and manual nat serve workflows.
aiq-add-tool skill, NAT function pattern, and testing reference
.agents/skills/aiq-add-tool/SKILL.md, .agents/skills/aiq-add-tool/references/nat-function-pattern.md, .agents/skills/aiq-add-tool/references/testing.md
SKILL.md documents the end-to-end tool creation workflow. nat-function-pattern.md specifies FunctionBaseConfig/SecretStr/@register_function/pyproject.toml wiring and YAML agent config. testing.md covers mocked httpx unit tests, integration checks, and PR evidence capture.
aiq-prepare-pr skill, PR checklist, and .claude/skills symlinks
.agents/skills/aiq-prepare-pr/SKILL.md, .agents/skills/aiq-prepare-pr/references/pr-checklist.md, .claude/skills/aiq-add-tool, .claude/skills/aiq-prepare-pr, .claude/skills/aiq-release-qa
SKILL.md defines the PR preparation workflow including DCO sign-off, aiq-release-qa evidence, and copy-pr-bot CI steps. pr-checklist.md details branch/scope rules, validation evidence, and iterative review loop. Three .claude/skills/ symlinks point to .agents/skills/.

aiq-research Follow-up Update

Layer / File(s) Summary
aiq-research Step 6 follow-up and Example 3
skills/aiq-research/SKILL.md
Adds a Step 6 entry to the top-level list, a full "Step 6 - Follow up" section with Ask (chat with context carryover, poll if deep-research job returned) and Redo (research with optional agent_type) logic plus citation/secret constraints, and Example 3 demonstrating both flows.

Estimated code review effort

🎯 2 (Simple) | ⏱️ ~10 minutes

🚥 Pre-merge checks | ✅ 5
✅ Passed checks (5 passed)
Check name Status Explanation
Description check ✅ Passed The description follows the template structure with all required sections completed: Overview (with context and detailed change descriptions), Validation (with actual commands and all checkboxes marked), and Related Issues linking to #269.
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.
Title check ✅ Passed Title follows Conventional Commits format with correct type (feat), scope (skills), concise imperative summary, 67 characters, and no trailing period.

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

✨ Finishing Touches
🧪 Generate unit tests (beta)
  • Create PR with unit tests

Comment @coderabbitai help to get the list of available commands and usage tips.

@AjayThorve

Copy link
Copy Markdown
Member

/ok to test 3f43277

@efajardo-nv efajardo-nv changed the title feat(skills): add aiq-add-tool, aiq-release-qa, aiq-prepare-pr; extend aiq-research feat(skills): complete maintainer skill set and extend aiq-research Jun 16, 2026

@AjayThorve AjayThorve left a comment

Copy link
Copy Markdown
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Looks really good, thanks Eli!

@AjayThorve
AjayThorve merged commit da1071b into NVIDIA-AI-Blueprints:develop Jun 16, 2026
9 of 10 checks passed
zhongxuanwang-nv added a commit to zhongxuanwang-nv/aiq that referenced this pull request Jun 23, 2026
…ainer skill artifacts

The maintainer skill set (.agents/skills/) shipped in NVIDIA-AI-Blueprints#269/NVIDIA-AI-Blueprints#277 carried a few
documentation defects found while auditing it against the live AI-Q config
schema and the sibling NeMo-Relay skill set. Documentation-only; no skills are
added or removed.

- aiq-add-data-source: correct the data_source_registry YAML example to match
  DataSourceEntry / DataSourceRegistryConfig and the working configs -- use the
  `data_sources` instance name, drop the non-existent `category` field, and list
  `tools` as plain function-instance-name strings (not `_type:` mappings). Add
  the missing `ruff format --check` to the validation block.
- aiq-add-data-source: replace the dangling `aiq-ui-change` reference (no such
  skill) with a generic frontends/ui note.
- aiq-prepare-pr, aiq-release-qa: remove stray `</content>` artifacts left at
  the end of three skill files.
- aiq-release-qa: the npm "only these scripts exist" claim was inaccurate
  (package.json defines many more); reword to recommend the canonical checks
  without asserting exhaustiveness.
- docs/integration/agent-skills.md, .agents/skills/README.md: list all four
  maintainer skills and all four .claude/skills maintainer symlinks.

Validation: scripts/validate_skills.py (6 skills OK), pytest
tests/test_agent_skills.py (4 passed), and pre-commit (detect-secrets,
validate-skills, markdown-link-check) on the changed files all pass.

Signed-off-by: Zhongxuan Wang <daniewang@nvidia.com>
cdgamarose-nv pushed a commit that referenced this pull request Jun 23, 2026
…ainer skill artifacts (#281)

The maintainer skill set (.agents/skills/) shipped in #269/#277 carried a few
documentation defects found while auditing it against the live AI-Q config
schema and the sibling NeMo-Relay skill set. Documentation-only; no skills are
added or removed.

- aiq-add-data-source: correct the data_source_registry YAML example to match
  DataSourceEntry / DataSourceRegistryConfig and the working configs -- use the
  `data_sources` instance name, drop the non-existent `category` field, and list
  `tools` as plain function-instance-name strings (not `_type:` mappings). Add
  the missing `ruff format --check` to the validation block.
- aiq-add-data-source: replace the dangling `aiq-ui-change` reference (no such
  skill) with a generic frontends/ui note.
- aiq-prepare-pr, aiq-release-qa: remove stray `</content>` artifacts left at
  the end of three skill files.
- aiq-release-qa: the npm "only these scripts exist" claim was inaccurate
  (package.json defines many more); reword to recommend the canonical checks
  without asserting exhaustiveness.
- docs/integration/agent-skills.md, .agents/skills/README.md: list all four
  maintainer skills and all four .claude/skills maintainer symlinks.

Validation: scripts/validate_skills.py (6 skills OK), pytest
tests/test_agent_skills.py (4 passed), and pre-commit (detect-secrets,
validate-skills, markdown-link-check) on the changed files all pass.

Signed-off-by: Zhongxuan Wang <daniewang@nvidia.com>
@AjayThorve AjayThorve added this to the v2.2 milestone Jul 7, 2026
@coderabbitai coderabbitai Bot mentioned this pull request Aug 20, 2026
6 tasks
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants