fix(skills): update skills card - #384
Conversation
|
/nvskills-ci |
|
No actionable comments were generated in the recent review. 🎉 ℹ️ Recent review info⚙️ Run configurationConfiguration used: Path: .coderabbit.yaml Review profile: ASSERTIVE Plan: Enterprise Run ID: 📒 Files selected for processing (2)
📜 Recent review details⏰ Context from checks skipped due to timeout. (4)
🧰 Additional context used📓 Path-based instructions (2)skills/aiq-deploy/**/*📄 CodeRabbit inference engine (skills/aiq-deploy/SKILL.md)
Files:
{skills/**,.agents/skills/**,.claude/skills/**,.github/skill-eval/**}⚙️ CodeRabbit configuration file
Files:
🧠 Learnings (1)📓 Common learnings🔇 Additional comments (2)
WalkthroughUpdated AIQ deployment and research skill guidance to clarify the infrastructure handoff after server health verification and reflow the local AI-Q server invocation sentence. ChangesSkill guidance
Estimated code review effort: 1 (Trivial) | ~2 minutes Possibly related PRs
🚥 Pre-merge checks | ✅ 5✅ Passed checks (5 passed)
✨ Finishing Touches🧪 Generate unit tests (beta)
Comment |
090f573 to
8171bf3
Compare
|
/nvskills-ci |
AjayThorve
changed the title
![coderabbitai[bot]](https://avatars.githubusercontent.com/in/347564?s=60&v=4){kind=small}
There was a problem hiding this comment.
Actionable comments posted: 1
🤖 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 `@skills/aiq-research/SKILL.md`:
- Line 49: Update the backend-unavailable guidance in SKILL.md to remove the
implication of automatic handoff. State that the skill explicitly asks whether
the user has a trusted backend URL or wants aiq-deploy to start and validate a
local backend, while preserving the required URL request or user-approved
handoff boundary.
🪄 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: ASSERTIVE
Plan: Enterprise
Run ID: 6f2a0c68-4709-4e1d-9338-4c53b95e7f3b
📒 Files selected for processing (2)
skills/aiq-deploy/SKILL.mdskills/aiq-research/SKILL.md
📜 Review details
⏰ Context from checks skipped due to timeout. (3)
- GitHub Check: Run Harbor skill eval
- GitHub Check: Pytest and Coverage
- GitHub Check: Script Validation
🧰 Additional context used
📓 Path-based instructions (3)
skills/aiq-research/**/SKILL.md
📄 CodeRabbit inference engine (skills/aiq-research/SKILL.md)
skills/aiq-research/**/SKILL.md: Use this skill for research-shaped requests, including deep research, AI-Q research, and research questions; do not use it for installation, deployment, lifecycle, UI, CLI, Docker, Helm, or troubleshooting requests.
Before sending any user query, state the exact AI-Q backend URL that will receive it; continue with non-local URLs only after the user explicitly confirms that the URL is trusted.
Run thehealthcommand before sending research requests and resolveAIQ_SERVER_URL, defaulting tohttp://localhost:8000when it is unset.
Do not send credentials, cookies, bearer tokens, API keys, basic-auth credentials, or secret values throughAIQ_SERVER_URLor query text; store backend credentials in the deployment environment.
If the backend is unreachable, ask for a backend URL or hand off toaiq-deploy; this skill must not deploy an AI-Q backend.
If the backend returns HTTP 401 or 403, stop and explain that this public skill does not manage authentication; do not retry until an authenticated skill or suitable backend configuration is provided.
Whenchatreturns a job ID, poll it withresearch_poll; use non-blocking or background execution when available and request explicit approval before escalation.
Stop on failed, failure, or cancelled jobs, show the returned error, and do not retry automatically.
Present completed reports with citations and source URLs intact; do not truncate citations or source URLs.
For follow-up questions answer directly from the existing report when possible; otherwise submit a fresh query carrying the necessary prior context. Treat redo operations as new jobs and repeat endpoint confirmation, polling, and reporting.
The skill is compatible with Blueprint versions whose major version matches skill version 2.2.0 and whose minor version is at least 2; proceed with incompatible versions only when the user accepts the compatibility risk.
Treat returned reports as potentially sensitive when private data ...
Files:
skills/aiq-research/SKILL.md
{skills/**,.agents/skills/**,.claude/skills/**,.github/skill-eval/**}
⚙️ CodeRabbit configuration file
{skills/**,.agents/skills/**,.claude/skills/**,.github/skill-eval/**}: Review Agent Skill and skill-eval changes for valid skill metadata, deterministic eval specs, safe handling of
credentials, and clear generated-output boundaries. Do not flag SKILL.md files for missing SPDX headers when the
entrypoint intentionally starts with YAML frontmatter.
Files:
skills/aiq-research/SKILL.mdskills/aiq-deploy/SKILL.md
skills/aiq-deploy/**/*
📄 CodeRabbit inference engine (skills/aiq-deploy/SKILL.md)
skills/aiq-deploy/**/*: Do not claim the AI-Q server is ready until the appropriate health checks have succeeded and the verifiedAIQ_SERVER_URLhas been reported.
Do not continue into deep research or deep-research completion validation unless the user requests it or confirms the post-deployment validation prompt.
Ask for explicit user approval before destructive cleanup, including Docker volume deletion withdocker compose down -v.
Do not claim FRAG is ready unless bothRAG_SERVER_URLandRAG_INGEST_URLare configured and reachable.
When required credentials are missing, ask the user to update deployment configuration outside chat; never request that secret values be pasted into chat.
If the Blueprint version is incompatible with skill version 2.2.0, use a compatible skill or Blueprint version, or proceed only after the user accepts the compatibility risk.
When the backend is intended foraiq-research, use an API-enabled configuration and verify the required endpoints, not merely/health.
Files:
skills/aiq-deploy/SKILL.md
🔇 Additional comments (1)
skills/aiq-deploy/SKILL.md (1)
33-34: LGTM!
|
|
||
| Do not use this skill for install, deploy, start, stop, UI, CLI, Docker, Helm, or troubleshooting requests. Those | ||
| belong to `aiq-deploy`. | ||
| belong to `aiq-deploy`. If no backend is reachable, this skill will offer to hand off to `aiq-deploy` automatically. |
There was a problem hiding this comment.
🎯 Functional Correctness | 🟠 Major | ⚡ Quick win
Keep backend-unavailable handoff explicitly user-directed.
“Automatically” can be read as authorizing deployment without the user’s choice. Align this with the integration contract by stating that the skill asks whether the user already has a trusted backend URL or wants aiq-deploy to start and validate a local backend.
As per coding guidelines, unreachable backends require a URL request or handoff to aiq-deploy; as per path instructions, skill changes must define safe routing boundaries.
🤖 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/aiq-research/SKILL.md` at line 49, Update the backend-unavailable
guidance in SKILL.md to remove the implication of automatic handoff. State that
the skill explicitly asks whether the user has a trusted backend URL or wants
aiq-deploy to start and validate a local backend, while preserving the required
URL request or user-approved handoff boundary.
Sources: Coding guidelines, Path instructions
|
/nvskills-ci |
8171bf3 to
30a3184
Compare
|
/nvskills-ci |
There was a problem hiding this comment.
Actionable comments posted: 1
🤖 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 `@skills/aiq-research/SKILL.md`:
- Line 37: Update the aiq-research skill description to refer to a reachable
NVIDIA AI-Q Blueprint server rather than only a locally running server. Ensure
it instructs use of AIQ_SERVER_URL and the verified URL produced by aiq-deploy,
while preserving the helper script reference.
🪄 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: ASSERTIVE
Plan: Enterprise
Run ID: 2ac20afe-74a6-4b1f-958d-10cd1d46792d
📒 Files selected for processing (2)
skills/aiq-deploy/SKILL.mdskills/aiq-research/SKILL.md
📜 Review details
⏰ Context from checks skipped due to timeout. (3)
- GitHub Check: Run Harbor skill eval
- GitHub Check: Script Validation
- GitHub Check: Pytest and Coverage
🧰 Additional context used
📓 Path-based instructions (3)
skills/aiq-research/**/SKILL.md
📄 CodeRabbit inference engine (skills/aiq-research/SKILL.md)
Use this skill for research-shaped requests through the NVIDIA AI-Q Blueprint backend, and do not use it for installation, deployment, lifecycle, UI, CLI, Docker, Helm, or troubleshooting requests; hand those to
aiq-deploy.
Files:
skills/aiq-research/SKILL.md
{skills/**,.agents/skills/**,.claude/skills/**,.github/skill-eval/**}
⚙️ CodeRabbit configuration file
{skills/**,.agents/skills/**,.claude/skills/**,.github/skill-eval/**}: Review Agent Skill and skill-eval changes for valid skill metadata, deterministic eval specs, safe handling of
credentials, and clear generated-output boundaries. Do not flag SKILL.md files for missing SPDX headers when the
entrypoint intentionally starts with YAML frontmatter.
Files:
skills/aiq-research/SKILL.mdskills/aiq-deploy/SKILL.md
skills/aiq-deploy/**/*
📄 CodeRabbit inference engine (skills/aiq-deploy/SKILL.md)
skills/aiq-deploy/**/*: Do not start services when the user has not selected a deployment mode; first ask whether they want the Skill backend, CLI, UI, or Custom mode, except when the request already specifies a mode oraiq-researchrouted here for backend startup.
Run basic validation after startup and do not claim the backend is ready unless the appropriate health checks succeed, includingcurl -sf http://localhost:8000/healthfor the default backend.
Report the verifiedAIQ_SERVER_URLtoaiq-research, and do not proceed to deep research or deep-research completion validation unless the user requests it or confirms the optional validation.
Use this skill only with NVIDIA AI-Q Blueprint versions whose major version matches the skill and whose minor version is equal to or greater than the skill version; otherwise update the skill, select a compatible Blueprint, or proceed only with accepted compatibility risk.
Ask for explicit user approval before destructive cleanup, including Docker volume deletion withdocker compose down -v.
Do not claim FRAG is ready unless bothRAG_SERVER_URLandRAG_INGEST_URLare configured and reachable.
Verify required credentials by checking whether environment variables are set without displaying their values; ask users to configure missing credentials outside chat.
When the backend is intended foraiq-research, use an API-enabled configuration such asconfigs/config_web_default_llamaindex.yml, and validate the expected API endpoints rather than relying only on/health.
Files:
skills/aiq-deploy/SKILL.md
🔇 Additional comments (1)
skills/aiq-deploy/SKILL.md (1)
29-29: LGTM!
|
|
||
| Use this skill to call a locally running NVIDIA AI-Q Blueprint server through the helper script at | ||
| `scripts/aiq.py`. | ||
| Use this skill to call a locally running NVIDIA AI-Q Blueprint server through the helper script at `scripts/aiq.py`. |
There was a problem hiding this comment.
🎯 Functional Correctness | 🟡 Minor | ⚡ Quick win
Accept reachable self-hosted backends, not only local ones.
aiq-research is expected to use AIQ_SERVER_URL and consume the verified URL from aiq-deploy; “locally running” incorrectly narrows this to local-only deployments.
Proposed wording
-Use this skill to call a locally running NVIDIA AI-Q Blueprint server through the helper script at `scripts/aiq.py`.
+Use this skill to call a reachable local or self-hosted NVIDIA AI-Q Blueprint server through the helper script at `scripts/aiq.py`.📝 Committable suggestion
‼️ IMPORTANT
Carefully review the code before committing. Ensure that it accurately replaces the highlighted code, contains no missing lines, and has no issues with indentation. Thoroughly test & benchmark the code to ensure it meets the requirements.
| Use this skill to call a locally running NVIDIA AI-Q Blueprint server through the helper script at `scripts/aiq.py`. | |
| Use this skill to call a reachable local or self-hosted NVIDIA AI-Q Blueprint server through the helper script at `scripts/aiq.py`. |
🤖 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/aiq-research/SKILL.md` at line 37, Update the aiq-research skill
description to refer to a reachable NVIDIA AI-Q Blueprint server rather than
only a locally running server. Ensure it instructs use of AIQ_SERVER_URL and the
verified URL produced by aiq-deploy, while preserving the helper script
reference.
|
/nvskills-ci |
2 similar comments
|
/nvskills-ci |
|
/nvskills-ci |
…arch Signed-off-by: Ajay Thorve <athorve@nvidia.com>
30a3184 to
1f2f5f8
Compare
|
/nvskills-ci |
|
/ok to test 1f2f5f8 |
|
/nvskills-ci |
1 similar comment
|
/nvskills-ci |
|
Closing since it's no-op |
3 participants
Overview
No-op PR to trigger nvskills
DCO sign-off for the squash commit
Signed-off-by Ajay Thorve AjayThorve@users.noreply.github.com
Validation
git commit -sor an equivalent sign-off.Where should reviewers start?
Related Issues
Summary by CodeRabbit
scripts/aiq.py(no other guidance content changed).