feat(claude): add NVIDIA AI-Q research and deploy skills#223
Merged
Conversation
Install the portable Agent Skills shipped by the NVIDIA AI-Q Blueprint (NVIDIA-AI-Blueprints/aiq, develop) into the user-global ~/.claude tree via chezmoi: - aiq-research: routes "deep research" requests to a running AI-Q backend (default http://localhost:8000), polls async jobs, presents cited reports. Pure-stdlib helper, no pip deps. - aiq-deploy: stands up and manages the local AI-Q backend. Copied verbatim from upstream, including the signed skill.oms.sig packages and evals so the published signatures stay intact. Skills are pinned to AI-Q Blueprint 2.1.0. No backend is deployed yet. Exclude *.oms.sig from the trailing-whitespace and end-of-file-fixer pre-commit hooks so those signed blobs keep their exact bytes. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
github-actions
Bot
added
documentation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
Install the two portable Agent Skills shipped by the NVIDIA AI-Q Blueprint into the user-global
~/.claudetree via chezmoi (exact_dot_claude/skills/):aiq-research— routes "deep research" / "AI-Q research" requests to a running AI-Q backend (defaulthttp://localhost:8000), polls async jobs, presents cited reports. Pure-stdlib helper (scripts/aiq.py), no pip deps.aiq-deploy— stands up and manages the local AI-Q backend thataiq-researchtalks to (13 reference docs: docker-compose, helm, env/secrets, validation, troubleshooting…).Copied verbatim from upstream (
develop), including the signedskill.oms.sigpackages andevalsso the published signatures stay intact. Skills are pinned to AI-Q Blueprint 2.1.0 (major version must match).Pre-commit fix
Excludes
*.oms.sigfrom thetrailing-whitespaceandend-of-file-fixerhooks — those hooks were appending a newline to the signature blobs, which would break signature verification.Notes / follow-ups
aiq-researchneeds an AI-Q server running; first use will runhealth, find none, and offer to hand off toaiq-deploy. Standing one up requires an NVIDIA API key (in the backend env, not the skill).develop; pulled from there. A future 3.x backend would need updated skills.🤖 Generated with Claude Code