Open
Conversation
Add AI-agent skill definitions used by Claude, OpenCode, and other coding assistants. Includes brainstorming, commit, PR, debugging, TDD, and other workflow skills from superpowers and agglayer-ai-skills plugins. - .agents/skills/: skill definitions (SKILL.md + supporting files) - .claude/skills/: symlinks for Claude Code discovery - skills-lock.json: pinned skill versions and integrity hashes - .github/workflows/skills-check.yml: CI for skill integrity - AGENTS.md: updated with pre-flight gate and skill references
![github-advanced-security[bot]](https://avatars.githubusercontent.com/in/57789?s=60&v=4){kind=small}
![chatgpt-codex-connector[bot]](https://avatars.githubusercontent.com/in/1144995?s=60&v=4){kind=small}
There was a problem hiding this comment.
💡 Codex Review
Here are some automated review suggestions for this pull request.
Reviewed commit: cd1f811a8f
ℹ️ About Codex in GitHub
Your team has set up Codex to review pull requests in this repo. Reviews are triggered when you
- Open a pull request for review
- Mark a draft as ready
- Comment "@codex review".
If Codex has suggestions, it will comment; otherwise it will react with 👍.
Codex can also answer questions or update the PR. Try commenting "@codex address that feedback".
Replace `npx skills check` (which only checks for globally installed skill updates and passes vacuously on fresh runners) with a script that verifies every skill declared in skills-lock.json has a corresponding directory and SKILL.md. Add explicit permissions block (contents: read) per CodeQL recommendation. Remove unnecessary Setup Node.js step since ubuntu-latest provides Node.js by default.
Replace structural-only CI check with `npx skills update -y -p` followed by `git diff --exit-code` to detect drift from upstream skill sources. Add permissions block per CodeQL recommendation. Update verify skill to latest upstream version, which adds blast-radius analysis script and example config. Add /skills to .gitignore (CLI working directory).
Add .blast-radius.yaml defining core crates, risk areas, and verification commands for the interop workspace: - Core crates: agglayer-primitives, agglayer-tries, agglayer-bincode - Risk areas: protobuf schema, proof/zkVM pipeline, bridge safety - Code commands: cargo make ci-all - Docs commands: mdbook build docs/knowledge-base/ Add minimal docs/knowledge-base/ scaffold (book.toml, SUMMARY.md, introduction.md) so mdbook builds succeed.
Signed-off-by: Simon Paitrault <spaitrault@polygon.technology>
Ekleog-Polygon
requested changes
Apr 17, 2026
Collaborator
Ekleog-Polygon
left a comment
Ekleog-Polygon
left a comment
There was a problem hiding this comment.
I think we agreed on installing user-wide the skills from the ai-agents repo, this can probably be closed?
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
3 participants
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.
Add AI-agent skill definitions for Claude, OpenCode, and other
coding assistants, along with a lock file for version pinning
and a CI workflow to verify skill integrity.
.agents/skills/: skill definitions (SKILL.md + supporting files)from superpowers and agglayer-ai-skills plugins
.claude/skills/: symlinks for Claude Code discoveryskills-lock.json: pinned skill versions and integrity hashes.github/workflows/skills-check.yml: CI check for skill integrityAGENTS.md: updated with pre-flight gate and skill references