chore(agent-guidance): add guidance-building skill#9
Merged
Conversation
Fallow audit reportFound 1 finding. Details
Generated by fallow. |
Fallow audit report0 inline findings selected for GitHub review. |
…dance-skill # Conflicts: # CLAUDE.md # README.md
🗺️ StyleProof report✓ No visual changes detected. |
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Why
AgenticProjectTemplate needs a reusable way to build and maintain agent-facing repo guidance, not just a finished example of
AGENTS.mdandCLAUDE.md. This adds the layer model and skill that future agents can use when installing or improving guidance in other repos.What Changed
.agents/project/AGENTIC_INFRASTRUCTURE.mdto define the layers for entry contracts, tool adapters, project context, decisions, templates, local gates, remote gates, and skills..claude/skills/build-agent-guidanceto guide agents through evidence-first updates toAGENTS.md,CLAUDE.md, and.agents/.AGENTS.md,CLAUDE.md,.agents/README.md, andREADME.md.Proof
python3 /Users/agents/.codex/skills/.system/skill-creator/scripts/quick_validate.py .claude/skills/build-agent-guidancepnpm checkpnpm verifypnpm e2eN/Awith reason:N/A— docs and skill-only change; no UI/CSS surface changed.N/Awith reason:N/A— StyleProof passed withNo visual changes.CI Status
Latest-sha checks are green: CI quality, Fallow, unit/component tests, production build, E2E behaviour map, security audit, CodeQL, Lighthouse, computed-style visual gate, and StyleProof.
Risk And Rollback
Low risk. This adds documentation and a repo-local skill; it does not change runtime code or gate behavior. Rollback is reverting the single commit if the layer model or skill shape needs to be split differently.
Definition Of Done
N/A— no product behaviour changed.)N/A— no runtime logic changed.)N/A— no UI changed; existing Playwright axe scan passed.).agents/project/ARCHITECTURE.mdandCONVENTIONS.md.N/A— this documents the current infrastructure layer model, no runtime architecture change.)