القائمة
Review PRs against the Intent Layer. Use for reviewing AI-generated PRs or having AI review human PRs. Provides risk scoring, checklists, and contract verification.
التثبيت باستخدام Codex أو Claude انسخ هذا Prompt والصقه في Codex أو Claude أو مساعد آخر ليراجع صفحة Skill ويثبّتها لك.
Set up hierarchical Intent Layer (AGENTS.md files) for codebases. Use when initializing a new project, adding context infrastructure to an existing repo, user asks to set up AGENTS.md, add intent layer, make agents understand the codebase, or scaffolding AI-friendly project documentation.
End-of-cycle learning capture and triage. Run after completing a feature, fixing a bug, or finishing any significant work. Reviews pending learnings, analyzes conversation for undocumented insights, and integrates into the Intent Layer with appropriate scope (global workflow vs local code).
Quick health check for Intent Layer - validates nodes, checks staleness, reports coverage gaps
Remove the Intent Layer from a repository. Deletes all child AGENTS.md files and removes the Intent Layer section from the root CLAUDE.md.
Interactive review of pending mistake reports from the learning loop. Walk through each report with the user, accepting/rejecting/discarding as appropriate.
Extract Intent Layer content from git history. Analyzes commits, PRs, and blame to discover pitfalls, contracts, architecture decisions, and entry points that should be documented in AGENTS.md files.
استنادا إلى تصنيف SOC المهني
| name | pr-review |
| description | Review PRs against the Intent Layer. Use for reviewing AI-generated PRs or having AI review human PRs. Provides risk scoring, checklists, and contract verification. |
| argument-hint | [BASE_REF] [HEAD_REF] [--pr NUMBER] [--ai-generated] |
Review a PR against the Intent Layer for contract compliance, pitfall awareness, and risk assessment.
# Basic review
scripts/review_pr.sh main HEAD
# Review AI-generated PR
scripts/review_pr.sh main HEAD --ai-generated
# Review with GitHub PR context
scripts/review_pr.sh main HEAD --pr 123 --ai-generated
scripts/review_pr.sh main HEAD --ai-generated
Review the output:
For each critical item in the checklist:
- [x] or flag concernIf --ai-generated was used:
Over-engineering flags:
Pitfall proximity:
Intent drift:
Use the agent-feedback-protocol format for any discoveries:
### Intent Layer Feedback
| Type | Location | Finding |
|------|----------|---------|
| Missing pitfall | `src/api/AGENTS.md` | [description] |
| Stale contract | `CLAUDE.md` | [description] |
Output a structured review comment:
## PR Review Summary
**Risk: [Score] ([Level])**
### Verified
- [x] Auth tokens validated before DB write
- [x] Rate limiting uses Redis
### Concerns
- [ ] New abstraction in `utils/helper.ts` may be unnecessary
### Intent Layer Feedback
[Any findings to update nodes]
- name: PR Review Check
run: |
./intent-layer/scripts/review_pr.sh origin/main HEAD --exit-code --ai-generated
# Exit 0 = low risk, 1 = medium, 2 = high
| Flag | Output |
|---|---|
--summary | Risk score only |
--checklist | Score + checklist |
--full | All layers (default) |
detect_changes.sh - Foundation for affected node discoveryagent-feedback-protocol.md - Format for surfacing findingsvalidate_node.sh - Validate node updates after review