pr-review
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.
What this skill does
# PR Review
Review a PR against the Intent Layer for contract compliance, pitfall awareness, and risk assessment.
## Quick Start
```bash
# 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
```
## Interactive Review Workflow
### Step 1: Run Initial Analysis
```bash
scripts/review_pr.sh main HEAD --ai-generated
```
Review the output:
1. **Risk Score** - Is this Low/Medium/High?
2. **Critical Items** - These MUST be verified
3. **AI Checks** - Any drift or over-engineering warnings?
### Step 2: Walk Through Critical Items
For each critical item in the checklist:
1. Read the contract/invariant
2. Find the relevant code in the diff
3. Verify the code respects the constraint
4. Mark checked: `- [x]` or flag concern
### Step 3: Check AI-Specific Warnings
If `--ai-generated` was used:
**Over-engineering flags:**
- New abstractions: Are they necessary?
- Excessive try/catch: Does error handling add value?
- New interfaces: Premature abstraction?
**Pitfall proximity:**
- For each alert, verify the AI handled the edge case
- If not, flag for fix before merge
**Intent drift:**
- If PR approach conflicts with documented architecture, escalate
### Step 4: Surface Findings
Use the agent-feedback-protocol format for any discoveries:
```markdown
### Intent Layer Feedback
| Type | Location | Finding |
|------|----------|---------|
| Missing pitfall | `src/api/AGENTS.md` | [description] |
| Stale contract | `CLAUDE.md` | [description] |
```
### Step 5: Generate Review Summary
Output a structured review comment:
```markdown
## 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]
```
## CI Integration
```yaml
- 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
```
## Output Modes
| Flag | Output |
|------|--------|
| `--summary` | Risk score only |
| `--checklist` | Score + checklist |
| `--full` | All layers (default) |
## When to Use
- **Before merging AI-generated PRs** - Verify contracts respected
- **AI reviewing human PRs** - Systematic contract checking
- **CI gate** - Block high-risk PRs for manual review
## Related
- `detect_changes.sh` - Foundation for affected node discovery
- `agent-feedback-protocol.md` - Format for surfacing findings
- `validate_node.sh` - Validate node updates after review
Related in Code Review
gstack
IncludedFast headless browser for QA testing and site dogfooding. Navigate pages, interact with elements, verify state, diff before/after, take annotated screenshots, test responsive layouts, forms, uploads, dialogs, and capture bug evidence. Use when asked to open or test a site, verify a deployment, dogfood a user flow, or file a bug with screenshots. (gstack)
startup-due-diligence
IncludedLegal due diligence review for seed-stage and Series A startups (US, Delaware C-Corp focus). Supports both investor and founder perspectives. Capabilities include: (1) Interactive document review and issue spotting; (2) Document request list generation; (3) Cap table and SAFE/convertible note analysis; (4) Red flag identification with severity ratings; (5) Diligence report generation. TRIGGERS: due diligence, DD, startup investment, cap table review, Series A, seed round, investor diligence, legal review startup, SAFE analysis, convertible note, 409A, founder vesting.
interview-master
IncludedThis skill should be used when the user asks to "generate interview questions", "prepare for interview", "optimize resume", "conduct mock interview", "analyze git commits for resume", "generate resume from code", "review my resume", or mentions interview preparation, career assistance, or extracting project experience from git history. Provides comprehensive interview and career development guidance for both job seekers and interviewers.
fix-issue
IncludedFixes GitHub issues using parallel analysis agents for root cause investigation, code exploration, and regression detection. Reads issue context from gh CLI, searches codebase and memory for related patterns, generates a fix with tests, and links the resolution back to the issue via PR. Includes prevention analysis to avoid recurrence. Use when debugging errors, resolving regressions, fixing bugs, or triaging issues.
sf-apex
IncludedGenerates and reviews Salesforce Apex code with 150-point scoring. TRIGGER when: user writes, reviews, or fixes Apex classes, triggers, test classes, batch/queueable/schedulable jobs, or touches .cls/.trigger files. DO NOT TRIGGER when: LWC JavaScript (use sf-lwc), Flow XML (use sf-flow), SOQL-only queries (use sf-soql), or non-Salesforce code.
swift-development
IncludedComprehensive Swift development for building, testing, and deploying iOS/macOS applications. Use when Claude needs to: (1) Build Swift packages or Xcode projects from command line, (2) Run tests with XCTest or Swift Testing framework, (3) Manage iOS simulators with simctl, (4) Handle code signing, provisioning profiles, and app distribution, (5) Format or lint Swift code with SwiftFormat/SwiftLint, (6) Work with Swift Package Manager (SPM), (7) Implement Swift 6 concurrency patterns (async/await, actors, Sendable), (8) Create SwiftUI views with MVVM architecture, (9) Set up Core Data or SwiftData persistence, or any other Swift/iOS/macOS development tasks.