review-sections
Generate branch-story sections 4-7 (Outcome, Historical Analysis, Concerns, Successful Development Patterns) from archived tickets and carry-over verdicts. Used by the report workflow when assembling a PR story.
What this skill does
# Review Sections
Guidelines for generating story sections 4-7 (Outcome, Historical Analysis, Concerns, Successful Development Patterns) from archived tickets.
## Input
- Branch name
- List of archived ticket paths
- Carry-over verdicts file path (`/tmp/carryover-verdicts.json`, optional — empty/missing if no active carry-overs)
## Analysis Process
1. **Read all archived tickets** for the branch using Glob pattern
2. **Extract relevant content** from each ticket:
- Overview section for accomplishments
- Related History section for patterns
- Considerations section for concerns
- Final Report section (if present) for outcomes
3. **Read carry-over verdicts** from the verdicts file path. Filter to entries with `verdict: still_active`. These carry-overs were judged active by the carry-over judge subagent (the `### Judge Carry-Overs` step in `core:report`) and must be re-surfaced in this story's section 6 (Concerns).
## Section Guidelines
### Section 4: Outcome
Summarize what was accomplished across all tickets.
- List key deliverables and features implemented
- Focus on user-visible or architecturally significant changes
- Use bullet points for clarity
- Include metrics if available (files changed, tests added, etc.)
### Section 5: Historical Analysis
Extract patterns and learnings from Related History sections.
- Identify recurring themes or decisions
- Note how past decisions influenced current implementation
- Highlight any patterns that should inform future work
- If no historical context found, write "No significant historical patterns identified."
### Section 6: Concerns
Risks, trade-offs, limitations, and forward-looking suggestions discovered during implementation. Each concern is one insight expressed as a title, a description, and how to fix it — with a severity label. Emit one `###` block per concern using this exact structure (it is parsed by `extract-carryover.sh` on `/ship`):
```markdown
### <Concise title>
- **Severity:** moderate
- **Description:** <what the problem/risk is> (see [hash](url) in path/to/file.ext)
- **How to Fix:** <the concrete fix or improvement>
```
Compose the section from two sources, in this order:
1. **Carried-over concerns** — entries in the verdicts file where `verdict: still_active`. Render each as a block above; prefix the title with `(carried from PR #N)` using `origin_pr`, and preserve the carry-over's existing `severity`.
2. **New concerns** — extracted from Considerations sections of this branch's tickets.
For new concerns:
- **Severity** is a label, not a number: `urgent` (act now), `moderate` (should fix), `low` (nice-to-have). Choose based on impact and urgency; default `moderate`.
- Frame the risk and the constructive suggestion together (risk in Description, suggestion in How to Fix) — they are two angles on the same insight.
- Put the commit_hash from ticket frontmatter (if present) and the file path inside the Description.
- Keep Description and How to Fix to one paragraph each.
If both sources are empty, write "None".
### Section 7: Successful Development Patterns
Capture effective patterns discovered during this branch's development.
- Extract positive observations from ticket Considerations sections
- Extract "what went well" insights from Final Report sections
- Identify effective approaches from Implementation Steps that proved successful
- Look for recurring successful strategies across multiple tickets
- Categories to consider:
- Architectural decisions that worked well
- Testing strategies that caught issues
- Refactoring approaches that improved code quality
- Collaboration or workflow patterns that were effective
- Tooling or automation choices that saved effort
- Each pattern should include reasoning for why it worked
- If no noteworthy patterns, write "None"
## Output Format
Return JSON with the following structure:
```json
{
"outcome": "Bullet list of accomplishments...",
"historical_analysis": "Patterns and learnings...",
"concerns": "Risks, trade-offs, and forward-looking suggestions, or 'None'",
"development_patterns": "Effective patterns or 'None'"
}
```
Each field should contain markdown-formatted content ready to be inserted into the story file.
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.