orchestra-review
Review a completed implementation branch against its spec and acceptance criteria — catch gaps, shortcuts, and quality issues before merge.
What this skill does
# Review
Validate a completed implementation against its spec. Check every acceptance criterion, catch shortcuts or incomplete work, and produce a clear pass/fail verdict before the branch is merged.
## Prerequisites
- Spec `status` must be `complete`
- An `impl/{ticket-id}` branch must exist with commits
- Working tree must be on the `impl/{ticket-id}` branch or you must be able to read it
## Steps
### 1. Load the Spec and Branch
- Locate the spec from $ARGUMENTS (path or work item name)
- Read the spec: objective, approach steps, deliverables table, acceptance criteria
- Read the PRD for original intent
- Confirm the branch exists:
```bash
git log impl/{ticket-id} --oneline
```
- Review the full diff against main:
```bash
git diff main...impl/{ticket-id}
```
### 2. Check Every Acceptance Criterion
Work through each criterion from the spec one by one:
- Read the criterion
- Find the evidence in the diff or deliverables
- Mark **PASS** or **FAIL** with specific file/line evidence
- Do not mark PASS without evidence — "looks fine" is not evidence
### 3. Verify the Deliverables Table
For each row in the spec's deliverables table:
- Confirm the file exists at the specified path
- Confirm it is non-empty and contains real content, not a placeholder
- Flag any deliverable marked delivered but missing or incomplete
### 4. Spot-Check the Implementation
Review the diff for quality issues beyond the acceptance criteria:
- Shortcuts or workarounds that technically pass criteria but are fragile
- Hard-coded values that should be dynamic
- Missing error handling at system boundaries
- Spec steps that appear skipped or only partially executed
- Anything that would surprise a future reader
**TDD tier check — treat missing tiers as a FAIL:**
- Unit tests present and committed before their implementation? If not: FAIL
- Integration tests present for any external boundary (network, DB, filesystem)? If absent: FAIL
- E2E tests present for the user-facing interface (CLI, HTTP endpoint)? If absent: FAIL
- Are integration tests hitting the real boundary (no mocks at the seam being tested)? If mocked: FAIL
### 5. Produce the Verdict
Output a structured review report:
```
## Review: {ticket-id}
**Verdict:** PASS | FAIL
### Acceptance Criteria
- [ ] {criterion 1} — PASS: {evidence}
- [ ] {criterion 2} — FAIL: {what's missing}
### Deliverables
- {path} — present / missing / incomplete
### Issues
{list any quality issues found, or "None"}
### Required Before Merge
{list blocking items if FAIL, or "None — ready for /orchestra-merge"}
```
### 6. If FAIL — Do Not Merge
If the verdict is FAIL:
- List each blocking issue clearly
- Do not update the spec status
- Signal: return to `/orchestra-implement` to address the issues, then re-run `/orchestra-review`
### 7. If PASS — Update Status
Update the spec frontmatter:
```yaml
status: reviewed
```
Signal: ready for `/orchestra-merge`
### 8. Write the Devlog
After producing the verdict, write a devlog entry regardless of PASS or FAIL.
File path: `.orchestra/devlog/{YYYY}-Q{N}/{YYYY-MM-DD}-review-{ticket-id}.md`
```markdown
---
created_on: {YYYY-MM-DD}
---
# {YYYY-MM-DD}: Review — {ticket-id}
## Verdict
{PASS | FAIL}
## What Was Reviewed
{1–2 sentences: what the work item did and what was checked}
## Findings
{Key passing criteria, failing criteria, and quality issues found.
Be specific — file paths, criterion names, what evidence was or wasn't there.}
## Next Step
{If PASS: ready for /orchestra-merge}
{If FAIL: return to /orchestra-implement — list the blocking issues}
```
## Quality Checks
- [ ] Every acceptance criterion evaluated with evidence, not assumed
- [ ] Every deliverable in the materials table confirmed to exist
- [ ] Diff reviewed for shortcuts or incomplete steps
- [ ] Verdict is unambiguous — PASS or FAIL, not "mostly done"
- [ ] If the work item involves code: all three test tiers confirmed present (unit, integration, E2E) — absence of any tier is a FAIL
- [ ] If the work item involves code: integration tests verified to hit real boundaries (not mocked at the seam)
- [ ] If the work item involves code: TDD commit ordering verified for all tiers
- [ ] Devlog written regardless of verdict
## Boundaries
- Do not fix issues found — report them and return to `/orchestra-implement`
- Do not merge — that is `/orchestra-merge`
- Do not push the branch
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.