Code review
Multi-agent code review with parallel specialized reviewers, architecture validation, challenge validation, and durable handling of previously decided findings. Use `rq` to request a review of diffs (defaults to main branch), `rs` to respond to findings and record intentional non-fix decisions beside the relevant code. Triggers on "review this", "review my code", "code review", "check for bugs", "audit this", when examining PRs, pull requests, branches, or diffs. Always asks user before applying fixes or adding decision comments.From its SKILL.md
npx -y skills add martinffx/atelier --skill code-reviewAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
SKILL.md
4.3 KB, as published. Nobody here has run it
Code Review Skill
Multi-agent code analysis with a simplicity gate, focused reviewers, and challenge validation.
Uses explicit subagent dispatch patterns from code-subagents.
Prerequisites
- Required: git
Arguments
Command Routing
| Invocation | Behavior |
|---|---|
| (no arguments) | Review diff to main branch |
rq | Review diff to main branch |
rq main | Review diff to main branch |
rq develop | Review diff to develop branch |
feat/foo | Review diff to feat/foo (bare branch = rq) |
rs | Respond to review findings (interview mode) |
Subagent Architecture
Use these concrete harness subagent types. If an exact match is unavailable, use the most correct available subagent based on the harness-provided descriptions.
subagent_type | Purpose |
|---|---|
sentinel | Triage only: changed-file analysis, context retrieval, reviewer selection |
oracle | Reviewer personas, evidence-based critique, failure-mode analysis, challenge validation |
architect | Architecture, design-boundary, data-model, and API-contract review |
Reviewer names such as Security, Correctness, Maintainability, and PerformanceOperator are prompt personas, not subagent types. Do not use general; it is not a harness agent.
Simplicity is a mandatory reviewer persona for migrations, refactors, and architectural
changes. Run it before the other reviewers; do not include it in the parallel reviewer batch.
Review Priority
Review in this order:
- User goal and prior behavior
- Necessity and deletion
- Correctness and security
- Architecture
- SDD compliance
Treat the SDD as evidence, not as authority for whether code is necessary. A finding that would expand behavior or infrastructure requires user approval. Never apply it as an ordinary review fix.
rq (Request Review) Subagents
| Step | Parallel | Purpose |
|---|---|---|
| 1. Triage | No | Detect context, select reviewers, identify relevant skills to look for |
| 2. Simplicity | No | Mandatory necessity and deletion review for migrations, refactors, and architectural changes |
| 3. Reviewers | Yes (per reviewer) | Correctness, security, and other specialty analysis |
| 4. Synthesis | No | Deduplicate findings inline |
| 5. Architect | No | Architecture review |
| 6. SDD + Challenge | No | Check SDD compliance last, then validate findings |
rs (Respond to Review)
No subagents. Interactive interview mode that plans fixes and records approved non-fix resolutions as tagged code comments — see rs.md.
Dispatch Patterns
Follows code-subagents patterns:
- Parallel dispatch for independent reviewers
- Sequential dispatch for dependent steps
- Fresh subagent per task — no context pollution
- Relevant skill search pre-step before each analysis phase
- Error handling: Log failures, continue with partial results
Agent Dispatch
| Agent | Used In Step |
|---|---|
sentinel | Triage only (context retrieval, file analysis) |
oracle | Reviewers and challenge validation |
architect | Architect (architecture review) |
Synthesis is performed inline by the main agent.
References
| Reference | Purpose |
|---|---|
| rq.md | Request review workflow - detailed steps with prompts |
| rs.md | Respond to review workflow - interview mode |
| reviewers.md | Reviewer definitions and prompts |
| output.md | Output format specification |
Workflow Routing
What ships with it: 4 files
39.1 KB alongside SKILL.md
references/
- output.md5.2 KB
- reviewers.md21.1 KB
- rq.md11.8 KB
- rs.md1.1 KB
Gives 0 of the 12 instructions most quality gates skills give
Counted across 1,524 of the 2,830 authors here whose files we hold, read 2026-09-06
- Read full output and check exit codein 45 of 1524, across 40 files
- Verify output confirms the claimin 44 of 1524, across 39 files
- Identify the command that proves the claimin 43 of 1524, across 39 files
- Execute the full verification commandin 36 of 1524, across 30 files
- Produce a verification reportin 34 of 1524, across 18 files
- Review git diff changesin 30 of 1524, across 16 files
- Fix build failures immediatelyin 29 of 1524, across 9 files
- Group findings by severityin 28 of 1524
- State claim only with evidencein 27 of 1524, across 22 files
- Verify regression tests with red-green cyclein 26 of 1524, across 22 files
- Run the full test suitein 26 of 1524, across 25 files
- Run test suite with coveragein 25 of 1524, across 10 files
Said here and by no other author read
- Run simplicity review before other reviewers
- Use sentinel for triage and context retrieval
- Use oracle for reviewer personas and challenge validation
- Use architect for architecture and design review
- Deduplicate findings during synthesis
- Log failures and continue with partial results
Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once.