From python
Performs multi-agent code reviews of git diffs/PRs/branches with parallel specialized reviewers, architecture validation, and challenge validation. Use rq/rs commands or triggers like 'review this'.
npx claudepluginhub martinffx/atelier --plugin pythonThis skill uses the workspace's default tool permissions.
Multi-agent code analysis with parallel reviewers and challenge validation.
Conducts deep PR reviews using 6-7 parallel specialized agents for code quality, security, testing, frontend/backend architecture. Use for thorough pull request analysis before merging.
Reviews GitHub pull requests using parallel subagents for CLAUDE.md compliance, bugs, git history context, past feedback, and code comment adherence.
Reviews pull requests autonomously with parallel multi-agent analysis for security, performance, testing, architecture, and style on changed files.
Share bugs, ideas, or general feedback.
Multi-agent code analysis with parallel reviewers and challenge validation.
Uses explicit subagent dispatch patterns from code-subagents.
If gfreview is not installed for rs:
Error: rs requires gfreview.
Install from: https://github.com/martinffx/gfreview
curl -fsSL https://raw.githubusercontent.com/martinffx/gfreview/main/install.sh | bash
$0 = command (rq or rs) $1 = target (branch or PR number)
| Invocation | Behavior |
|---|---|
rq | Review diff to main branch |
rq develop | Review diff to develop branch |
rq 42 | Requires gfreview — review PR #42 |
rs | Requires gfreview — find PR for current branch |
rs 42 | Requires gfreview — respond to PR #42 |
gh pr list --head $(git branch --show-current) --json number --jq '.[0].number'
| Step | Subagent | Uses | Parallel | Purpose |
|---|---|---|---|---|
| 1 | Triage | clerk agent (minimax-m2.5) | No | Detect context, select reviewers, identify skills to load |
| 2 | Reviewers | general subagent | Yes (per reviewer) | Specialty analysis (loads detected skills) |
| 3 | Synthesis | general subagent | No | Deduplicate findings |
| 4 | Architect | architect agent (kimi-k2.5) | No | Architecture review |
| 5 | Challenge | oracle agent (glm-5) | No | Validate findings with sequential-thinking |
| Step | Subagent | Uses | Parallel | Purpose |
|---|---|---|---|---|
| 1 | Analysis | general subagent | Yes (per discussion) | Analyze feedback (loads relevant skills) |
| 2 | Validation | general subagent | No | Validate suggested fixes |
Follows code-subagents patterns:
| Agent | Model | Used In Step |
|---|---|---|
clerk | minimax-m2.5 | Triage (context retrieval, file analysis) |
architect | kimi-k2.5 | Architect (architecture review) |
oracle | glm-5 | Challenge (validate findings, sequential-thinking) |
general | (varies) | Reviewers, Synthesis, Validation |
See agents/ for agent definitions.
When gfreview is installed:
gfreview list --json --state opengfreview discussions <id>Each finding posted as inline comment with severity prefix:
Blocker:Issue:Suggestion:Nit:See gfreview.md for detailed command reference.
| Reference | Purpose |
|---|---|
| rq.md | Request review workflow - detailed steps with prompts |
| rs.md | Respond to review workflow - detailed steps with prompts |
| reviewers.md | Reviewer definitions and prompts |
| output.md | Output format specification |
| gfreview.md | gfreview CLI integration |
| context-flow.md | Data flow between workflow steps |