with one click
review-pr
// Read-only pull request review workflow with risk analysis, targeted checklists, and Codex subagent consultation.
// Read-only pull request review workflow with risk analysis, targeted checklists, and Codex subagent consultation.
AReaL commit message conventions. MUST load on every git commit -- provides Conventional Commits format with scope inference from file paths.
Upgrade focused runtime dependencies in AReaL. First validates and updates per-package API checklists for structural completeness, then updates pyproject files, resolves conflicts, locks, updates the Dockerfile, and audits API compatibility against the checklists.
AReaL commit message conventions. MUST load on every git commit -- provides Conventional Commits format with scope inference from file paths.
AReaL commit message conventions. MUST load on every git commit -- provides Conventional Commits format with scope inference from file paths.
Guide for adding a new model to the Archon engine. Use when user wants to add support for a new HuggingFace model architecture in ArchonEngine.
Guide for adding a new dataset loader to AReaL. Use when user wants to add a new dataset.
| name | review-pr |
| description | Read-only pull request review workflow with risk analysis, targeted checklists, and Codex subagent consultation. |
Use this skill when the user asks for a PR review of the current branch or a specific PR.
--quick to stop after the change analysis phasegh for PR metadata and git diff retrieval.references/review-pr-domains-and-signals.mdreferences/review-pr-templates.mdgh pr view to fetch PR title, body, state, draft status, and changed files.references/review-pr-domains-and-signals.md.CRITICAL, HIGH, MEDIUM, or LOW.CHANGE_ANALYSIS_REPORT that lists:
If --quick is set, return the change analysis report and stop here.
references/review-pr-templates.md.Consult the matching Codex subagents registered in .codex/config.toml when relevant:
archon-expertfsdp-expertmegatron-expertalgorithm-expertlauncher-expertIf the Codex runtime supports parallel subagent execution, run independent review passes in parallel. Otherwise, execute them serially.
Produce findings first, ordered by severity:
CRITICALHIGHMEDIUMLOWFor every finding, include:
Use this structure:
CHANGE_ANALYSIS_REPORT:
- detected_domains: [...]
- detected_signals: [...]
- risk_level: ...
- affected_files: [...]
- related_frameworks: [...]
- identified_risks: [...]
Findings
1. [severity] Title — path:line
- Problem: ...
- Fix: ...
Open Questions
- ...
Residual Risk
- ...