npx claudepluginhub iyulab/claude-plugins --plugin iyuThis skill is limited to using the following tools:
Review PRs aligned with project philosophy. Focus on what Claude wouldn't catch without project context.
Creates isolated Git worktrees for feature branches with prioritized directory selection, gitignore safety checks, auto project setup for Node/Python/Rust/Go, and baseline verification.
Executes implementation plans in current session by dispatching fresh subagents per independent task, with two-stage reviews: spec compliance then code quality.
Dispatches parallel agents to independently tackle 2+ tasks like separate test failures or subsystems without shared state or dependencies.
Review PRs aligned with project philosophy. Focus on what Claude wouldn't catch without project context.
https://github.com/user/repo/pull/123#123 (in repo context)Flags: --quick (blockers only) | --save (save to ./claudedocs/pr-review-[date]-[number].md) | --security-focus (security-focused review)
gh pr view $0 --json state,mergeable,reviewDecision,statusCheckRollupgh pr view $0 --json title,body,author,files,additions,deletions,commits,comments,reviewsgh pr diff $0From the pre-loaded status data:
merged / closed → SKIPdraft → Brief reviewFrom the pre-loaded details: Identify: What problem does it solve? What approach? Contributor type (First-time / Returning / Core).
Classify findings by severity:
| Level | Meaning |
|---|---|
| Blocker | Must fix — bugs, security, critical logic errors |
| Major | Should fix — performance, missing tests, pattern violations |
| Minor | Nice to have — naming, docs, minor improvements |
| Praise | Must include at least 1 — acknowledge good work |
Security issues are always Blocker.
Read CLAUDE.md / README.md. Evaluate using the philosophy-alignment-guide.md:
| Dimension | Question |
|---|---|
| Core Mission Fit | Serves project's core purpose? |
| Scope Alignment | Library vs application responsibility? |
| Pattern Consistency | Consistent with existing architecture? |
| User Base Impact | Benefits majority or niche? |
Overall: High (4-5 avg) / Medium (3-3.9) / Low (1-2.9)
Latent discovery: Does this PR reveal gaps? Missing tests elsewhere? API design issues? Documentation needs?
| Quality HIGH | Quality LOW | |
|---|---|---|
| Philosophy HIGH | APPROVE | MERGE_WITH_FIXES |
| Philosophy MED | APPROVE_WITH_NOTES | REQUEST_CHANGES |
| Philosophy LOW | REDIRECT | DECLINE |
For decision examples, see decision-examples.md.
Adjust tone by contributor type:
For tone rules, see tone-rules.md.
Blockers only → APPROVE or REQUEST_CHANGES.