Clade coverage-driven project review — walks every VERIFY.md checkpoint, fixes failures in-session, converges when all checkpoints pass. NOT the Claude Code built-in /review (which reviews a single pull request diff) — if the user wants a PR review, route to /review-pr (Clade's PR reviewer) or the CC built-in.
Scanned 6/11/2026
Install via CLI
Skills Directoryopenskills install shenxingy/Clade---
name: review
description: Clade coverage-driven project review — walks every VERIFY.md checkpoint, fixes failures in-session, converges when all checkpoints pass. NOT the Claude Code built-in /review (which reviews a single pull request diff) — if the user wants a PR review, route to /review-pr (Clade's PR reviewer) or the CC built-in.
when_to_use: "review everything, test all, full review, VERIFY.md, 全面测试, coverage review — NOT for post-iteration anchor checks in autonomous loops (use /verify), NOT for PR review (use /review-pr or the CC built-in /review)"
user_invocable: true
---
# Review Skill
Performs a systematic, coverage-driven review of the project by working through every checkpoint in `VERIFY.md`. Unlike a free-form code review, this skill tests specific scenarios end-to-end, fixes failures immediately, and only declares convergence when all checkpoints are ✅ or ⚠.
**Convergence condition**: all checkpoints in VERIFY.md are ✅ (pass) or ⚠ (known limitation). No ⬜ (untested) or ❌ (fail) remaining.
No comments yet. Be the first to comment!
Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...
