本文へ移動
cccskills
無料GitHub で公開

plugin-review

Review plugin quality with tiered checks and dependency scoping. Use for PR and pre-release audits.

インストール方法を見る

含まれるファイル(5)

  • SKILL.md3.9 KB
  • modules/dependency-detection.md1.5 KB
  • modules/tier-branch.md2.3 KB
  • modules/tier-pr.md1.9 KB
  • modules/tier-release.md2.9 KB

SKILL.md(原文)

インストールする前に、エージェントに与えられる指示の中身を確認できます。

Plugin Review

Overview

Tiered quality review of plugins with dependency-aware scoping.

When NOT To Use

  • Reviewing one skill rather than a plugin (use abstract:skills-eval)
  • Reviewing hooks (use abstract:hooks-eval)
  • Tracing Skill() references across plugins (use abstract:skill-graph-audit)

Tiers

TierTriggerScopeDepthDuration
branchDefaultAffected and relatedQuick gates~2 min
prBefore mergeAffected and relatedStandard~5 min
releaseBefore version bumpAll 17 pluginsFull~15 min

Orchestration

  1. Detect scope: parse --tier flag, find affected plugins from git diff, resolve related plugins from docs/plugin-dependencies.json
  2. Plan: build check matrix (tier x plugin x role)
  3. Execute: run checks per tier definition
  4. Report: per-plugin table, aggregate verdict

Scope Detection

Affected plugins: git diff main --name-only filtered to plugins/*/.

Related plugins: load docs/plugin-dependencies.json, look up each affected plugin's reverse index to find dependents. Mark as "related" (lighter checks).

If --tier release or no git diff available, scope to all plugins.

Module Loading

  • Always: this SKILL.md (orchestration logic)
  • branch tier: load modules/tier-branch.md
  • pr tier: load modules/tier-branch.md then modules/tier-pr.md
  • release tier: load all tier modules plus modules/tier-release.md
  • When resolving deps: load modules/dependency-detection.md

Verdict

ResultMeaning
PASSAll checks green
PASS-WITH-WARNINGSNon-blocking issues
FAILBlocking issues found

Output Format

Plugin Review (<tier> tier)
Affected: <list>
Related:  <list> (<reason>)

Plugin          test  lint  type  reg   verdict
<name>          PASS  PASS  PASS  PASS  PASS
...

Verdict: <PASS|PASS-WITH-WARNINGS|FAIL> (N/N plugins healthy)

PR and release tiers add scorecard sections.

Quality Gate Mode

The --quality-gate flag enables CI/CD integration with exit codes that distinguish warnings from failures:

  • 0: all quality gates passed
  • 1: warnings present but gates passed (non-blocking)
  • 2: quality gate failures (blocking)
  • 3: critical issues found (blocking)

Use --fail-on warning to treat warnings as blocking.

Configuration

Place a .plugin-review.yaml file in the plugin root to customize thresholds and focus areas:

plugin_review:
  quality_gates:
    structure_min: 80
    skills_min: 75
    hooks_min: 70
    tokens_max_total: 50000
    bloat_max_percentage: 15
  focus_areas:
    - skills
    - hooks
    - tokens
  exclude_patterns:
    - "*/legacy/*"
    - "*/deprecated/*"
  severity_overrides:
    missing_description: warning
    large_file: info

See the /plugin-review command reference for full usage examples.

Exit Criteria

  • The output includes a per-plugin table with columns: test, lint, type, reg, verdict, and an aggregate PASS / PASS-WITH-WARNINGS / FAIL verdict.
  • Scope detection identifies affected plugins via git diff main --name-only filtered to plugins/*/; if git diff is unavailable, the skill falls back to all-plugin scope and states this explicitly.
  • Any plugin scoring below the structure_min (default 80) or skills_min (default 75) threshold is listed as a FAIL, not a warning.
  • --quality-gate mode returns exit code 2 for blocking failures and exit code 1 for non-blocking warnings, distinguishable by the calling CI step.

レビュー

まだレビューはありません。使ってみた感想をお寄せください。

同じリポジトリのスキル

概要と使いどころ

Shapes turns action-first: action leads, steps numbered, state restated. Use for ADHD-friendly output. Do not use to trim tokens; use response-compression.

日本語の概要は準備中です。原文の説明を表示しています。

athola/claude-night-market3412026年10月10日 更新

Inverts burden of proof for code additions. Use when reviewing PRs, planning refactors, or running unbloat to challenge every addition's necessity.

日本語の概要は準備中です。原文の説明を表示しています。

athola/claude-night-market3412026年10月10日 更新

Tracks per-agent token usage and flags waste in parallel dispatch. Use when evaluating parallel agent efficiency or after a multi-agent run.

日本語の概要は準備中です。原文の説明を表示しています。

athola/claude-night-market3412026年10月10日 更新

Coordinates Claude agent teams via filesystem protocol. Use when orchestrating parallel agents with task dependencies. Do not use for single-agent tasks.

日本語の概要は準備中です。原文の説明を表示しています。

athola/claude-night-market3412026年10月10日 更新

Evaluates API surface design, consistency, and exemplar alignment. Use when reviewing public API changes or before releasing a new API surface.

日本語の概要は準備中です。原文の説明を表示しています。

athola/claude-night-market3412026年10月10日 更新

Selects architecture paradigm via research before scaffolding. Use when architecture is undecided and the choice needs justification and documentation.

日本語の概要は準備中です。原文の説明を表示しています。

athola/claude-night-market3412026年10月10日 更新

athola のスキルをすべて見る

このスキルの問題を報告する