feat(skills): SKILL.md の name に plugin プレフィックスを統一付与 + lint 追加#77
Merged
Conversation
各 SKILL.md の `name:` を `<plugin>:<skill>` 形式に揃え、Skill ツール識別子をプラグイン名前空間と一致させる。`bun run docs` で各プラグイン AGENTS.md の component list も同期。 Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
- mutils に consecutive-review-loop スキルを新設。N 回連続パスまでサブエージェント レビュー → 修正のループを回し、失敗で streak を 0 にリセット。各レビューは byte 単位で同一の flat prompt を使い、過去の指摘や試行回数などの履歴情報を サブエージェントに渡さない（独立性を保つため） - 疑似コードブロックでアルゴリズムを明示 - AGENTS.md に「条件判定が明確な処理を指示する場合は疑似コードを書く」ルールを追加 - .claude/rules/ai-generated/ にスキル作成中に判明した agnix 関連の落とし穴を追記
|
Warning Review limit reached
More reviews will be available in 44 minutes and 17 seconds. Learn how PR review limits work. Your organization has run out of usage credits. Purchase more in the billing tab. ⌛ How to resolve this issue?After more reviews become available, a review can be triggered using the We recommend that you space out your commits to avoid hitting the rate limit. 🚦 How do rate limits work?CodeRabbit enforces hourly rate limits for each developer per organization. Our paid plans include higher PR review limits than trial, open-source, and free plans. In all cases, reviews become available again over time. During sustained high-volume PR review activity, CodeRabbit may temporarily slow when the next review becomes available. Please see our Fair Usage Limits Policy for further information. ℹ️ Review info⚙️ Run configurationConfiguration used: Organization UI Review profile: CHILL Plan: Pro Run ID: ⛔ Files ignored due to path filters (2)
📒 Files selected for processing (31)
📝 WalkthroughWalkthroughThis PR synchronizes plugin versions across the marketplace registry and systematically adds namespace-prefixed identifiers to all skill definitions. It updates thirteen plugins, introduces a new consecutive-review-loop skill for mutils, and clarifies instruction standards for agent documentation. ChangesPlugin Namespace Refactoring and Skill Registry Update
Estimated code review effort🎯 2 (Simple) | ⏱️ ~12 minutes Possibly related PRs
Poem
🚥 Pre-merge checks | ✅ 5✅ Passed checks (5 passed)
✏️ Tip: You can configure your own custom pre-merge checks in the settings. ✨ Finishing Touches🧪 Generate unit tests (beta)
Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out. Comment |
- `readPluginComponents` で `name` が `<plugin>:` プレフィックスを持たない場合に frontmatterErrors を発行 - ルート `check` スクリプトに `docs-tools check-list` を追加し、`bun run check` で違反を即検知 - mutils:consecutive-review-loop に同規約を適用、mutils を 0.22.3 へ bump Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
![coderabbitai[bot]](https://avatars.githubusercontent.com/in/347564?s=60&v=4){kind=small}
There was a problem hiding this comment.
Actionable comments posted: 3
🤖 Prompt for all review comments with AI agents
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.
Inline comments:
In `@AGENTS.md`:
- Around line 84-86: Update the rule that mandates pseudocode for agent-facing
docs (AGENTS.md / CLAUDE.md / SKILL.md) by adding an explicit
pseudocode/text-block requirement: when a document D contains conditional logic,
loops, counter updates, state resets, or termination conditions, require D to
include a pseudocode block that specifies exactly when to increment/decrement
counters, what each counter/state represents, when to reset state, and the
explicit termination condition; if D lacks such constructs the pseudocode block
remains optional—ensure the rule text references the documents (AGENTS.md,
CLAUDE.md, SKILL.md) and the required pseudocode elements (condition evaluation,
counting/reset behavior, termination) so authors know what to include.
In `@plugins/mutils/AGENTS.md`:
- Around line 30-47: The Components table is missing a row for the newly added
skill mutils:consecutive-review-loop; add a table entry named
"mutils:consecutive-review-loop" to the AGENTS.md Components table with a
concise description of its responsibility (e.g., running repeated review cycles
to refine outputs until convergence or acceptance), include intended trigger
phrases/usage examples, and ensure the regenerated table contains this row so
AGENTS.md documents the agent implementation per the project's guideline.
In `@plugins/mutils/skills/consecutive-review-loop/SKILL.md`:
- Line 2: Update the skill identifier in SKILL.md by changing the name field
value from "consecutive-review-loop" to the namespaced form
"mutils:consecutive-review-loop"; edit the `name` key in the SKILL.md header so
it follows the plugin-prefixed convention used by the registry and other mutils
skills.
🪄 Autofix (Beta)
Fix all unresolved CodeRabbit comments on this PR:
- Push a commit to this branch (recommended)
- Create a new PR with the fixes
ℹ️ Review info
⚙️ Run configuration
Configuration used: Organization UI
Review profile: CHILL
Plan: Pro
Run ID: 65dbda82-72d4-4c3e-99de-83ce5e186676
📒 Files selected for processing (67)
.claude-plugin/marketplace.json.claude/rules/ai-generated/gotchas.md.claude/rules/ai-generated/project-context.mdAGENTS.mdplugins/cc-hooks-ts/AGENTS.mdplugins/cc-hooks-ts/plugin.jsonplugins/cc-hooks-ts/skills/cc-hooks-ts/SKILL.mdplugins/context/AGENTS.mdplugins/context/plugin.jsonplugins/context/skills/generate-docs-index/SKILL.mdplugins/context/skills/refactor-project-context/SKILL.mdplugins/context/skills/verify-context/SKILL.mdplugins/debug/AGENTS.mdplugins/debug/plugin.jsonplugins/debug/skills/plugin-debug/SKILL.mdplugins/devkit/AGENTS.mdplugins/devkit/plugin.jsonplugins/devkit/skills/cli-compliance/SKILL.mdplugins/devkit/skills/init-project/SKILL.mdplugins/devkit/skills/standards-audit/SKILL.mdplugins/devkit/skills/standards/SKILL.mdplugins/diagram-render/AGENTS.mdplugins/diagram-render/plugin.jsonplugins/diagram-render/skills/draw-diagram/SKILL.mdplugins/diagram-render/skills/render/SKILL.mdplugins/gh-projects/AGENTS.mdplugins/gh-projects/plugin.jsonplugins/gh-projects/skills/cli/SKILL.mdplugins/gh-projects/skills/create-epic/SKILL.mdplugins/gh-projects/skills/decompose-epic/SKILL.mdplugins/gh-projects/skills/epic-story-task/SKILL.mdplugins/gh-projects/skills/plan-dependencies/SKILL.mdplugins/gh-projects/skills/review-progress/SKILL.mdplugins/github-issue-db/AGENTS.mdplugins/github-issue-db/plugin.jsonplugins/github-issue-db/skills/report-repo-issues/SKILL.mdplugins/github-issue-db/skills/search-similar-issues/SKILL.mdplugins/github-issue-db/skills/update-existing-issues/SKILL.mdplugins/github-workflow/AGENTS.mdplugins/github-workflow/plugin.jsonplugins/github-workflow/skills/create-issue/SKILL.mdplugins/mutils/AGENTS.mdplugins/mutils/plugin.jsonplugins/mutils/skills/consecutive-review-loop/SKILL.mdplugins/mutils/skills/feedback/SKILL.mdplugins/mutils/skills/ideal-driven-design/SKILL.mdplugins/mutils/skills/investigate-repo/SKILL.mdplugins/mutils/skills/issue-status-review/SKILL.mdplugins/mutils/skills/skill-create/SKILL.mdplugins/mutils/skills/task-history/SKILL.mdplugins/mutils/skills/temp-skill/SKILL.mdplugins/swarm/AGENTS.mdplugins/swarm/plugin.jsonplugins/swarm/skills/swarm/SKILL.mdplugins/swarm/skills/team-design/SKILL.mdplugins/ui-dev/AGENTS.mdplugins/ui-dev/plugin.jsonplugins/ui-dev/skills/dev-command/SKILL.mdplugins/ui-dev/skills/figma-data/SKILL.mdplugins/ui-dev/skills/figma-implement/SKILL.mdplugins/ui-dev/skills/figma-screenshot/SKILL.mdplugins/workspace-id/AGENTS.mdplugins/workspace-id/plugin.jsonplugins/workspace-id/skills/workspace-id/SKILL.mdplugins/zenn-article/AGENTS.mdplugins/zenn-article/plugin.jsonplugins/zenn-article/skills/write-article/SKILL.md
Comment on lines
+84
to
+86
| - IF: AGENTS.md / CLAUDE.md / SKILL.md などエージェント向け指示文書に、条件分岐・ループ・カウンタ更新・状態リセット・終了条件など条件判定が明確な処理を書く; THEN MUST: 疑似コード（`pseudocode` / `text` コードブロック）を併記する | ||
| - 理由: 散文だけで状態遷移を記述するとエージェント間で解釈がブレる。疑似コードがあれば「いつ何をカウントし・いつリセットするか」が一意に決まる | ||
| - MUST NOT: 「成功したらカウントを増やす」のような散文だけで複雑な状態遷移を済ませる |
There was a problem hiding this comment.
🛠️ Refactor suggestion | 🟠 Major | ⚡ Quick win
Add pseudocode next to the new conditional instruction rule.
This section introduces conditional/state-transition logic in prose only; add a pseudocode or text block that explicitly defines condition evaluation, counting/reset behavior, and termination to remove ambiguity.
Proposed patch
## 指示の書き方
- IF: AGENTS.md / CLAUDE.md / SKILL.md などエージェント向け指示文書に、条件分岐・ループ・カウンタ更新・状態リセット・終了条件など条件判定が明確な処理を書く; THEN MUST: 疑似コード（`pseudocode` / `text` コードブロック）を併記する
- 理由: 散文だけで状態遷移を記述するとエージェント間で解釈がブレる。疑似コードがあれば「いつ何をカウントし・いつリセットするか」が一意に決まる
- MUST NOT: 「成功したらカウントを増やす」のような散文だけで複雑な状態遷移を済ませる
+
+```pseudocode
+when writing instruction document D in {AGENTS.md, CLAUDE.md, SKILL.md}:
+ if D contains conditional logic, loops, counter updates, state resets, or termination conditions:
+ require pseudocode block in D
+ pseudocode must define:
+ - when to increment/decrement counters
+ - what each counter represents
+ - when to reset counters/state
+ - explicit termination condition
+ else:
+ pseudocode block is optional
+```As per coding guidelines: "**/{AGENTS,CLAUDE,SKILL}.md: When writing conditional logic, loops, counter updates, state resets, or termination conditions ... MUST include pseudocode alongside prose descriptions."
🤖 Prompt for AI Agents
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.
In `@AGENTS.md` around lines 84 - 86, Update the rule that mandates pseudocode for
agent-facing docs (AGENTS.md / CLAUDE.md / SKILL.md) by adding an explicit
pseudocode/text-block requirement: when a document D contains conditional logic,
loops, counter updates, state resets, or termination conditions, require D to
include a pseudocode block that specifies exactly when to increment/decrement
counters, what each counter/state represents, when to reset state, and the
explicit termination condition; if D lacks such constructs the pseudocode block
remains optional—ensure the rule text references the documents (AGENTS.md,
CLAUDE.md, SKILL.md) and the required pseudocode elements (condition evaluation,
counting/reset behavior, termination) so authors know what to include.
masseater
changed the title
5 tasks
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
plugins/*/skills/*/SKILL.mdの frontmatternameを<plugin>:<skill>形式に統一（38 件）Skill(<plugin>:<skill>)参照と整合する命名へ揃え、プラグイン名前空間で衝突を防ぐdoc-engineのreadPluginComponentsに<plugin>:プレフィックス必須チェックを追加bun run checkにdocs-tools check-listを組み込み、違反が CI/pre-push で検知されるplugin.jsonを patch bump（repository-lint/require-version-bump対応）Test plan
bun run check:plugin-listで違反が検知されることを確認（プレフィックス削除で発火）bun run check/ pre-push 通過Relates to #49
Relates to #30