Agent Skill Bridge Review
Skill7 starsChanged 5 months agoMITView on GitHub
Review changes to the Agent Skills import/export bridge for path safety, round-trip fidelity, and validation correctness.
In this repository140 other files it gives its agents.
- AGENTS.mdAGENTS.md
- .codex/AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- .github/copilot-instructions.mdCopilot instructions
- static/llms.txtllms.txt
- ask-codexSkill
- river-review-disciplineSkill
- skill-creatorSkill
- skill-ops-plannerSkill
- skill-optimizerSkill
- commandsSkill
- adversarial-reviewSkill
- review-teamSkill
- river-review-architectureSkill
- river-review-codeSkill
- river-review-docsSkill
- river-review-frontendSkill
- river-review-performanceSkill
- river-review-security-auditSkill
- river-review-securitySkill
- river-reviewSkill
- river-review-testingSkill
- unknown-coverage-reviewSkill
- Coverage and Failure Path GapsSkill
- Flaky Test Risk CheckSkill
- GitHub Actions Workflow Security ReviewSkill
- Standard Review Policy for DownstreamSkill
- Test Assertion Effectiveness 常に PASS するテストの検出Skill
- Test Presence for Changed CodeSkill
- Test Naming and StructureSkill
- テスト観点レビュー(差分ドリブン)Skill
- a11y Accessible Name BasicsSkill
- Altitude Generalization GuardSkill
- API Compatibility and Test Gap ReviewSkill
- Assumption Resolution Trace Plan の前提解消トレーサビリティSkill
- Async Correctness 非同期処理の正しさ検証Skill
- Behavior-Structure Separation 振る舞い変更と構造変更の分離・外部挙動維持Skill
- Closure Scope Retention GuardSkill
- Component Variants / States Documentation コンポーネント状態の文書化Skill
- Configuration File ReviewSkill
- Cross-File Leakage リファクタ後の caller 側残骸検出Skill
- Design Source-of-Truth Conformance デザイン定義準拠Skill
- Design System Component Reuse GuardSkill
- Design Token EnforcementSkill
- Detector Detection Power 検査器の検出力の検証Skill
- Documentation Hygiene ドキュメント衛生Skill
- End-to-End Wiring 末端到達・貫通の検証Skill
- Existing-Pattern Conformance 既存パターン準拠の確認Skill
- Firebase Security Rules ReviewSkill
- Fix Scope Integrity 指摘対応ループのスコープ逸脱・前提破壊検出Skill
- GitHubレビューコメント対応(修正案つき)Skill
- Hallucinated Reference 幻覚的参照の実在確認Skill
- Hello Skill (Always-On Sample)Skill
- i18n Unused Key ReviewSkill
- Impact Evidence Coverage 影響・失敗系・外部依存の証拠充足Skill
- Independent Review SynthesisSkill
- Invisible Unicode Injection Scan 不可視 Unicode コード注入検出Skill
- Knowledge-to-Code Alignment 新知識のコード反映・設計知識の保全Skill
- Laravel Eloquent N+1 and Query Efficiency ReviewSkill
- Laravel Mass Assignment and Authorization ReviewSkill
- The first 60 shown.
The file
We split this skill into the rules it gives an agent
4 rules. About 0 are common, 3 are distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈3
Distinctive · estimate
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 38
Test coverage: every newly exported function from the module must have at least one node:test case.
- Distinctive: line 42
Do not critique the RR skill schema itself.
- Distinctive: line 43
Do not flag auto-fill behaviour as missing validation when the converted metadata passes the strict RR schema.
- Distinctive: line 57
If test fixtures are added without corresponding logic changes, that is expected (test-only commits).
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Pattern declaration
Primary pattern: Reviewer Secondary patterns: Inversion Why: ブリッジモジュールのパス安全性・往復忠実性・バリデーション正当性をチェックリスト型で評価するが、対象ファイル外の変更では実行不要
Guidance
- Path traversal:
assertSafePathmust reject ids containing..,/, or NUL bytes. Any new file-write path must route through this function orsanitizeSkillId. - Round-trip fidelity: export followed by re-import must preserve
name,description, and body content. Verify that new fields added to conversion logic do not break this property. - Auto-fill correctness:
convertAgentSkillToRRmust not overwrite explicitly provided values (id, category, phase, applyTo). Defaults apply only when the field is absent. - Validation gate: both strict and loose validation paths must be exercised. The
errorsarray must capture invalid skills without aborting the entire import batch. - Test coverage: every newly exported function from the module must have at least one
node:testcase.
Non-goals
- Do not critique the RR skill schema itself; focus on bridge logic only.
- Do not flag auto-fill behaviour as missing validation when the converted metadata passes the strict RR schema.
Pre-execution Gate / 実行前ゲート
このスキルは以下の条件がすべて満たされない限りNO_REVIEWを返す。
- 差分にAgent Skillブリッジ関連ファイル(
agent-skill-bridge.mjs,validate-agent-skills.mjs,agent-skill-loose.schema.json等)の変更が含まれている - 差分がコメント・JSDoc・空白のみの変更ではない
- inputContextにdiffが含まれている
ゲート不成立時の出力: NO_REVIEW: agent-skill-bridge — Agent Skillブリッジ関連の実質的なコード変更が検出されない
False-positive guards
- If test fixtures are added without corresponding logic changes, that is expected (test-only commits).
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

