Referenced asset is missing from the plugin package.
River Review
Versioned Skill Registry of code-review skills driven by a perspective-based review agent (code, security, performance, architecture, testing, adversarial) that verifies findings against the diff.
river-review-maintainers/river-review · v1.126.0 · Development & Workflow
Trust Score
72
Security
64
Surfaces
136
What is River Review?
River Review is a published development & workflow plugin for AI coding agents in the codex ecosystem, developed by river-review maintainers and distributed through the HOL AI plugin registry. Versioned Skill Registry of code-review skills driven by a perspective-based review agent (code, security, performance, architecture, testing, adversarial) that verifies findings against the diff.
- Canonical slug
- river-review-maintainers/river-review
- Version
- v1.126.0 · updated Oct 9, 2026
- Open data
- entity.json (JSON-LD)
Trust & Reputation
Factor Analysis
Per-metric points (0–100 each) combined via a weighted average into the overall score.
Registry Snapshot
- Repository
- https://github.com/s977043/river-review
- Publisher verification
- No
- Marketplace source
- Unknown
- Scanner
- Broker fallback
- Safety label
- caution
- Digest verified
- Yes
Trust & reputation
Trust & Reputation
Factor Analysis
Per-metric points (0–100 each) combined via a weighted average into the overall score.
Provenance
- Plugin root
- .
- Source repo
- https://github.com/s977043/river-review
- Source commit
- d418c1935f88…
- Publisher verified
- No
- Owner verified
- Not owner verified
Continuous scanner CI detected
No action is required. This plugin receives the full trust score.
Verified badge not detected
Add the HOL verified badge to the repository README to score +2% trust. Plugin owners can open that pull request from Guard Plugins.
Security Posture
- Provider
- registry-broker-fallback
- Grade
- D · caution
- Version
- Unknown
Findings
privacyPolicyURL should be present for marketplace readiness.
termsOfServiceURL should be present for marketplace readiness.
Cisco skill scanner timed out after 60000 ms
Cisco skill scanner timed out after 60000 ms
Cisco skill scanner timed out after 60000 ms
Cisco skill scanner timed out after 60000 ms
Cisco skill scanner timed out after 60000 ms
Script permission declarations are required for scripts/: scripts/templates/skill/README.md, scripts/templates/skill/SKILL.md, scripts/templates/skill/eval/promptfoo.yaml, scripts/templates/skill/skill.yaml, scripts/templates/skill/prompt/system.md, scripts/templates/skill/prompt/user.md
Cisco skill scanner timed out after 60000 ms
Cisco skill scanner timed out after 60000 ms
Cisco skill scanner timed out after 60000 ms
Cisco skill scanner timed out after 60000 ms
Cisco skill scanner timed out after 60000 ms
Cisco skill scanner timed out after 60000 ms
Cisco skill scanner timed out after 60000 ms
Cisco skill scanner timed out after 60000 ms
Cisco skill scanner timed out after 60000 ms
Cisco skill scanner timed out after 60000 ms
Cisco skill scanner timed out after 60000 ms
Cisco skill scanner timed out after 60000 ms
Cisco skill scanner timed out after 60000 ms
Cisco skill scanner timed out after 60000 ms
Cisco skill scanner timed out after 60000 ms
Cisco skill scanner timed out after 60000 ms
Cisco skill scanner timed out after 60000 ms
Cisco skill scanner timed out after 60000 ms
Cisco skill scanner timed out after 60000 ms
Cisco skill scanner timed out after 60000 ms
Cisco skill scanner timed out after 60000 ms
Cisco skill scanner timed out after 60000 ms
Cisco skill scanner timed out after 60000 ms
Cisco skill scanner timed out after 60000 ms
Cisco skill scanner timed out after 60000 ms
Cisco skill scanner timed out after 60000 ms
Cisco skill scanner timed out after 60000 ms
Cisco skill scanner timed out after 60000 ms
Cisco skill scanner timed out after 60000 ms
Cisco skill scanner timed out after 60000 ms
Cisco skill scanner timed out after 60000 ms
Cisco skill scanner timed out after 60000 ms
Cisco skill scanner timed out after 60000 ms
Cisco skill scanner timed out after 60000 ms
Cisco skill scanner timed out after 60000 ms
Cisco skill scanner timed out after 60000 ms
Cisco skill scanner timed out after 60000 ms
Cisco skill scanner timed out after 60000 ms
Cisco skill scanner timed out after 60000 ms
Cisco skill scanner timed out after 60000 ms
Cisco skill scanner timed out after 60000 ms
Cisco skill scanner timed out after 60000 ms
Cisco skill scanner timed out after 60000 ms
Cisco skill scanner timed out after 60000 ms
Cisco skill scanner timed out after 60000 ms
Cisco skill scanner timed out after 60000 ms
Cisco skill scanner timed out after 60000 ms
Cisco skill scanner timed out after 60000 ms
Cisco skill scanner timed out after 60000 ms
Cisco skill scanner timed out after 60000 ms
Cisco skill scanner timed out after 60000 ms
Cisco skill scanner timed out after 60000 ms
Cisco skill scanner timed out after 60000 ms
Cisco skill scanner timed out after 60000 ms
Cisco skill scanner timed out after 60000 ms
Cisco skill scanner timed out after 60000 ms
Cisco skill scanner timed out after 60000 ms
Cisco skill scanner timed out after 60000 ms
Cisco skill scanner timed out after 60000 ms
Cisco skill scanner timed out after 60000 ms
Cisco skill scanner timed out after 60000 ms
Cisco skill scanner timed out after 60000 ms
Cisco skill scanner timed out after 60000 ms
Cisco skill scanner timed out after 60000 ms
Cisco skill scanner timed out after 60000 ms
Cisco skill scanner timed out after 60000 ms
Cisco skill scanner timed out after 60000 ms
Cisco skill scanner timed out after 60000 ms
Cisco skill scanner timed out after 60000 ms
Cisco skill scanner timed out after 60000 ms
Cisco skill scanner timed out after 60000 ms
Cisco skill scanner timed out after 60000 ms
Cisco skill scanner timed out after 60000 ms
Cisco skill scanner timed out after 60000 ms
Cisco skill scanner timed out after 60000 ms
Cisco skill scanner timed out after 60000 ms
Cisco skill scanner timed out after 60000 ms
Cisco skill scanner timed out after 60000 ms
Cisco skill scanner timed out after 60000 ms
Cisco skill scanner timed out after 60000 ms
Cisco skill scanner timed out after 60000 ms
Cisco skill scanner timed out after 60000 ms
Cisco skill scanner timed out after 60000 ms
Cisco skill scanner timed out after 60000 ms
Cisco skill scanner timed out after 60000 ms
Cisco skill scanner timed out after 60000 ms
Cisco skill scanner timed out after 60000 ms
Cisco skill scanner timed out after 60000 ms
Cisco skill scanner timed out after 60000 ms
Cisco skill scanner timed out after 60000 ms
Cisco skill scanner timed out after 60000 ms
Cisco skill scanner timed out after 60000 ms
Cisco skill scanner timed out after 60000 ms
Cisco skill scanner timed out after 60000 ms
Cisco skill scanner timed out after 60000 ms
Cisco skill scanner timed out after 60000 ms
Cisco skill scanner timed out after 60000 ms
Cisco skill scanner timed out after 60000 ms
Cisco skill scanner timed out after 60000 ms
Cisco skill scanner exited with code 1: Error loading skill: No SKILL.md and no .md files found in /tmp/hol-skill-safety-B72W1x (lenient mode requires at least one markdown file)
Cisco skill scanner exited with code 1: Error loading skill: No SKILL.md and no .md files found in /tmp/hol-skill-safety-PSus2b (lenient mode requires at least one markdown file)
Cisco skill scanner exited with code 1: Error loading skill: No SKILL.md and no .md files found in /tmp/hol-skill-safety-sVqgMU (lenient mode requires at least one markdown file)
Cisco skill scanner exited with code 1: Error loading skill: No SKILL.md and no .md files found in /tmp/hol-skill-safety-rwcyAN (lenient mode requires at least one markdown file)
Cisco skill scanner timed out after 60000 ms
Cisco skill scanner timed out after 60000 ms
Cisco skill scanner timed out after 60000 ms
Cisco skill scanner timed out after 60000 ms
Cisco skill scanner timed out after 60000 ms
Cisco skill scanner timed out after 60000 ms
Cisco skill scanner timed out after 60000 ms
Cisco skill scanner timed out after 60000 ms
Cisco skill scanner timed out after 60000 ms
Cisco skill scanner timed out after 60000 ms
Cisco skill scanner timed out after 60000 ms
Cisco skill scanner timed out after 60000 ms
Cisco skill scanner timed out after 60000 ms
Cisco skill scanner timed out after 60000 ms
Cisco skill scanner timed out after 60000 ms
Cisco skill scanner timed out after 60000 ms
Cisco skill scanner timed out after 60000 ms
Cisco skill scanner timed out after 60000 ms
Cisco skill scanner timed out after 60000 ms
Cisco skill scanner timed out after 60000 ms
Cisco skill scanner timed out after 60000 ms
Cisco skill scanner timed out after 60000 ms
Cisco skill scanner timed out after 60000 ms
Cisco skill scanner timed out after 60000 ms
Cisco skill scanner timed out after 60000 ms
Cisco skill scanner timed out after 60000 ms
Cisco skill scanner timed out after 60000 ms
River Review — Frequently asked questions
- What is River Review?
- River Review is an AI plugin in the HOL registry. Versioned Skill Registry of code-review skills driven by a perspective-based review agent (code, security, performance, architecture, testing, adversarial) that verifies findings against the diff.
- How do I install River Review?
- Install River Review in your harness: Codex — codex plugin marketplace add s977043/river-review; Claude Code — /plugin marketplace add s977043/river-review; Any agent — npx skills add s977043/river-review. Full step-by-step guidance is on the HOL plugin page.
- How do I install River Review in Codex?
- To install River Review in Codex, start with codex plugin marketplace add s977043/river-review. The complete step-by-step install guide for Codex is on the HOL plugin page.
- How do I install River Review in Claude Code?
- To install River Review in Claude Code, start with /plugin marketplace add s977043/river-review. The complete step-by-step install guide for Claude Code is on the HOL plugin page.
- Is River Review free?
- Pricing for River Review is published on its HOL plugin page when the maker schedules a launch.
- Who publishes River Review?
- River Review is published by river-review maintainers and listed on HOL.
- Is River Review available now?
- River Review availability is listed on its HOL plugin page.
Install Guidance
Install in Claude Code
Install through the Claude Code plugin marketplace.
- 1
Add the marketplace
Run this inside a Claude Code session.
claude code - 2
Install the plugin
Use the plugin name and the marketplace name shown by the previous command.
claude code - 3
Scripted alternative
Non-interactive equivalent for scripts and CI pipelines. Add --scope project to pin the install to one repository.
shell
Plugin Manifest
{
"name": "river-review",
"version": "1.126.0",
"description": "Turn review into an organizational judgment asset. Review Judgment as Code for AI-assisted development, delivered as a capability pack for Codex: your team's review criteria as versioned, repo-owned skills (a Skill Registry), driven by a review agent that runs perspective-based reviewer roles (code, security, performance, architecture, testing, adversarial) and verifies findings against the diff so humans keep the high-risk judgment.",
"author": {
"name": "river-review maintainers",
"url": "https://github.com/s977043/river-review"
},
"homepage": "https://river-review.the3396.com/",
"repository": "https://github.com/s977043/river-review",
"license": "MIT",
"keywords": [
"code-review",
"security-review",
"performance",
"architecture",
"testing",
"adversarial-review",
"skills"
],
"skills": "./",
"interface": {
"displayName": "River Review",
"developerName": "river-review maintainers",
"shortDescription": "Turn review into an organizational judgment asset: a Skill Registry of review skills, driven by a review agent",
"longDescription": "River Review turns review into an organizational judgment asset. It is Review Judgment as Code for AI-assisted development: a capability pack that runs your team's review criteria as versioned, repo-owned skills (a Skill Registry), driven by a review agent that executes perspective-based reviewer roles (code, security, performance, architecture, testing) plus an adversarial pass, and verifies findings against the diff so human reviewers keep the high-risk judgment.",
"category": "Developer Tools",
"capabilities": [
"Read"
],
"websiteURL": "https://river-review.the3396.com/",
"composerIcon": "./assets/icon.svg"
},
"holManifestOrigin": "repository",
"registryIndexVersion": 5
}Marketplace Source
- Repo URL
- https://github.com/s977043/river-review
- Marketplace path
- Unknown
- Source path
- plugins/s977043/river-review
- Install policy
- AVAILABLE
Skills
136 SKILL.md files ship with this plugin. Preview, copy, or download each one, then install them with the Skills CLI.
ask-codex
.claude/skills/ask-codex/SKILL.md
Get a second opinion or independent review from Codex (OpenAI) via the local Codex CLI. Use when the user wants Codex to review a design memo, PR, diff, or decision, or to cross-check an approach from another model. Also trigger on "Codexに聞いて", "Codexと相談", "Codexにレビュー", "Codexの意見", "別のモデルで確認".
river-review-discipline
.claude/skills/river-review-discipline/SKILL.md
AI 駆動開発のレビュー品質を安定化させるレビュー規律。レビュー対象を分類し、要件・設計・差分・検証・報告を分けて見て、根拠に基づき approved / needs_revision / blocked / rejected を明示し、未検証事項と残リスクを隠さず memory に残す。「レビューして」「PR レビュー」「仕様/設計/差分/検証/報告をレビュー」「セキュリティ影響/データ影響を確認」「完了報告を検証」「/compact 前にレビュー記憶を作る」ときに使う。
skill-creator
.claude/skills/skill-creator/SKILL.md
Design a new Claude Code skill from a concrete use case and produce a repo-ready skill package. Use when the user asks to create a new skill, define a skill's responsibility, draft SKILL.md, choose frontmatter, design supporting files, or prepare eval criteria for a new skill. Also trigger on "スキルを作りたい", "スキルを作って", "スキルを追加して", "新しいスキル", "SKILL.md生成".
skill-ops-planner
.claude/skills/skill-ops-planner/SKILL.md
Create an operating policy and roadmap for a live portfolio of Claude Code skills. Use when the user asks to organize, govern, audit, measure, retire, or scale skills already used by a team or repository. Also trigger on "スキルの運用計画", "スキルポートフォリオ", "スキルロードマップ", "スキルを整理して".
skill-optimizer
.claude/skills/skill-optimizer/SKILL.md
Evaluate and improve an existing Claude Code skill using explicit success criteria and small controlled changes. Use when the user asks to optimize a skill, reduce over-triggering or under-triggering, improve reliability, tighten instructions, or add evals for a skill. Also trigger on "スキルを改善して", "スキルを最適化して", "スキルの品質を確認して".
<Skill Name>
scripts/templates/skill/SKILL.md
<What this skill does>
adversarial-review
skills/agent-skills/adversarial-review/SKILL.md
|
review-team
skills/agent-skills/review-team/SKILL.md
|
river-review-architecture
skills/agent-skills/river-review-architecture/SKILL.md
|
river-review-code
skills/agent-skills/river-review-code/SKILL.md
|
river-review-docs
skills/agent-skills/river-review-docs/SKILL.md
|
river-review-frontend
skills/agent-skills/river-review-frontend/SKILL.md
|
river-review-performance
skills/agent-skills/river-review-performance/SKILL.md
|
river-review-security-audit
skills/agent-skills/river-review-security-audit/SKILL.md
|
river-review-security
skills/agent-skills/river-review-security/SKILL.md
|
river-review-testing
skills/agent-skills/river-review-testing/SKILL.md
|
river-review
skills/agent-skills/river-review/SKILL.md
|
unknown-coverage-review
skills/agent-skills/unknown-coverage-review/SKILL.md
|
Coverage and Failure Path Gaps
skills/downstream/coverage-gap/SKILL.md
Find missing tests for critical paths, edge cases, and failure handling in changed code.
Flaky Test Risk Check
skills/downstream/flaky-test/SKILL.md
Detects patterns that make tests flaky and proposes stabilization steps.
GitHub Actions Workflow Security Review
skills/downstream/gha-workflow-security/SKILL.md
Reviews GitHub Actions workflow diffs for script injection of untrusted input, pull_request_target with untrusted checkout, over-broad GITHUB_TOKEN permissions, and unpinned third-party actions.
Standard Review Policy for Downstream
skills/downstream/review-policy-standard-downstream/SKILL.md
Applies standard AI review policy guidelines for downstream (test/QA) phase reviews.
Test Assertion Effectiveness 常に PASS するテストの検出
skills/downstream/test-assertion-effectiveness/SKILL.md
テストは存在するがアサーションが実質何も検証しておらず、実装が壊れても落ちない(常に PASS する)構造を diff-time で検出する。Check 1 missing assertion(テスト本体にアサーションが無い)、Check 2 tautological assertion(定数同士・入力自身・mock の戻り値自身を assert し SUT に依存しない)、Check 3 nonexistent expected literal(assertDontSee / assertNotContains 等の期待文字列が対象ファイルに実在しない)、Check 4 stale expected value(同一 diff で対象の出力が変わったのに期待値が据え置き)、Check 5 unscoped expectation(汎用的な属性・クラスを応答全体に対して assert し対象要素にスコープされていない)、Check 6 swallowed failure(例外の握り潰しや到達しない位置のアサーションで判定が成立しない)、の 6 Check を対象とする report-only。テストの有無は test-existence、未テスト経路の量は coverage-gap、非決定性は flaky-test、命名は test-naming、JS/TS の un-awaited resolves / rejects は vitest-mock-isolation、tdd-ledger artifact ベースの RED/GREEN 検証は plangate-tdd-evidence、.only / .skip / xit / @ts-ignore と空の catch は heuristic-review.mjs の決定論検出器へ委譲する
Test Presence for Changed Code
skills/downstream/test-existence/SKILL.md
Check whether changed code paths have corresponding tests and suggest minimal coverage.
Test Naming and Structure
skills/downstream/test-naming/SKILL.md
Ensure tests use clear naming and cover edge cases with proper describe/it structure.
テスト観点レビュー(差分ドリブン)
skills/downstream/test-plan-review/SKILL.md
変更差分から重要なテスト観点と欠落を洗い出し、優先度付きでテストケース案を提示する
a11y Accessible Name Basics
skills/midstream/a11y-accessible-name/SKILL.md
画像・ボタン・フォーム要素に適切なアクセシブルネームがあるか確認する。
Agent Skill Bridge Review
skills/midstream/agent-skill-bridge/SKILL.md
Review changes to the Agent Skills import/export bridge for path safety, round-trip fidelity, and validation correctness.
Altitude Generalization Guard
skills/midstream/altitude-generalization/SKILL.md
Detects per-caller special-cases (bandaids) bolted onto shared infrastructure/common functions, and when two or more same-kind special-cases exist proposes generalizing the lower-level mechanism instead.
API Compatibility and Test Gap Review
skills/midstream/api-compatibility/SKILL.md
Detect breaking API contract changes, DTO modifications without compatibility handling, and missing tests for changed API boundaries.
Assumption Resolution Trace Plan の前提解消トレーサビリティ
skills/midstream/assumption-resolution-trace/SKILL.md
plan artifact がある時のみ、plan 中の assumption / open question が実装で解消された証拠を diff・PR 本文と突合する evidence-sufficiency 観点。解消されないまま残った前提・未記録の新規 Unknown を検出する。plan 欠損時は発火しない(Pre-execution Gate)。plan 欠損でも PR 本文に前提が inline 列挙されていれば列挙分のみ部分評価し、計画 issue の bare 参照だけなら skip する
Async Correctness 非同期処理の正しさ検証
skills/midstream/async-correctness/SKILL.md
await 漏れ・floating promise・並行競合など、非同期処理の correctness バグを検出する。並列化の効率提案(SIMPLIFY Efficiency)や配線断点(e2e-wiring)ではなく、「await を忘れて結果・順序・エラー伝播が壊れる」実装バグに限定する
Behavior-Structure Separation 振る舞い変更と構造変更の分離・外部挙動維持
skills/midstream/behavior-structure-separation/SKILL.md
リファクタリング(構造変更)と機能変更(behavior change)が同一 diff に混在していないかを識別し、structural change に対する external behavior preservation の証拠(テスト・型・静的解析)が揃っているかを diff-time で確認する。証拠不足のときは Characterization Test 追加を促すか question とする。DTO/公開 API の破壊的変更検出は api-compatibility、完了主張の反証や抽出リファクタの性能特性退行は refactor-claim-audit、新知識の命名・責務・境界への反映は knowledge-to-code-alignment、投機的抽象化・スコープ逸脱は altitude-generalization / fix-scope-integrity へ委譲する
Closure Scope Retention Guard
skills/midstream/closure-scope-retention/SKILL.md
Detects long-lived objects (caches, listeners, singletons) that capture an entire enclosing scope via closures/environment capture, keeping large arrays or buffers alive, and proposes copying only the needed fields.
Component Variants / States Documentation コンポーネント状態の文書化
skills/midstream/component-variants-states/SKILL.md
新規追加された UI コンポーネントに、variants(種類)とインタラクティブ状態(hover / focus / disabled / loading / error)が定義・文書化されているかを確認し、状態設計の欠落を検出する
Configuration File Review
skills/midstream/config-json/SKILL.md
Review JSON/YAML configuration files for common issues and best practices.
Cross-File Leakage リファクタ後の caller 側残骸検出
skills/midstream/cross-file-leakage/SKILL.md
モジュール/スキルの構造変更で当該ファイルは更新したが、caller 側が古い構造(旧参照・旧シグネチャ・旧採番)を参照したまま残るパターンを検出する
Design Source-of-Truth Conformance デザイン定義準拠
skills/midstream/design-source-conformance/SKILL.md
リポジトリに DESIGN.md やデザイントークン定義が存在する場合に、新規 UI 実装の色・余白・フォントサイズ・角丸・シャドウがその定義済みスケールに準拠しているかを照合する。定義が無ければ実行しない
Design System Component Reuse Guard
skills/midstream/design-system-component-reuse/SKILL.md
既存デザインシステムコンポーネント(Button / Input / Modal / Card 等)を再実装していないかを検出する。Figma→コード実装時に既存コンポーネントを無視した実装を防ぐ。
Design Token Enforcement
skills/midstream/design-token-enforcement/SKILL.md
デザイントークンを使わずに直書きされた色・余白・フォントサイズ・角丸・シャドウを検出する。Figma Variables / Tailwind config / CSS custom properties のルールに違反する実装を指摘する。
Detector Detection Power 検査器の検出力の検証
skills/midstream/detector-detection-power/SKILL.md
検査器(linter / ガード / CI ゲート / バリデータ / フィルタ)そのものの検出力が差分で静かに落ちていないか、また新設した検査が実際に検出できることが実証されているかを diff-time で検出する。Check 1 unverified detection reduction(検査器の検出ロジック(正規表現・除外パターン・解決集合・allowlist・baseline)を変更して検出件数が減ったのに、減った 1 件ずつが誤検出であった根拠が示されないまま「誤検出を潰した」「N → M 件に減少」と改善として主張している)、Check 2 unproven guard detection power(新しい検査ロジック・CI ゲート・バリデーションを追加・変更したのに、検出すべき入力を注入して検出されること/検出すべきでない入力で黙ることを示す変異注入の証跡が無く、「追加した」「CI が緑」を検出力の証拠として扱っている)、の 2 Check を対象とする report-only。テスト自身のアサーションが実質何も検証していない構造は test-assertion-effectiveness、レビュー基準・品質ゲートの明示的な弱体化(ルールの削除・閾値の引き下げ・suppression entry 追加・lint ルールの無効化)は review-criteria-integrity、リファクタ完了主張一般の検証は refactor-claim-audit、workflow の permissions と action pin は gha-workflow-security、設定ファイルの構文・型の妥当性は config-json へ委譲する
Documentation Hygiene ドキュメント衛生
skills/midstream/doc-hygiene/SKILL.md
AGENTS.md などの恒久ドキュメントに一過性のタスクログが混入していないか、SOP / decision / log / learned の役割が混同されていないか、公開物(README / docs / 記事)に内部メモ・ローカルパス・AI 会話断片が残っていないかを差分で検出する
End-to-End Wiring 末端到達・貫通の検証
skills/midstream/e2e-wiring/SKILL.md
宣言した処理(計測 / 通知 / 保存 / 検証 / 例外通知)が起点から末端まで途切れず配線されているかを確認し、「実装したつもり」で経路が途中で止まっている欠落を検出する
Existing-Pattern Conformance 既存パターン準拠の確認
skills/midstream/existing-pattern-conformance/SKILL.md
新実装が、同種の先行実装(同レイヤ・同責務・同概念)に在る防御 / バリデーション / エラー処理 / 規約 / 共通化ロジック / 概念定義を、欠落・重複・食い違いなく継承しているかを grep で先行特定して確認する
Firebase Security Rules Review
skills/midstream/firebase-security-rules/SKILL.md
Detects over-permissive Firestore/Storage rules (allow read, write: if true / auth-only without ownership), missing auth checks on writes, and admin SDK private key exposure to client bundles.
Fix Scope Integrity 指摘対応ループのスコープ逸脱・前提破壊検出
skills/midstream/fix-scope-integrity/SKILL.md
指摘対応の反復(レビューコメント→修正→再レビュー)で、個別には正しい修正の蓄積が当初スコープを逸脱した(scope creep)、または成立済みの前提("動いていた"状態)を破壊した(premise break)連鎖を diff-time で検出する。技術的正しさとスコープ整合性を別軸で評価し、report-only で finding/question のみ出力する。1コメント単位のトリアージ・構造変更後の caller 残骸・plan 前提解消は隣接 skill へ委譲する
GitHubレビューコメント対応(修正案つき)
skills/midstream/gh-address-comments/SKILL.md
PRレビューコメントを重要度ごとに整理し、対応方針・修正案・質問をまとめて返信案を作る
Hallucinated Reference 幻覚的参照の実在確認
skills/midstream/hallucinated-reference/SKILL.md
差分で新規に導入された import・メソッド呼び出し・ライブラリ API 参照が実在するかを code_search で検証し、AI 生成コード特有の幻覚的参照(存在しない関数・メソッド・モジュール・引数シグネチャ)を検出する
Hello Skill (Always-On Sample)
skills/midstream/hello-skill/SKILL.md
Minimal always-on sample skill to guarantee an end-to-end review experience.
i18n Unused Key Review
skills/midstream/i18n-unused-key/SKILL.md
Detect i18n/locale keys that are removed from source but remain in locale files, or keys added to locale files without source usage.
Impact Evidence Coverage 影響・失敗系・外部依存の証拠充足
skills/midstream/impact-evidence-coverage/SKILL.md
diff-time で「影響範囲を repo 全体で調査した証拠」「失敗系を検証した証拠」「外部依存・レート制限・キャッシュ整合を確認した証拠」の欠落を検出する evidence-sufficiency 観点。defect そのものは既存 skill へ委譲し、本 skill は「そのリスク種別を調査した証拠が差分・PR 本文・テストに残っているか」の meta 評価のみを行う。証拠が同一 diff に同梱(テスト・canary・grep 記録)されていれば充足とみなす
Independent Review Synthesis
skills/midstream/independent-review-synthesis/SKILL.md
複数の AI / 人間レビュー結果 (review-self / review-external / findings-pool) を統合し、実在性・重大度・対応優先度・merge 可否を検証する。
Invisible Unicode Injection Scan 不可視 Unicode コード注入検出
skills/midstream/invisible-unicode-injection/SKILL.md
差分に追加されたソースコードへ混入した不可視・危険な Unicode 文字(タグ文字・異体字セレクター・ゼロ幅文字・双方向制御/マーク・変則空白)を検出する。GlassWorm 型サプライチェーン攻撃・ASCII smuggling・Trojan Source(CVE-2021-42574)でコードを不可視化する手口を、決定論的な静的解析(列挙した code point 集合に限定)として捕捉し、canary テストで誤検出の再発を防ぐ
Knowledge-to-Code Alignment 新知識のコード反映・設計知識の保全
skills/midstream/knowledge-to-code-alignment/SKILL.md
リファクタリングを「更新されたチームの理解と、コードが表現する過去の理解の差分同期」と捉え、今回得た新知識(要求・ドメイン知識・制約)が naming と responsibility へ反映されているか、boundary が現在の understanding を表現しているか、diff の削除行やコメントに現れる過去の design history と constraint を失っていないかを diff-time で確認する。Knowledge Delta の signal は diff(追加/削除された hunk・コメント・ADR 参照)を一次情報とし、PR 本文が供給されるときは補助に用い、不確実なら question に留める。ドメイン用語の一貫性は ubiquitous-language-naming、集約/コンテキスト境界の設計判断は bounded-context-language、投機的抽象化・caller special-case は altitude-generalization、スコープ逸脱/前提破壊は fix-scope-integrity、振る舞い変更と構造変更の分離は behavior-structure-separation、完了主張の反証は refactor-claim-audit へ委譲する
Laravel Eloquent N+1 and Query Efficiency Review
skills/midstream/laravel-eloquent-nplus1/SKILL.md
Detects N+1 query patterns (relation access inside loops without eager loading), full-table get()/all() loads, and unsafe chunk()/cursor() usage in Laravel Eloquent code.
Laravel Mass Assignment and Authorization Review
skills/midstream/laravel-mass-assignment/SKILL.md
Detects mass assignment via create/update($request->all()), unguarded models, and missing authorization on mutating controller actions in Laravel.
Loading State Transition Review
skills/midstream/loading-state/SKILL.md
Detect missing loading/error/empty state handling that could trap users in spinners or disabled states.
Logging and Observability Guard
skills/midstream/logging-observability/SKILL.md
Ensure code changes keep logs/metrics/traces useful for debugging failures and regressions.
Logic Torturing 論理検証
skills/midstream/logic-torturing/SKILL.md
変更に含まれる設計判断・実装選択の論理的整合性を徹底的に検証し、確証バイアスを排除して判断精度を高める
Modern Web Accessibility for Interactive UI
skills/midstream/modern-web-a11y-interactive/SKILL.md
キーボード操作 / focus 管理 / 動的コンテンツ更新 / ARIA role / フォームの自動遷移など、インタラクティブ UI のアクセシビリティ観点を suggestion で提示する。
Modern Web Browser Compatibility + Baseline Awareness
skills/midstream/modern-web-browser-compat/SKILL.md
新しい Web API / CSS の利用追加に対し、Baseline 状態とブラウザ互換性 / progressive enhancement の有無を suggestion で示す。
Modern Web Performance + Core Web Vitals
skills/midstream/modern-web-performance/SKILL.md
画像・スクリプト・スタイル・interaction 変更が LCP / INP / CLS / リソースコストに与える影響を suggestion で提示する。
Modern Web Semantic + Platform-Native
skills/midstream/modern-web-semantic/SKILL.md
legacy workaround を避け、semantic HTML / Web Platform Native API / modern CSS の利用機会を提示する。
Next.js App Router Client/Server Boundary
skills/midstream/nextjs-app-router-boundary/SKILL.md
App Router の Server Component でクライアント専用APIを使っていないか確認する。
Next.js Server Action Security Review
skills/midstream/nextjs-server-action-security/SKILL.md
Checks Next.js Server Actions ('use server') for missing authentication/authorization before mutations, missing input validation, and untrusted client-supplied IDs — treating each action as a public HTTP endpoint.
Normalization Consistency Review
skills/midstream/normalization-consistency/SKILL.md
Detect inconsistencies in ID formatting, date/time display, monetary amounts, and enum/status labels compared to existing patterns in the codebase.
Nullability Contract Review
skills/midstream/nullability-contract/SKILL.md
Detect null/undefined/empty handling gaps where callers or consumers may receive unexpected nullish values.
PR Description Review
skills/midstream/pr-description/SKILL.md
Review whether the PR description is review-ready and consistent with the diff (Why/What, impact, tests, linked issues).
React Router Action Contract Review
skills/midstream/react-router-action-contract/SKILL.md
Checks React Router v7 action conventions: validation errors returned as data with 4xx status (not thrown), redirect on success, and 3-branch ErrorBoundary handling.
React Router Loader Boundary Review
skills/midstream/react-router-loader-boundary/SKILL.md
Detects route data fetched in useEffect instead of loaders, server/client API leaks across loader boundaries, and missing HydrateFallback in React Router v7 framework mode.
Refactor-Claim Audit リファクタ完了主張の検証
skills/midstream/refactor-claim-audit/SKILL.md
コミット/PR の「全部置換した」「-N%削減」等の完了主張を grep で反証できる残骸や best/typical/worst 試算で検証し、抽出・集約リファクタでは並列度(Promise.all)/fast-path/遅延評価の性能特性退行と、Map/Set 集約キーの cross-kind 衝突による検出漏れも監査する
Review Automation Boundary Guard
skills/midstream/review-automation-boundary/SKILL.md
Detect review findings that belong in CI/lint/formatter rather than human review.
Review Comment Triage (No-Code-Fix Mode)
skills/midstream/review-comment-triage/SKILL.md
レビューコメントの重要度ラベリングと対応方針・返信案を整理する。AI はコード修正やパッチ提案を行わない。
Review Criteria Integrity レビュー基準・品質ゲートの自己弱体化検出
skills/midstream/review-criteria-integrity/SKILL.md
差分が「その差分自身を審査するレビュー基準・品質ゲート」を弱めていないかを diff-time で検出する。Check 1 レビュールールの削除・弱体化(.river/rules.md / .river/rules.d/*)、Check 2 実行時コンフィグの閾値・ゲート緩和(.river-review.{json,yaml,yml} の review.severity 引き下げ / exclude 拡大 / memory.suppressionEnabled 無効化 / selection.skills.exclude 追加)、Check 3 suppression entry の新規追加、Check 4 lint・静的解析設定からのルール削除や無効化、Check 5 branch protection・required check の緩和、の 5 Check を対象とし、これらが機能変更と同一 PR に混在し、かつ意図の宣言が無い場合に指摘する。report-only。workflow の permissions / action pin は gha-workflow-security、既存 suppression entry の使い分けは suppression-feedback、設定ファイルの一般的妥当性は config-json、.only / .skip / @ts-ignore / @ts-nocheck は heuristic-review.mjs の決定論検出器、リファクタと機能追加の混在は behavior-structure-separation へ委譲する
Standard Review Policy for Midstream
skills/midstream/review-policy-standard-midstream/SKILL.md
Applies standard AI review policy guidelines for midstream (implementation) phase reviews.
Secret / Credential Scan 機密情報の混入検出
skills/midstream/secret-credential-scan/SKILL.md
差分に追加された API キー・トークン・credential・秘密鍵・.env 値・個人ローカルパスなどの機密情報を、言語・ファイル種別に依存せず検出する。決定論的に判定できる範囲は CI(gitleaks 等)へ移譲しつつ、レビューで取りこぼしを補足する
Baseline Security Checks
skills/midstream/security-basic/SKILL.md
Check common security risks in application code (SQLi, XSS, secrets, open redirect).
Self-Contradiction Detector 自己矛盾検出
skills/midstream/self-contradiction/SKILL.md
同一ファイル/隣接ファイル内で「規則Xを守れ」と宣言した直後にXを破っている、宣言と実装の乖離を検出する
Supabase RLS Policy Review
skills/midstream/supabase-rls-policy/SKILL.md
Detects tables created without ROW LEVEL SECURITY enabled, over-permissive policies (USING (true) / WITH CHECK (true) without owner conditions), and service_role key exposure in client code.
Suppression Feedback Workflow
skills/midstream/suppression-feedback/SKILL.md
Riverbed Memory の suppression entry を活用するときの判断基準と CLI 操作を案内する。
Tailwind CSS Class Hygiene Review
skills/midstream/tailwind-class-hygiene/SKILL.md
Checks Tailwind utility class hygiene at the syntax level: arbitrary-value overuse that bypasses the theme scale, conflicting/duplicate utilities on one element, and hardcoded arbitrary colors that should use design tokens.
Type-Driven Design Guard
skills/midstream/type-driven-design/SKILL.md
Detect primitive obsession and missing domain/brand types; check that state is modeled via discriminated unions.
TypeScript Null Safety Guardrails
skills/midstream/typescript-nullcheck/SKILL.md
Enforce null/undefined safety for changed TypeScript code and suggest safer patterns.
TypeScript Strictness Guard
skills/midstream/typescript-strict/SKILL.md
Enforce TypeScript strictness by reducing any/unsafe assertions and ensuring null handling.
Ubiquitous Language Naming Consistency
skills/midstream/ubiquitous-language-naming/SKILL.md
Detects domain terms drifting between code identifiers and the established ubiquitous language (same concept under different names, or different concepts sharing a name).
Vitest Mock Isolation Review
skills/midstream/vitest-mock-isolation/SKILL.md
Detects Vitest test-isolation hazards: unrestored vi.spyOn/vi.mock without afterEach cleanup or restoreMocks config, un-awaited resolves/rejects assertions, and shared mutable module state across tests.
War Game 敵対的シミュレーション
skills/midstream/war-game/SKILL.md
攻撃者・競合・悪意あるユーザーの視点で変更を分析し、防御の盲点と悪用シナリオを可視化する
ADR Decision Quality
skills/upstream/adr-decision-quality/SKILL.md
Ensure ADRs capture context, decision, alternatives, tradeoffs, and follow-ups in a way that prevents future drift.
AI Agent Review Readiness
skills/upstream/ai-agent-review-readiness/SKILL.md
Checks whether AI-assisted work defines review criteria, accessible context, explicit review loop, human judgment boundary, and feedback capture before delegating to an agent.
API Design Consistency
skills/upstream/api-design/SKILL.md
Ensure API design follows RESTful naming and consistent conventions.
API Versioning & Backward Compatibility
skills/upstream/api-versioning-compat/SKILL.md
Ensure API/contract changes specify versioning strategy, backward compatibility, deprecation plan, and migration guidance.
Architecture Boundaries & Dependencies
skills/upstream/architecture-boundaries/SKILL.md
Ensure architecture/design docs define clear boundaries, ownership, dependency direction, and change impact to avoid tight coupling.
Architecture Diagrams Readiness
skills/upstream/architecture-diagrams/SKILL.md
Ensure architecture diagrams are readable, consistent with text, and clear on scope, boundaries, and data flow.
Architecture Risks, Assumptions & Open Questions
skills/upstream/architecture-risk-register/SKILL.md
Ensure design docs explicitly capture risks, assumptions, and open questions with owners, deadlines, and mitigation plans.
Architecture Traceability & Consistency
skills/upstream/architecture-traceability/SKILL.md
Ensure design changes stay consistent across ADRs, diagrams, and specs; decisions are traceable; and drift is explicitly managed.
Architecture Validation Plan Guard
skills/upstream/architecture-validation-plan/SKILL.md
Detect missing validation plans (how to verify the design is correct) in design documents and ADRs.
Availability & Resilience Architecture
skills/upstream/availability-architecture/SKILL.md
Ensure architecture docs capture availability targets, failover strategy, capacity headroom, and resilience trade-offs for critical services.
Bounded Context & Ubiquitous Language
skills/upstream/bounded-context-language/SKILL.md
Ensure architecture docs define bounded contexts, ownership, and a consistent ubiquitous language to prevent domain drift and coupling.
Cache Strategy Consistency Guard
skills/upstream/cache-strategy-consistency/SKILL.md
Detect undefined or inconsistent cache strategies (layers, consistency, invalidation, TTL, failure handling) in design documents.
Capacity, Performance & Cost Assumptions
skills/upstream/capacity-cost-design/SKILL.md
Ensure architecture/design docs state traffic assumptions, performance budgets, resource limits, and cost risks for critical paths.
File Inventory
.claude-plugin/plugin.json
file
1,371 bytes
5944cabbac610f94…
.claude/skills/ask-codex/SKILL.md
skill
3,405 bytes
e816d075eeaacc52…
.claude/skills/river-review-discipline/anti-patterns.md
file
6,270 bytes
930d56cf65d651ab…
.claude/skills/river-review-discipline/review-memory.md
file
1,576 bytes
98001559c5c0955d…
.claude/skills/river-review-discipline/river-review-loop.md
file
4,815 bytes
9ee8ac9374a5cf82…
.claude/skills/river-review-discipline/SKILL.md
skill
13,398 bytes
940083a84ef6871a…
.claude/skills/river-review-discipline/templates/design-review-template.md
file
1,702 bytes
fe7bda8f7f7c8d71…
.claude/skills/river-review-discipline/templates/diff-review-template.md
file
1,975 bytes
c962734ca91a7587…
.claude/skills/river-review-discipline/templates/report-review-template.md
file
1,169 bytes
3636dcfb7492471c…
.claude/skills/river-review-discipline/templates/requirements-review-template.md
file
1,266 bytes
940ea38064e4888a…
.claude/skills/river-review-discipline/templates/verification-review-template.md
file
1,281 bytes
6c2a19f5566a93a3…
.claude/skills/river-review-discipline/usage-prompts.md
file
4,243 bytes
dd2c1ab1eb9d4d1d…
.claude/skills/skill-creator/assets/basic-skill-template.md
file
3,454 bytes
bcfe8e4c1de5dc36…
.claude/skills/skill-creator/assets/eval-rubric-template.md
file
583 bytes
116c3c6acf018487…
.claude/skills/skill-creator/references/design-principles.md
file
1,212 bytes
510931475b4265aa…
.claude/skills/skill-creator/references/review-default.md
file
392 bytes
ca556fb8b72e41f0…
.claude/skills/skill-creator/SKILL.md
skill
6,600 bytes
d05cfcfe66aacb56…
.claude/skills/skill-ops-planner/assets/skill-roadmap-template.md
file
399 bytes
e2332065ded0dce0…
.claude/skills/skill-ops-planner/references/portfolio-policy.md
file
886 bytes
32b50edff1603031…
.claude/skills/skill-ops-planner/references/review-default.md
file
392 bytes
ca556fb8b72e41f0…
.claude/skills/skill-ops-planner/SKILL.md
skill
4,493 bytes
d55a45048358936e…
.claude/skills/skill-optimizer/assets/eval-rubric-template.md
file
810 bytes
0cd1b62704c8b04d…
.claude/skills/skill-optimizer/references/optimization-playbook.md
file
845 bytes
b7b09b8eb9562c23…
.claude/skills/skill-optimizer/references/review-default.md
file
392 bytes
ca556fb8b72e41f0…
.claude/skills/skill-optimizer/SKILL.md
skill
5,346 bytes
9d389a2762ed6584…
.codex-plugin/plugin.json
plugin-manifest
1,739 bytes
a5d2f7ab10d6b58e…
.github/instructions/docs.instructions.md
file
690 bytes
19a6fa20a9f4f724…
.github/instructions/js-ts.instructions.md
file
599 bytes
05a7b80f93da3f92…
.github/instructions/skills.instructions.md
file
983 bytes
31331756770955b9…
AGENTS.md
file
7,432 bytes
83ee8e9041b42186…
agents/contracts/adapter-map.json
file
3,229 bytes
96b40f963a6adefa…
agents/contracts/completion-judge.agent.json
file
1,311 bytes
57d652d5aa04b600…
agents/contracts/consistency-judge.agent.json
file
995 bytes
46e746925cc6b2f6…
agents/contracts/finding-verifier.agent.json
file
914 bytes
72ac42df0b09951c…
agents/contracts/review-orchestrator.agent.json
file
1,198 bytes
14f0607b97167a71…
agents/contracts/specialist-reviewer.agent.json
file
1,344 bytes
81e3047fa58515b0…
agents/examples/river-review-self.agent.yaml
file
8,127 bytes
35004c53d2562812…
agents/examples/river-review.agent.yaml
file
10,945 bytes
4664811fd626780c…
agents/river-review.md
file
577 bytes
2f7a9db8198b7300…
agents/spec/agent.schema.json
file
9,764 bytes
46de1a5a67738f03…
CLAUDE.md
file
20,129 bytes
bf6a39ccbf68cbdb…
commands/challenge.md
file
1,980 bytes
4f7d8c350948f71e…
commands/check.md
file
949 bytes
df8e9ebc0db5f83f…
commands/pr.md
file
4,230 bytes
9935bbf22725db3f…
commands/review-local.md
file
419 bytes
e848fa9081b24bea…
commands/review-team.md
file
3,575 bytes
b2de7ac7f1cc827e…
commands/setup-team.md
file
3,016 bytes
7f93fcb13aafbbb0…
commands/skill.md
file
1,918 bytes
1c5d7db4fa90b975…
GEMINI.md
file
1,194 bytes
29f69a0c67663f58…
hooks/format.sh
file
1,866 bytes
4191b97983565d43…
hooks/hooks.json
file
943 bytes
85df9536e2433799…
hooks/README.md
file
3,483 bytes
6f283f6cdd982e2e…
package-lock.json
file
862,408 bytes
9f589958534b54df…
package.json
file
7,647 bytes
a48881f28b9675bd…
README.md
file
52,364 bytes
f6288e5f367c8d52…
scripts/templates/skill/eval/promptfoo.yaml
file
1,234 bytes
e7b4ca22a500025c…
scripts/templates/skill/prompt/system.md
file
2,096 bytes
d8371ae66db6f842…
scripts/templates/skill/prompt/user.md
file
948 bytes
82f8510907b9d8aa…
scripts/templates/skill/README.md
file
2,176 bytes
2689bbc41409d267…
scripts/templates/skill/SKILL.md
skill
1,228 bytes
d3d86acb174e2c0a…
scripts/templates/skill/skill.yaml
file
3,541 bytes
b6c3051aa92b79b1…
SECURITY.md
file
2,515 bytes
afd7f64b145cb2af…
skills/agent-skills/adversarial-review/references/TECHNIQUES.md
skill
6,288 bytes
80c2b87b5db41ef6…
skills/agent-skills/adversarial-review/SKILL.md
skill
7,491 bytes
9eb9f3421fad9e41…
skills/agent-skills/review-team/SKILL.md
skill
9,968 bytes
271dcec5f38b7c49…
skills/agent-skills/river-review-architecture/references/ROUTING.md
skill
4,003 bytes
580ab67512a66283…
skills/agent-skills/river-review-architecture/SKILL.md
skill
6,036 bytes
74d628fd3275cf3d…
skills/agent-skills/river-review-code/references/ROUTING.md
skill
7,721 bytes
c77fadbc397d689e…
skills/agent-skills/river-review-code/references/SIMPLIFY.md
skill
9,510 bytes
0b807df2abbb3c76…
skills/agent-skills/river-review-code/references/UX-SAFEGUARD.md
skill
6,529 bytes
5ac2bd1865944369…
skills/agent-skills/river-review-code/SKILL.md
skill
10,293 bytes
82a1660367e8d6e4…
skills/agent-skills/river-review-docs/references/ROUTING.md
skill
1,342 bytes
b46e01e2b9fde1d1…
skills/agent-skills/river-review-docs/SKILL.md
skill
4,268 bytes
e3319ef44edb01f8…
skills/agent-skills/river-review-frontend/references/ROUTING.md
skill
7,158 bytes
0b99ad1c487dd14e…
skills/agent-skills/river-review-frontend/SKILL.md
skill
12,688 bytes
52831e255df39e1f…
skills/agent-skills/river-review-performance/references/ROUTING.md
skill
1,731 bytes
fe032d4c3ad47b33…
skills/agent-skills/river-review-performance/SKILL.md
skill
7,126 bytes
e78e651a67931ec6…
skills/agent-skills/river-review-security-audit/references/attack-classes.json
skill
10,961 bytes
8cc3c986ca64fe27…
skills/agent-skills/river-review-security-audit/SKILL.md
skill
16,848 bytes
8c616fda97950ef9…
skills/agent-skills/river-review-security/references/ROUTING.md
skill
2,052 bytes
6ed874698e34bc8b…
skills/agent-skills/river-review-security/SKILL.md
skill
4,287 bytes
1689b1400a0ea80e…
skills/agent-skills/river-review-testing/references/ROUTING.md
skill
1,785 bytes
c94f4edb74a6a2a6…
skills/agent-skills/river-review-testing/SKILL.md
skill
3,609 bytes
ab714db853fcc374…
skills/agent-skills/river-review/fixtures/01-intent-comment-resolves-finding.md
skill
2,866 bytes
e4a1bbec0712288c…
skills/agent-skills/river-review/fixtures/02-intent-comment-downgrade-with-rebuttal.md
skill
2,516 bytes
fcb5d78222adad04…
skills/agent-skills/river-review/fixtures/03-comment-contradicts-implementation.md
skill
2,165 bytes
e93506d00653c559…
skills/agent-skills/river-review/fixtures/04-intentional-comment-does-not-suppress-security.md
skill
3,070 bytes
18070922f91ef234…
skills/agent-skills/river-review/fixtures/05-test-detection-power-only-is-minor.md
skill
3,270 bytes
1f0acdff34a3603a…
skills/agent-skills/river-review/references/FEEDBACK_TO_FIXTURE.md
skill
8,750 bytes
17a714cda2b2ef7a…
skills/agent-skills/river-review/references/FEEDBACK.md
skill
8,470 bytes
dd5e1b0ab0eaca24…
skills/agent-skills/river-review/references/IMPROVEMENT_LOOP.md
skill
6,761 bytes
daa9cd9b2793bb27…
skills/agent-skills/river-review/references/ROUTING.md
skill
4,937 bytes
e4a6b3d969444d4f…
skills/agent-skills/river-review/references/VERIFICATION.md
skill
10,817 bytes
066a6e763f3419cb…
skills/agent-skills/river-review/SKILL.md
skill
16,013 bytes
a421987fd7cc3b0f…
skills/agent-skills/unknown-coverage-review/fixtures/01-pass-evidence-sufficient.md
skill
1,874 bytes
dbc53c0088140bd2…
skills/agent-skills/unknown-coverage-review/fixtures/02-needs-review-nonblocking-unknown.md
skill
1,784 bytes
e7dcf9e0f13b86cc…
skills/agent-skills/unknown-coverage-review/fixtures/03-fail-blocking-compat-unknown.md
skill
1,816 bytes
e628012415aca1b2…
skills/agent-skills/unknown-coverage-review/fixtures/04-security-audit-missing-surface.md
skill
1,767 bytes
a78a9f63ca5ccc62…
skills/agent-skills/unknown-coverage-review/fixtures/05-security-audit-unsupported-covered.md
skill
1,621 bytes
0c305a98cd17d37b…
skills/agent-skills/unknown-coverage-review/fixtures/06-security-audit-legitimate-out-of-scope.md
skill
1,563 bytes
cb4cf220730ae8a1…