Review & quality
19,195 rows, by stacks then stars
1,766 of these skill files have been read, by 1,273 distinct authors, and what they tell an agent counted. What Review & quality authors agree on, and what they forbid
Run2 simpo testing and verification
cxcscmu/SkillLearnBench/skills/b2-self-feedback-claude-haiku-4-5/nlp-paper-reproduction/run2_simpo-testing-and-verification Skill
93★ repoTesting SimPO loss function with fixed tensors and output verification
cxcscmu/SkillLearnBench/skills/b2-self-feedback-claude-haiku-4-5/temperature-simulation/run2_nml-calibration-workflow Skill
93★ repoComplete NML-based GLM calibration workflow with validation and verification
Run2 data filtering validation
cxcscmu/SkillLearnBench/skills/b2-self-feedback-claude-haiku-4-5/travel-planning/run2_data_filtering_validation Skill
93★ repoAdvanced filtering and validation of travel datasets with strict cuisine matching, budget constraints, and data quality checks.
cxcscmu/SkillLearnBench/skills/b2-self-feedback-claude-haiku-4-5/video-object-counting/run2_csv_validation_export Skill
93★ repoGenerate and validate CSV files with data integrity checks, verification, and comprehensive error handling for reliable data export.
Run2 image processing verification
cxcscmu/SkillLearnBench/skills/b2-self-feedback-claude-haiku-4-5/video-object-counting/run2_image_processing_verification Skill
93★ repoRobust image processing with format conversion, in-place modification, and comprehensive verification of image properties.
cxcscmu/SkillLearnBench/skills/b2-self-feedback-claude-opus-4-6/travel-planning/run2_budget-validation Skill
93★ repoValidate travel budget calculations including accommodation nights, meal costs, and constraint compliance.
Run2 file organization and validation
cxcscmu/SkillLearnBench/skills/b2-self-feedback-gemini-3-flash-preview/organize-messy-files/run2_file_organization_and_validation Skill
93★ repoSafely moves files and validates the integrity of the organization process.
cxcscmu/SkillLearnBench/skills/b2-self-feedback-gemini-3-flash-preview/travel-planning/run2_budget_validation Skill
93★ repoValidate travel budgets using accommodation and restaurant data.
cxcscmu/SkillLearnBench/skills/b2-self-feedback-gemini-3-flash-preview/weighted-gdp-calculation/run2_excel-verification Skill
93★ repoVerifying Excel formula results and handling errors using recalc.py and openpyxl.
Run3 Compose Seven Character Regulated Verse Character by Character Using Anchors
cxcscmu/SkillLearnBench/skills/b3-teacher-feedback-claude-haiku-4-5/chinese-poem-generator/run3_Compose-Seven-Character-Regulated-Verse-Character-by-Character-Using-Anchors Skill
93★ repoFill in your poem position-by-position, starting with the 4 rhyme characters (lines 2, 4, 6, 8). For each remaining position, select a character, verify its pinyin and tone in your reference table, confirm it matches the required 平/仄 classification, then move to the next position. Never move to a new line until all 7 positions of the current line pass verification.
Run3 Verify Rhyme Integrity in Modern Mandarin Finals
cxcscmu/SkillLearnBench/skills/b3-teacher-feedback-claude-haiku-4-5/chinese-poem-generator/run3_Verify-Rhyme-Integrity-in-Modern-Mandarin-Finals Skill
93★ repoCheck that all 4 rhyme characters (lines 2, 4, 6, 8) belong to the same modern Mandarin rhyme family by comparing their finals and tone patterns. Use Xinhua Dictionary or online Mandarin phonetic tool to confirm final identity (e.g., -ing, -ang, -ong) and ensure all 4 characters have identical tone classification (all 平, or all 仄) in the rhyme position.
Run3 evidence validation checkpoint
cxcscmu/SkillLearnBench/skills/b3-teacher-feedback-claude-haiku-4-5/enterprise-information-search/run3_evidence-validation-checkpoint Skill
93★ repoBefore writing final answers, validate that all required evidence has been extracted, multi-hop traversal was executed, and answers are complete against expected values.
Run3 Create and Apply Git Patch Files for Druid Security Fixes
cxcscmu/SkillLearnBench/skills/b3-teacher-feedback-claude-haiku-4-5/fix-security-bug/run3_Create-and-Apply-Git-Patch-Files-for-Druid-Security-Fixes Skill
93★ repoGenerate proper git-compatible patch files that address the empty key validation and JavaScript filter disabling vulnerabilities, then apply them to the Druid 0.20.0 source repository.
Run3 Disable JavaScript Execution in Druid Filters
cxcscmu/SkillLearnBench/skills/b3-teacher-feedback-claude-haiku-4-5/fix-security-bug/run3_Disable-JavaScript-Execution-in-Druid-Filters Skill
93★ repoConfigure and enforce a security policy that completely disables JavaScript filter evaluation in Apache Druid, preventing arbitrary code execution through the javascript filter type even if structural validation is bypassed.
Run3 Input Stream Validation Before Jackson Deserialization
cxcscmu/SkillLearnBench/skills/b3-teacher-feedback-claude-haiku-4-5/fix-security-bug/run3_Input-Stream-Validation-Before-Jackson-Deserialization Skill
93★ repoValidate and sanitize raw JSON input at the point where it enters Jackson's deserialization pipeline, before any ObjectMapper.readValue() call processes it, to prevent bypass attacks using empty keys.
Run3 Check Repository Dependencies
cxcscmu/SkillLearnBench/skills/b3-teacher-feedback-claude-haiku-4-5/nlp-paper-reproduction/run3_Check-Repository-Dependencies Skill
93★ repoUse when starting a new project to verify Python version requirements declared in configuration files. This prevents version mismatches before environment setup.
Run3 Track and Verify File Organization
cxcscmu/SkillLearnBench/skills/b3-teacher-feedback-claude-haiku-4-5/organize-messy-files/run3_Track-and-Verify-File-Organization Skill
93★ repoUse this skill to systematically track all files before and after sorting to ensure no files are lost, duplicated, or left out during the organization process.
Run3 check and setup python310
cxcscmu/SkillLearnBench/skills/b3-teacher-feedback-claude-sonnet-4-6/nlp-paper-reproduction/run3_check-and-setup-python310 Skill
93★ repoUse this skill when you need to find, install, or configure a Python 3.10 environment on the system. Checks for existing python3.10 binary, installs if missing, and sets up pip for that version.
cxcscmu/SkillLearnBench/skills/b3-teacher-feedback-claude-sonnet-4-6/travel-planning/run3_itinerary-validation Skill
93★ repoUse this skill to validate a completed itinerary JSON against all task requirements before finalizing output. Run this checklist after formatting and before writing the file.
cxcscmu/SkillLearnBench/skills/b3-teacher-feedback-gemini-3-flash-preview/temperature-simulation/run3_glm-metric-validator Skill
93★ repoCalculate specific RMSE metrics by merging simulation and observation data using exact datetime and rounded-depth matching.
Run2 itinerary validation check
cxcscmu/SkillLearnBench/skills/b3-teacher-feedback-gemini-3-flash-preview/travel-planning/run2_itinerary-validation-check Skill
93★ repoA final verification step to ensure the JSON output meets all structural and constraint requirements before delivery.
Run3 answer formatter and tracker
cxcscmu/SkillLearnBench/skills/b3-teacher-feedback-gemini-3.1-flash-lite-preview/enterprise-information-search/run3_answer_formatter_and_tracker Skill
93★ repoUse this to structure the final output into the required JSON schema, calculating precise token usage based on the retrieved context.
cxcscmu/SkillLearnBench/skills/b3-teacher-feedback-gemini-3.1-flash-lite-preview/financial-analysis/run3_data_format_validation Skill
93★ repoEnsures the generated output strictly adheres to the required JSON schema.
Run2 unit test execution and verification
cxcscmu/SkillLearnBench/skills/b3-teacher-feedback-gemini-3.1-flash-lite-preview/nlp-paper-reproduction/run2_unit_test_execution_and_verification Skill
93★ repoCreates an orchestration script to run the immutable unit test and capture the output loss values.
cxcscmu/SkillLearnBench/skills/b4-skill-creator-claude-haiku-4-5/enterprise-information-search/json-output-formatter Skill
93★ repoFormat enterprise data retrieval results as JSON with token tracking. Use this skill when you need to output query results to JSON files in the format {"q1": {"answer": [...], "tokens": N}, ...}. Handles answer list formatting, token counting, and file output validation.
cxcscmu/SkillLearnBench/skills/b4-skill-creator-gemini-3.1-flash-lite-preview/chinese-poem-generator/rhyme-scheme-validator Skill
93★ repoGuidance on ensuring a consistent rhyme scheme in modern Mandarin for classical Chinese poetry, focusing on rhyming vowels.
cxcscmu/SkillLearnBench/skills/b4-skill-creator-gemini-3.1-flash-lite-preview/enterprise-information-search/json-answer-formatter Skill
93★ repoFormat retrieval answers as a dictionary in /root/answer.json.
cxcscmu/SkillLearnBench/skills/human_authored/enterprise-information-search/artifact-review-search Skill
93★ repoMulti-hop search over enterprise artifacts to find key reviewers, approvers, feedback contributors, authors, product reports, competitor insights, and demo URLs. Prevents cross-product leakage and prevents treating meeting participants as reviewers.
cognyai/claude-code-marketing-skills/skills/deliverability-check Skill
no license92★ repoAudit a sending domain's deliverability — SPF, DKIM, DMARC, MX, BIMI, blocklists — with a prioritized fix order
cognyai/claude-code-marketing-skills/skills/landing-page-review Skill
no license92★ repoCRO review of a landing page with specific conversion recommendations
monte-carlo-data/mc-agent-toolkit/skills/generate-validation-notebook Skill
91★ repoGenerate SQL validation notebooks for dbt changes. Pass a GitHub PR URL or local dbt repo path.
omergocmen/vibe-coder-kit/.agent/skills/code-review Skill
89★ repoSystematic code review skill covering both requesting a review (pre-commit checklist) and receiving and responding to review feedback. Checks code quality, security, test coverage, architectural alignment, and documentation before any code is committed.
omergocmen/vibe-coder-kit/.agent/skills/github Skill
89★ repoManages all git operations (commit, push, branch management, PR creation) in a standardized, safe, and consistent way. Automatically runs the code-review skill before any commit. Enforces Conventional Commits standard. Handles the full lifecycle: branch → review → commit → push → PR.
deepklarity/harness-kit/.claude/skills/hk-changelog Skill
89★ repoGenerate changelog entries from git diffs, prepend to CHANGELOG.md, and optionally commit + PR. Use when the user wants to update the changelog.
michtio/craftcms-claude-skills/skills/craft-php-guidelines Skill
88★ repoCraft CMS 5 PHP coding standards and conventions. ALWAYS load when writing, editing, reviewing, or discussing any PHP in a Craft plugin or module — even small edits. Also when running ECS, PHPStan, or scaffolding with ddev craft make. Covers: PHPDoc blocks (@author, @since, @throws chains), section headers (=========), class organization, naming conventions (services, queue jobs, records, events, enums), defineRules() and validation, beforePrepare() and addSelect(), MemoizableArray, DateTimeHelper vs Carbon, strict_types/declare(strict_types=1), short nullable notation (?string), typed properties, void returns, control flow (early returns, match over switch), CP Twig template conventions, form macros, translations (Craft::t), ECS/PHPStan config, scaffolding commands, and the verification checklist. Triggers on: writing service classes, models, controllers, elements, element queries, records, queue jobs, migrations, or any PHP class in a Craft context; PHP code review, refactoring, or style questions; requireAdmin vs requirePermission, manage-settings, settings permission, kebab-case permission handles never camelCase, allowAdminChanges, read-only settings, getCpNavItem dead nav item, permission handle constant on owning controller, App::env() never getenv(), App::parseEnv() for $VAR settings, no-em-dash user-facing copy. NOT for front-end Twig (craft-twig-guidelines), template architecture (craft-site), or CP JavaScript/Garnish (craft-garnish). If you are touching PHP in a Craft context, you need this skill.
mturac/everything-openai-codex/skills/security-review Skill
88★ repoUse this skill when adding authentication, handling user input, working with secrets, creating API endpoints, or implementing payment/sensitive features. Provides comprehensive security checklist and patterns.
mturac/everything-openai-codex/skills/verification-loop Skill
88★ repoA comprehensive verification system for OpenAI Codex sessions.
mturac/everything-openai-codex/.kiro/skills/security-review Skill
88★ repoUse this skill when adding authentication, handling user input, working with secrets, creating API endpoints, or implementing payment/sensitive features. Provides comprehensive security checklist and patterns.
mturac/everything-openai-codex/.kiro/skills/verification-loop Skill
88★ repoA comprehensive verification system for Kiro sessions.
mturac/everything-openai-codex/docs/ja-JP/skills/django-verification Skill
88★ repoVerification loop for Django projects: migrations, linting, tests with coverage, security scans, and deployment readiness checks before release or PR.
mturac/everything-openai-codex/docs/ja-JP/skills/flutter-dart-code-review Skill
88★ repoウィジェットのベストプラクティス、状態管理パターン(BLoC、Riverpod、Provider、GetX、MobX、Signals)、Dartのイディオム、パフォーマンス、アクセシビリティ、セキュリティ、クリーンアーキテクチャをカバーするライブラリに依存しないFlutter/Dartのコードレビューチェックリスト。
mturac/everything-openai-codex/docs/ja-JP/skills/git-workflow Skill
88★ repoGitワークフロー、ブランチ戦略、コミットメッセージ規約、およびプルリクエストプロセス。
mturac/everything-openai-codex/docs/ja-JP/skills/laravel-verification Skill
88★ repo日本語翻訳:このファイルは laravel-verification 用の日本語翻訳が必要です
mturac/everything-openai-codex/docs/ja-JP/skills/network-config-validation Skill
88★ repo日本語翻訳:このファイルは network-config-validation 用の日本語翻訳が必要です
mturac/everything-openai-codex/docs/ja-JP/skills/quarkus-verification Skill
88★ repoQuarkusプロジェクト検証ループ:ビルド、静的分析、カバレッジ付きテスト、セキュリティスキャン、ネイティブコンパイル、本番環境またはPR前の差分レビュー。
mturac/everything-openai-codex/docs/ja-JP/skills/safety-guard Skill
88★ repo本番システムでの作業時や、エージェントを自律的に実行する際に破壊的な操作を防ぐためにこのスキルを使用してください。
Scientific thinking literature review
mturac/everything-openai-codex/docs/ja-JP/skills/scientific-thinking-literature-review Skill
88★ repo学術、生物医学、技術、科学的なトピックに対するシステマティックな文献レビューワークフロー。検索計画、ソースのスクリーニング、統合、引用確認、証拠ログを含む。
mturac/everything-openai-codex/docs/ja-JP/skills/security-review Skill
88★ repo認証の追加、ユーザー入力の処理、シークレットの操作、APIエンドポイントの作成、支払い/機密機能の実装時にこのスキルを使用します。包括的なセキュリティチェックリストとパターンを提供します。
mturac/everything-openai-codex/docs/ja-JP/skills/springboot-verification Skill
88★ repoVerification loop for Spring Boot projects: build, static analysis, tests with coverage, security scans, and diff review before release or PR.
mturac/everything-openai-codex/docs/ja-JP/skills/verification-loop Skill
88★ repoEOC: open-source operating system for OpenAI Codex workflows with agents, skills, hooks, rules, memory, safety gates, and cross-harness adapters.
mturac/everything-openai-codex/docs/ko-KR/skills/security-review Skill
88★ repo인증 추가, 사용자 입력 처리, 시크릿 관리, API 엔드포인트 생성, 결제/민감한 기능 구현 시 이 스킬을 사용하세요. 포괄적인 보안 체크리스트와 패턴을 제공합니다.
mturac/everything-openai-codex/docs/ko-KR/skills/verification-loop Skill
88★ repoOpenAI Codex 세션을 위한 포괄적인 검증 시스템.
mturac/everything-openai-codex/docs/tr/skills/laravel-verification Skill
88★ repoVerification loop for Laravel projects: env checks, linting, static analysis, tests with coverage, security scans, and deployment readiness.
mturac/everything-openai-codex/docs/tr/skills/quarkus-verification Skill
88★ repoVerification loop for Quarkus projects: build, static analysis, tests with coverage, security scans, native compilation, and diff review before release or PR.
mturac/everything-openai-codex/docs/tr/skills/security-review Skill
88★ repoKimlik doğrulama eklerken, kullanıcı girdisi işlerken, secret'larla çalışırken, API endpoint'leri oluştururken veya ödeme/hassas özellikler uygularken bu skill'i kullanın. Kapsamlı güvenlik kontrol listesi ve kalıplar sağlar.
mturac/everything-openai-codex/docs/tr/skills/springboot-verification Skill
88★ repoVerification loop for Spring Boot projects: build, static analysis, tests with coverage, security scans, and diff review before release or PR.
mturac/everything-openai-codex/docs/tr/skills/verification-loop Skill
88★ repoOpenAI Codex oturumları için kapsamlı doğrulama sistemi.
mturac/everything-openai-codex/docs/zh-CN/skills/django-verification Skill
88★ repoDjango项目的验证循环:迁移、代码检查、带覆盖率的测试、安全扫描,以及在发布或PR前的部署就绪检查。
mturac/everything-openai-codex/docs/zh-CN/skills/flutter-dart-code-review Skill
88★ repo库无关的Flutter/Dart代码审查清单,涵盖Widget最佳实践、状态管理模式(BLoC、Riverpod、Provider、GetX、MobX、Signals)、Dart惯用法、性能、可访问性、安全性和整洁架构。
mturac/everything-openai-codex/docs/zh-CN/skills/git-workflow Skill
88★ repoGit工作流模式,包括分支策略、提交约定、合并与变基、冲突解决以及适用于各种规模团队的协作开发最佳实践。