Claude Skills
The open format is called Agent Skills and works in Claude Code, Codex, Cursor and other agents — most people know it as Claude Skills.
Every Agent Skill we could find on GitHub, deduplicated by content. 86 961 files from 2 125 authors, of which 68 678 are unique — the rest is the same skill repackaged into someone else's repository. For each one: what it weighs in tokens, whether it ships runnable scripts, and which MCP servers it needs.
> Mechanically replace static dependency call sites with wrapper or built-in abstraction calls across a bounded scope (file, project, or namespace). Performs codemod-style bulk replacement of DateTime.UtcNow to TimeProvider.GetUtcNow(), File.ReadAllText to IFileSystem, and similar transformations. Adds constructor injection parameters and updates DI registration. TimeProvider, migrate static calls to wrapper, bulk replace File.* with IFileSystem, codemod static to injectable, add constructor injection for time provider, mechanical migration of statics, refactor DateTime to TimeProvider, swap static for injected dependency, convert static calls to use abstraction, replace statics in a class, migrate one file to TimeProvider, scoped migration, update call sites. wrappers (use generate-testability-wrappers), migrating between test frameworks.
> Migrate .NET test projects from xUnit.net (v2 or v3) to MSTest v4. port [Fact]/[Theory]/[InlineData]/[MemberData]/[ClassData] to [TestMethod]/[DataRow]/[DynamicData], port Assert.Equal/True/Throws/ThrowsAsync to Assert.AreEqual/IsTrue/ThrowsExactly/ThrowsExactlyAsync, port IClassFixture/ ICollectionFixture/IDisposable/IAsyncLifetime/ITestOutputHelper/[Trait]/[Fact(Skip)] to MSTest equivalents, preserve xUnit parallel-class default via xUnit, NUnit/TUnit -> MSTest (no skills exist); MSTest version upgrades (use migrate-mstest-v1v2-to-v3 or migrate-mstest-v3-to-v4); VSTest <-> MTP only (use migrate-vstest-to-mtp); general .NET upgrades.
> Microsoft.Testing.Platform) a project uses from `Directory.Build.props`, `global.json`, and `.csproj`, then picks the matching command syntax. USE test runner/platform from project files; `--` separator rules on .NET SDK 8/9 vs 10+; choosing the right filter syntax for MSTest / xUnit / NUnit / TUnit (--filter, --filter-class, --filter-trait, --filter-query, --treenode-filter); TRX/reporting (--report-trx vs --logger trx); blame/hang/crash diagnostics (--blame-hang-timeout, --blame-crash); running tests against a single target framework when a project targets multiple TFMs (e.g., `<TargetFrameworks>net8.0;net9.0</TargetFrameworks>`, `--framework <TFM>`); and avoiding MTP/VSTest argument mixups (--logger trx on MTP, --report-trx on VSTest, --blame on MTP). failing test logic.
Canonical patterns for writing custom MSBuild targets. USE FOR: diagnosing and fixing custom target authoring anti-patterns, reviewing MSBuild target definitions for correctness, diagnosing broken SDK target chains across files (e.g., Directory.Build.targets silently redefining SDK targets), fixing targets that replace CompileDependsOn instead of extending it with $(CompileDependsOn), fixing query targets that return stale results due to Outputs vs Returns misuse, fixing missing Inputs/Outputs causing unnecessary rebuilds, fixing missing FileWrites registration. Covers DependsOnTargets vs BeforeTargets vs AfterTargets, the Build→CoreBuild three-level pattern, hooking into the build pipeline, the $(XxxDependsOn) chain-extension pattern. DO NOT USE FOR: incremental build tuning (use incremental-build), parallelization (use build-parallelism), general anti-patterns (use msbuild-antipatterns), non-MSBuild build systems.
MSBuild property definition patterns: conditional defaults, composition/concatenation, path normalization, trailing slash handling, TFM detection helpers, and property evaluation order. USE FOR: diagnosing and fixing MSBuild property definition issues in .props or .csproj files, reviewing and fixing shared property configuration anti-patterns, fixing DefineConstants or NoWarn being overwritten instead of appended, fixing unconditional property assignments that prevent project-level overrides, fixing unquoted conditions that fail when properties are empty, fixing hardcoded paths that break cross-platform builds, setting property defaults that can be overridden, understanding property evaluation order and last-write-wins semantics. DO NOT USE FOR: props vs targets placement (use directory-build-organization), item operations (use item-management), target structure (use target-authoring), general anti-patterns (use msbuild-antipatterns), non-MSBuild build systems.
Catalog of MSBuild anti-patterns with detection rules and fix recipes. USE FOR: reviewing, auditing, or cleaning up .csproj, .vbproj, .fsproj, .props, .targets, or .proj files. Each anti-pattern has a symptom, explanation, and concrete BAD→GOOD transformation. Covers Exec-instead-of-built-in-task, unquoted conditions, hardcoded paths, restating SDK defaults, scattered package versions, and more. DO NOT USE FOR: non-MSBuild build systems (npm, Maven, CMake, etc.), project migration to SDK-style (use msbuild-modernization).
>- Provides file paths to language-specific reference files for the test ANALYSIS skills (assertion-quality, test-anti-patterns, test-gap-analysis, test-smell-detection, test-tagging). Call this skill to discover available extension files (e.g., dotnet.md for .NET/MSTest/xUnit/NUnit/TUnit, python.md for pytest/unittest, typescript.md for Jest/Vitest/Mocha, java.md for JUnit/TestNG, etc.). Do not use directly — invoked by the test-quality-auditor agent and polyglot analysis skills that need framework-specific lookup tables (test markers, assertion APIs, skip annotations, sleep patterns, mystery guest indicators, integration markers, setup/teardown, tag-support capability).
Reference data for detecting the test platform (VSTest vs Microsoft.Testing.Platform) and test framework (MSTest, xUnit, NUnit, TUnit) from project files. DO NOT USE directly — loaded by run-tests, mtp-hot-reload, and migrate-vstest-to-mtp when they need detection logic.
> Audits existing test code in any language for anti-patterns and quality issues — produces a severity-ranked report (Critical / Warning / Info) Java (JUnit/TestNG), Go, Ruby (RSpec/Minitest), Rust, Swift, Kotlin (JUnit/Kotest), PowerShell (Pester), C++ (GoogleTest/Catch2). INVOKE when asked to audit, review, rank, or find problems in existing tests — "audit my tests", "test smell audit", "rank by severity", tests that pass but verify nothing, no/missing assertions, swallowed exceptions, always-true / self-comparing / tautological assertions, broad exception types, flakiness (sleep/Date.now/time.sleep), ordering dependency, shared global state, duplicated tests, magic values, missing await on async assertions. writing-mstest-tests for MSTest); running tests (use run-tests); framework migration.
Performs pseudo-mutation analysis on production code in any language to find gaps in existing test suites. Use when the user asks to find weak tests, discover untested edge cases, check if tests would catch a bug, or evaluate test effectiveness through mutation-style reasoning. Analyzes production code for mutation points (boundaries, boolean flips, null/None/nil returns, exception/error removal, arithmetic changes) and checks whether tests would detect each mutation. Polyglot: .NET (MSTest/xUnit/NUnit/TUnit), Python (pytest/unittest), TS/JS (Jest/Vitest/Mocha/node:test), Java (JUnit/TestNG), Go, Ruby (RSpec/Minitest), Rust, Swift, Kotlin (JUnit/Kotest), PowerShell (Pester), C++ (GoogleTest/Catch2). DO NOT USE FOR: writing new tests (use code-testing-agent, or writing-mstest-tests for MSTest), detecting anti-patterns (use test-anti-patterns), measuring assertion diversity (use assertion-quality), or running actual mutation testing tools (Stryker, mutmut, PIT, cargo-mutants).
> Deep-dive audit using the full testsmells.org 19-smell academic catalog for tests in any language. Every finding maps to a named, citable smell from the research literature (Assertion Roulette, Duplicate Assert, Mystery Guest, Eager Test, Sensitive Equality, Conditional Test Logic, Sleepy Test, Magic Number Test, etc.) with research-backed severity. (RSpec/Minitest), Rust, Swift, Kotlin (JUnit/Kotest), PowerShell (Pester), C++ (GoogleTest/Catch2). INVOKE ONLY when explicitly asked for the testsmells.org 19-smell academic catalog or citable smell names from the literature. writing new tests (use code-testing-agent, or writing-mstest-tests for MSTest); running tests (use run-tests); framework migration.
> Write new MSTest unit tests and fix existing MSTest code using MSTest 3.x/4.x modern APIs and best practices. better MSTest assertion than Assert.IsTrue, replace hard cast with MSTest type assertion, MSTest assertion APIs (IsInstanceOfType, Contains, ContainsSingle, HasCount, IsEmpty, IsNotEmpty, DoesNotContain, StartsWith, EndsWith, MatchesRegex, IsGreaterThan, IsInRange, IsNull), fix swapped Assert.AreEqual arguments, replace ExpectedException with Assert.Throws, data-driven tests (DataRow, DynamicData, ValueTuples), test lifecycle (sealed classes, TestInitialize, TestCleanup), async tests and cancellation tokens, test parallelization (Parallelize / DoNotParallelize), MSTest.Sdk project setup. running tests (use run-tests), MSTest version migration (use migrate-mstest-v1v2-to-v3 or migrate-mstest-v3-to-v4), xUnit/NUnit/TUnit, or non-.NET languages.
Systematic activities that need to be performed after a release is done.
Analyzes test suites in any language and tags each test with a standardized set of traits (positive, negative, critical-path, boundary, smoke, regression, integration, performance, security). Use when the user wants to categorize, audit, or label tests with traits. Works with .NET (MSTest TestCategory / xUnit Trait / NUnit Category / TUnit Property), Python (pytest markers; unittest has no canonical tag syntax so report-only), TypeScript/JavaScript (Jest/Vitest test names, describe-block conventions), Java (JUnit 5 @Tag / TestNG groups), Go (subtest naming / build tags / file _test.go), Ruby (RSpec metadata), Rust (cargo test naming / cfg attributes), Swift (XCTest test plans / Swift Testing @Tag), Kotlin (JUnit @Tag / Kotest tags), PowerShell (Pester -Tag), C++ (GoogleTest filter prefixes / Catch2 [tags] / doctest decorators). Auto-edits when the framework has canonical syntax; falls back to report-only otherwise. Do not use for writing new tests, running tests, or migrating frameworks.
GitHub PR/issue agent transcripts: redact, preview, and insert safely.
Pre-commit/ship code review: Codex default; optional Claude, Pi, or Kimi.
Publish a redacted local coding session to an authenticated read-only Beam catalog.
Source-blind user behavior validation against a prewritten contract for apps, CLIs, APIs, and generated artifacts.
Crabbox/Testbox remote proof for OpenClaw: trusted-source routing, untrusted isolation, Linux/macOS/Windows/WSL2, live E2E, desktop, diagnostics, cleanup.
Clipboard-ready handoff prompt for another agent to investigate or continue a task.
House README standard: structure, badge row, tone, per-archetype templates, and verification gates for steipete/openclaw repos.
Render Codex, Claude Code, OpenClaw, or Pi session JSONL transcripts as a searchable, shareable single-file HTML viewer.
Dub a video into another language and generate subtitles using the default Together + Cartesia stack. Trigger when the user wants to translate / dub / voice-over a video file, or generate subtitles for it. Handles `.mp4` / `.mkv` / `.webm`. Installs as the `violin` CLI (and `violin-api` for the FastAPI server) via `uv tool install`. For alternative models (OpenAI / ElevenLabs) or custom configs, point the user to the repo: https://github.com/shang-zhu/violin.
| Transforms vague video ideas into detailed scene-by-scene plans (scenes.md). Conducts research, asks clarifying questions about audience/scope/focus, and outputs comprehensive scene specifications ready for implementation with ManimCE or ManimGL. Use this BEFORE writing any Manim code. This skill plans the video; use manimce-best-practices or manimgl-best-practices for implementation.
| Best practices for Manim Community Edition - the community-maintained Python animation engine. Covers Scene structure, animations, LaTeX/MathTex, 3D with ThreeDScene, camera control, styling, and CLI usage. NOT for ManimGL/3b1b version (which uses `manimlib` imports and `manimgl` CLI).
| Best practices for ManimGL (Grant Sanderson's 3Blue1Brown version) - OpenGL-based animation engine with interactive development. Covers InteractiveScene, Tex with t2c, camera frame control, interactive mode (-se flag), 3D rendering, and checkpoint_paste() workflow. NOT for Manim Community Edition (which uses `manim` imports and `manim` CLI).
当设计或修改 REST API 响应结构、处理 API 返回值，或生成 Excel/CSV/PDF/对账文件等下游产物时触发。防止 API 设计缺陷导致的字段错位、类型歧义，以及生成产物时关键字段缺失但静默成功的问题。
当编写新模块、设计接口、重构代码或代码审查时触发。提供经典模块化六原则检查清单（大小适中/调用深度/扇入扇出/边界清晰/作用域内聚/可预测性），适用于 PR/Review/新模块设计场景。
当重构涉及字段映射（dataIndex、枚举映射、类型转换）时触发。防止字段名推测错误，确保字段映射的正确性。
网关/代理/WAF/CDN 中间件的安全关键词匹配实现规范，防止纯子串匹配误判正常响应内容中的技术术语（如 Cloudflare、502、error）
涉及浏览器、编辑器、CDN/WAF、IM 平台、操作系统剪贴板、第三方 SaaS 等"外部黑盒系统"的代码编写或 bug 调试时触发。强制先抓真实环境数据再推理,避免连续 2 轮"凭代码推理"的修复 no-op。关键词:粘贴/复制异常、跨平台显示不一致、第三方 API 怪结果、CDN/WAF 拦截、本地复现失败、HTML→MD 转换丢属性。
当用户操作 .sh、Dockerfile、Makefile、.yml、.yaml 文件，或在 Markdown 中编写 bash 代码块时触发。提供 Bash 编写规范。
当 API/任务可能执行超过 10 秒（批量数据处理、远程 API 批量调用、全表扫描、跨租户聚合）时触发。防止同步接口被网关 30s 超时切断、用户重复点击触发并发、状态缓存内存泄漏等问题。提供异步任务状态机标准模板。
前端开发规范，包含 Vue 3 编码规范、UI 风格约束、TypeScript 规范等
Java 开发规范，包含命名约定、异常处理、Spring Boot 最佳实践等
当代码涉及多租户隔离（TenantContext、tenantId、租户拦截器/过滤器、X-Tenant-Code）时触发。防止租户越权访问、数据串租户等安全问题。
当代码涉及支付回调、webhook 通知、notify_url、微信支付/支付宝回调处理时触发。防止回调伪造、重放攻击、金额篡改等支付安全问题。
Go 开发规范，包含命名约定、错误处理、并发编程、测试规范等
当用户执行系统级命令（sysctl、iptables、systemctl、Docker 配置、数据库 DDL）或进行服务器运维操作时触发。提供运维安全规范。
当代码涉及循环内查询、批量 ID 查询、IN 子句、BFS/递归遍历、嵌套 service 调用时触发。防止 N+1 查询、IN 子句过长、递归内存炸裂等性能陷阱。
当用户操作 Redis 相关代码（go-redis、Jedis、redis-py、ioredis）时触发。涵盖禁止 KEYS 命令、SCAN 替代、大 key 控制、Pipeline 批量、TTL 规范等安全与性能要点。
当用户要求重构代码（提取组件、合并重复逻辑、重命名变量、优化结构）时触发。提供重构安全检查清单，防止丢失原始上下文。
当用户执行 /ruanzhu 命令或请求生成软著源代码文档时触发。提供软著源代码 DOCX 生成规范。
Rust 开发规范（聚焦 Axum + Tokio 后端栈），覆盖工具链、错误处理、异步陷阱、模块组织、依赖管理与测试规范
当使用 MinIO/OSS/S3 等对象存储、设计文件上传下载功能时触发。提供存储 URL 策略选择规范，防止 URL 过期、访问失败等问题。
当代码涉及 Excel/CSV/JSON/PDF 大文件导出、批量序列化、内存里构建大对象时触发。防止 OOM、临时文件残留、同步导出阻塞 HTTP 线程等内存安全陷阱。
当代码出现 LocalDate.now() / LocalDateTime.now() / Instant.now() / new Date() / Date.now() / time.Now() 等"当前时间"调用，或涉及周/月/日起点、跨时区比较、数据库时间字段时触发。防止生产环境时区漂移导致的统计错乱。
Review changed code for reuse, quality, and efficiency, then fix any issues found. Also scans project files for size limit violations.
专业级 UI/UX 设计规范，需要高质量界面设计时手动触发或描述"设计感/专业UI"时自动触发。覆盖视觉层次、配色体系、排版节奏、交互微动效、响应式适配等。日常前端开发由 frontend-dev skill + frontend-design 插件覆盖。
网关/代理/WAF/CDN 中间件的安全关键词匹配实现规范，防止纯子串匹配误判正常响应内容中的技术术语（如 Cloudflare、502、error）
Python 开发规范，包含 PEP 8 风格、类型注解、异常处理、测试规范等
当设计或修改 REST API 响应结构、处理 API 返回值时触发。防止 API 设计缺陷导致的字段错位、类型歧义等问题。
涉及浏览器、编辑器、CDN/WAF、IM 平台、操作系统剪贴板、第三方 SaaS 等"外部黑盒系统"的代码编写或 bug 调试时触发。强制先抓真实环境数据再推理,避免连续 2 轮"凭代码推理"的修复 no-op。关键词:粘贴/复制异常、跨平台显示不一致、第三方 API 怪结果、CDN/WAF 拦截、本地复现失败、HTML→MD 转换丢属性。
Go 开发规范，包含命名约定、错误处理、并发编程、测试规范等
前端开发规范，包含 Vue 3 编码规范、UI 风格约束、TypeScript 规范等
当重构涉及字段映射（dataIndex、枚举映射、类型转换）时触发。防止字段名推测错误，确保字段映射的正确性。
Java 开发规范，包含命名约定、异常处理、Spring Boot 最佳实践等
Python 开发规范，包含 PEP 8 风格、类型注解、异常处理、测试规范等
当用户操作 Redis 相关代码（go-redis、Jedis、redis-py、ioredis）时触发。提供 Redis 安全与性能规范。
当用户要求重构代码（提取组件、合并重复逻辑、重命名变量、优化结构）时触发。提供重构安全检查清单，防止丢失原始上下文。
Claude Skills — questions
Answers built from the skills we actually parsed.