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. 79 437 files from 1 744 authors, of which 61 785 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.
Write, update, and audit KDoc documentation for the Multik library. Handles the full cycle: KDoc comments on source code, syncing with Writerside user docs in docs/topics/, and creating/updating Korro code samples.
Write and edit Writerside user documentation pages for the Multik library. Covers all page types: Getting Started, User Guide, and API Reference. Handles page structure, Korro code samples, mk.tree navigation, and cross-references. Use this skill when creating new doc pages, updating existing ones, or when the multik-kdoc skill needs to create/update Writerside topics.
Match a design project to supported design-award programs, tracks, and entry categories; apply structural eligibility gates; verify current official rules; compare published criteria and cautiously described winner trends; and output fit, evidence confidence, and submission priority. Use when a user asks which award or category to enter, compares awards, or requests an award-fit analysis. Supports iF, iF Student, Red Dot Product, Red Dot Design Concept, IDEA, DIA, K-Design, GOOD DESIGN AWARD Japan, Core77, James Dyson, and EPDA. Do not use for winner retrieval alone, detailed submission-file compliance, general design evaluation, optimization, or winning-probability prediction.
Route and coordinate an end-to-end design-award workflow across winner research, evidence-based evaluation, award matching, entry-text preparation, and final submission checking. Use when a user asks for a complete award plan, does not know which Design Judge skill to use, wants multiple stages coordinated, or needs a resumable workflow with explicit handoffs. Do not replace the specialist skills, invent project facts, treat scores as winning probabilities, or bypass current official-rule verification.
Find and verify award-winning designs in the same or adjacent functional category through eight explicit relevance dimensions: problem and user, core function, sensing technology, intervention mechanism, physical form, use context and workflow, system architecture, and visual language. Use when a user asks for same-category winners, comparable precedents, design benchmarks, appearance-related award winners, or examples from iF Design, Red Dot, IDEA, or iF Design Student Award. Do not use this skill to score, judge, optimize, or match the user's design to an award.
Evaluate one design or a user-approved maturity-mapped batch through a transparent evidence-based rubric. Classify each work, score design quality and presentation, identify Critical risks, report evidence confidence, and optionally shortlist works within separate maturity tracks. Use when a user asks to judge, score, critique, review, diagnose, batch-evaluate, or rank designs by evidence-aligned evaluation score. Do not use this skill to retrieve winners, choose an award, produce a redesign, audit submission-file compliance, simulate an official jury, or predict winning probability.
Extract evidence-grounded project facts from user-provided design attachments, identify missing information, and prepare the exact written fields required by supported design-award entry forms. Use when a user asks to prepare, draft, adapt, translate, or validate application text for iF, iF Student, Red Dot Product Design, IDEA, DIA, K-Design, GOOD DESIGN AWARD Japan, Core77, James Dyson, or EPDA. Also use to build a reusable project dossier from briefs, decks, reports, manuals, patents, research, images, or prior application materials. Do not use for award selection alone, winner retrieval, design-quality scoring, final file-format auditing, or winning-probability prediction.
Shared support package for the Design Judge skill collection. Install it with design-award-search and design-award-match so those skills can read the canonical functional-design taxonomy and official award-source registry. Do not invoke it as a standalone design workflow.
Audit a design-award submission package against the current official rules for a specific award cycle. Check required materials and technical constraints, cross-material facts and claims, rights and disclosure risks, and final submission readiness. Use when a user asks for a pre-submission check, compliance review, missing-material audit, consistency check, or final go/no-go decision. Do not use this skill to choose an award, retrieve winners, judge the design itself, rewrite the whole entry, or give a legal clearance opinion.
Configure TypeAgent integration mode and settings
Read-only investigation and analysis of GitHub issues for Shopify/cli. Fetches issue details via gh CLI, searches for duplicates, examines the monorepo for relevant context, applies version-based maintenance policy classification, and produces a structured investigation report. Use when a GitHub issue URL is provided or when asked to analyze or triage an issue.
Prevent predictable Shopify CLI PR CI failures before push or submit. Use when users: (1) ask what to run before pushing, submitting, restacking, opening, or updating a PR, (2) ask which generated files to commit or stage, (3) want to validate a branch against GitHub Actions, or (4) want to avoid CI churn after command, docs, workflow, schema, or test changes. At PR time, default to suggesting the minimal pre-submit checks rather than running a full local workflow automatically.
Write a new library instrumentation end-to-end. Use when the user ask to add a new APM integration or a library instrumentation.
>- Review a code diff / branch / PR for technical debt — code duplication, unnecessary complexity / over-engineering, and redundant or dead code. Use whenever the user wants a tech-debt, cleanup, or refactor review, asks to check a branch or PR for duplication / complexity / dead code before opening a PR, or behavior-preserving fixes; it never changes behavior.
Convert JUnit 5 @MethodSource/@CsvSource/@ValueSource parameterized tests to @TableTest (JDK8)
>- Performance-overhead review of a code diff / branch / PR for the dd-trace-java tracer. Flags hot-path allocation, unbounded memory, repeated work, escaping objects, native-boundary crossings, and JVM-specific pitfalls (escape analysis, JNI / virtual-thread pinning, backtracking-regex ReDoS, varargs/boxing hashing, String.format, ByteBuddy-Advice anti-patterns) using the tracer performance rubric. Use whenever the user wants a performance / overhead / hot-path review, asks to check a diff or PR for allocation / GC / memory / latency / startup cost, or mentions the "perf rubric" or the "do no harm / assume hot" tracer posture — verify-first findings; it never edits code.
> Post-migration quality review. Checks Java test files produced by migrate-groovy-to-java against the shared quality rules. Use after migration, or on any branch with recently migrated .java test files. Produces structured FINDING blocks grouped by severity, then offers to auto-fix BLOCKERs and WARNINGs.
> Converts Spock/Groovy test files in a Gradle module to equivalent JUnit 5 Java tests. Use when asked to "migrate groovy", "convert groovy to java", "g2j", or when a module has .groovy test files that need to be replaced with .java equivalents.
依据真实 OpenAPI、路由实现和现有测试生成并验证 API 测试。用于用户要求测试接口、补集成测试、验证 API 契约、生成回归用例或排查接口兼容性时；区分“生成测试”和“执行请求”的授权，不猜测状态码、响应结构或 SLA，不在未确认环境中发送写请求。
Changelog 生成器 - 从 Git 历史自动生成 CHANGELOG
数据库迁移助手 - Schema 对比、迁移脚本生成
审计 Node.js、Python、Go、Rust、JVM、Ruby 项目的依赖漏洞、版本健康度与许可证事实；当用户要求检查 package.json、lockfile、requirements、go.mod、Cargo.toml、pom.xml、Gemfile.lock，或生成不改依赖的中文审计报告时使用
项目目录结构地图 - 生成带说明的可视化目录树，快速理解任意代码库
环境变量管理器：扫描、校验、同步 .env 文件，生成安全配置模板
编程错误消息翻译专家 — 将英文错误消息翻译成中文，解释原因并提供修复方案
安全诊断并修复 ESLint error、warning 和配置兼容问题。用于用户要求运行 lint、解释 ESLint 报错、限定范围自动修复或迁移 ESLint 配置时；优先使用项目锁定的包管理器与版本，先预检再修改，不自动下载最新版或批量改写无关源码。
安全处理 Git 状态检查、提交信息、commit、分支、push、PR 和 rebase。用于用户要求检查改动、生成或创建提交、管理分支、推送、发起 PR 或整理历史时；严格区分每个动作的授权，并保护工作树中已有和无关的修改。
分析真实项目并生成或修订安全、可验证的 GitHub Actions workflow；当用户要求创建 CI、测试矩阵、构建、Release、部署、缓存、Secrets、OIDC、PR 自动化或排查 workflow 配置时使用
国际化/本地化助手 — 扫描代码中的硬编码文本、生成 i18n 配置、批量翻译
日志分析助手 — 智能解析日志文件，识别异常模式，定位问题根因
基于可复现基线和 profiler 证据分析性能问题。用于用户要求定位慢接口、慢任务、慢查询、内存或网络瓶颈，制定优化方案，或验证优化收益时；区分实测结论与静态推断，不虚构耗时和提升比例，生产环境操作需明确授权。
重构顾问 - 识别代码坏味道并提供重构方案
代码安全审计 - 漏洞扫描、依赖检查、安全最佳实践
中文 Skill 收录评估器。用于核验 GitHub 上的 Claude Code、Codex、Agent Skills、Plugin、MCP、CLI 或 Agent 工作流是否值得加入精选列表；检查真实资产、安装方式、活跃度、重复项和安全边界，并生成分类、中文描述与可追溯证据。
依据真实代码契约生成并验证单元测试或集成测试。用于用户要求为函数、类、接口或缺陷补测试、提高覆盖率、生成回归用例或完善测试策略时；先读取现有测试与调用方，不猜测空值、异常或超时行为，不自动安装框架或访问生产依赖。
中文代码审查专家 - 生成详细的中文代码审查报告
中文文档生成器 - 从代码库自动生成中文技术文档
中文 README 生成器 - 先分析项目，再生成面向中文开发者的高质量 README
Provides guidance for writing and benchmarking optimized CUDA kernels for NVIDIA GPUs (H100, A100, T4) targeting HuggingFace diffusers and transformers libraries. Kernels must be kernel-builder/ABI3-compliant: no pybind11, no setup.py, TORCH_LIBRARY_EXPAND bindings only. Supports models like LTX-Video, Stable Diffusion, LLaMA, Mistral, and Qwen. Includes integration with HuggingFace Kernels Hub (get_kernel) for loading pre-compiled kernels. Includes benchmarking scripts to compare kernel performance against baseline implementations.
Provides guidance for writing and benchmarking optimized Triton kernels for AMD GPUs (MI355X, R9700) on ROCm, targeting HuggingFace diffusers (LTX-Video, SD3, FLUX) and transformers. Core kernels: RMSNorm, RoPE 3D, GEGLU, AdaLN. Includes XCD swizzle, autotune, diffusers integration patterns, and LTX-Video pipeline injection.
Provides guidance for writing, optimizing, and benchmarking C++ CPU kernels with SIMD intrinsics (AVX2/AVX512) for the Hugging Face kernels ecosystem. Includes a two-phase workflow: Phase 1 correctness (generic → AVX2) and Phase 2 performance exploration (AVX512 with branching trial loop), runtime CPU dispatch, OpenMP threading, and brgemm integration for GEMM-heavy kernels.
Provides guidance for writing, optimizing, and benchmarking Triton kernels for Intel XPU GPUs (Battlemage/Arc Pro B50) using the Xe-Forge optimization framework. Includes an LLM-driven trial-loop workflow (analyze, validate, benchmark, profile, finalize), XPU-specific patterns (tensor descriptors, GRF mode, tile swizzling), KernelBench fused kernels, and Flash Attention.
Use this skill whenever the user mentions Microsoft Teams in a development context — whether they're building, integrating, configuring, debugging, or just asking questions. Covers bots, message extensions, embedded web apps, Adaptive Cards, dialogs, SSO, infrastructure, the Teams Developer CLI/SDK, and general Teams platform queries. If the word "Teams" appears, err on the side of invoking this skill.
用于在正式动手前先澄清目标、约束、边界与方案，适合需要先理清问题再决定后续 skill 或实现路径的场景;触发名:brainstorming
用于对抗样本、模型提取、提示注入、成员推断、训练投毒、LoRA 滥用、LLM 越狱等 AI/ML 相关 CTF 题;触发名:ctf-ai-ml
面向中文用户和新手的统一入口，保持原有两种模式：1) 自动分流，2) 先头脑风暴再分流。分流目标既可以是 ctf-*，也可以在 Web/接口/漏洞验证阶段增强到 strix-*；适合不知道该用哪个 skill、想先理清题意、又不想自己先判断何时该切到工具链或漏洞专项的场景;触发名:ctf-beginner-hub
用于 RSA、AES、ECC、格攻击、LWE、CVP、Coppersmith、Pollard、Wiener、填充预言机、GCM、KDF、伪随机数与零知识证明等密码学和数学类 CTF 题;触发名:ctf-crypto
用于磁盘镜像、内存转储、事件日志、PCAP、隐写分析、Windows 注册表、音频信号、Docker 镜像、coredump 以及已删除文件与凭据恢复等取证类 CTF 题;触发名:ctf-forensics
用于混淆脚本、恶意样本、自定义加密协议、C2 流量、PE/.NET 二进制、RC4/AES 通信、YARA、shellcode、进程注入与反分析等恶意软件类 CTF 题;触发名:ctf-malware
用于编码题、pyjail、bash jail、RF/SDR、DNS 异常、Unicode、奇特语言、QR、音频、约束求解、博弈论与沙箱逃逸等跨类或边缘 CTF 题;触发名:ctf-misc
用于公开资料检索、社交媒体分析、地理定位、DNS、用户名枚举、反向图片搜索、历史快照、公开记录与坐标识别等 OSINT 类 CTF 题;触发名:ctf-osint
用于缓冲区溢出、格式化字符串、堆利用、ROP、ret2libc、shellcode、内核利用、seccomp 绕过与沙箱逃逸等 pwn 类 CTF 题;触发名:ctf-pwn
用于二进制、APK、WASM、固件、自定义虚拟机、字节码、游戏客户端、类恶意加载器以及反调试/反分析逻辑等逆向类 CTF 题;触发名:ctf-reverse
面向 CTF 新手与综合题的统一总控 skill。保持原有两种主模式：1) 自动分流，2) 先头脑风暴再分流。分流目标既可以是 ctf-*，也可以在 Web/接口/漏洞验证阶段增强到 strix-*；适合不知道该用哪个 skill、想边做边学、又不想自己先判断何时切换到工具链或漏洞专项的场景;触发名:ctf-super-hub
用于 XSS、SQL 注入、SSTI、SSRF、XXE、JWT、鉴权绕过、文件上传、请求走私、OAuth/OIDC、SAML 与原型污染等 Web 类 CTF 题;触发名:ctf-web
用于把已经完成的解题过程整理成结构化、可复现、可提交的 CTF 题解文档，适合赛后复盘、队内同步与对外提交说明;触发名:ctf-writeup
用于在 CTF 挑战开始时做首轮分类、轻量 triage 与 skill 路由，识别主导类别后转到对应 ctf-* skill，类别已明确时也可直接作为入口;触发名:solve-challenge
Strix JWT 与 OIDC 安全测试手册,覆盖令牌伪造、算法混淆与声明篡改;触发名:strix-authentication-jwt
给中文用户和新手用的 Strix Lite 统一入口：先判断该用哪一个 strix-* 工具或漏洞测试 skill，再给最小化起手步骤；适合在 Web 安全测试、工具链使用、漏洞验证时不知道先用哪个 Strix skill 的场景;触发名:strix-beginner-hub
Claude Skills — questions
Answers built from the skills we actually parsed.