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.
Migration logic for Azure SDK for .NET data-plane libraries migrating from AutoRest/Swagger to TypeSpec-based generation. Uses MCP tools from the generator-agent server for automated deterministic fixes.
Patterns and techniques for mitigating breaking changes during Azure management-plane SDK migration from Swagger/AutoRest to TypeSpec. Covers SDK-side customizations (partial classes, CodeGenType, CodeGenSuppress) and TypeSpec decorator customizations (clientName, access, markAsPageable, alternateType, hierarchyBuilding).
Resolve review comments on Azure management-plane .NET SDK PRs. Handles renaming types/properties, changing property types, and other API surface adjustments by updating TypeSpec client.tsp and regenerating.
Handles Azure SDK for .NET management-plane migrations from AutoRest/Swagger to TypeSpec; use for MPG, mgmt migration, or Azure.ResourceManager.* migration requests.
Query and modify CODEOWNERS ownership, service labels, and package associations in Azure SDK repositories. **UTILITY SKILL**. FOR SINGLE OPERATIONS: view, add, or remove owners and labels. WHEN: \"code owners\", \"view codeowners\", \"add package owner\", \"remove package owner\", \"add label\", \"remove label\", \"codeowners blocked PR\", \"who owns this package\", \"create service label\", \"update codeowners cache\", \"unblock release\". INVOKES: azsdk_engsys_codeowner_view, azsdk_engsys_codeowner_add_package_owner, azsdk_engsys_codeowner_add_label_owner, azsdk_check_service_label, azsdk_create_service_label, azsdk_engsys_codeowner_update_cache, azsdk_engsys_codeowner_check_package.
Review Azure SDK management-plane migration PRs (Swagger/AutoRest -> TypeSpec). Checks customization quality, TypeSpec decorator usage, and migration-specific anti-patterns on top of the standard mgmt PR review.
Generate new Azure.Provisioning.* libraries OR regenerate existing ones. Use when introducing a brand-new provisioning library, adding new resource types, enum values, or API versions.
Pre-commit validation checks for azure-sdk-for-net. Use this before committing or pushing changes to SDK packages. Runs dotnet format, exports public API listings, updates snippets, and regenerates code as needed.
Generate a test given sample. Parameters: <cs_root> C# SDK repository root; <package_name> Package name: one of Azure.AI.Projects, Azure.AI.Projects.Agents or Azure.AI.Extensions.OpenAI; <sample_name> the sample to use as a starting point for the test.
**WORKFLOW SKILL** — Prepares Azure.ResourceManager SDK refresh pull requests in azure-sdk-for-net. WHEN: \"prepare sdk refresh\", \"refresh Azure.ResourceManager package\", \"update ARM SDK from autorest tag\", \"refresh changelog dependencies\". INVOKES: git and GitHub pull request tools for branch, commit, push, and PR creation. FOR SINGLE OPERATIONS: Use git or GitHub tools directly.
Generate the code from typespec for C#. Parameter: C# SDK repository root location <cs_root>.
Update the CHANGELOG.md files of C# projects. Parameters: cs_root C# SDK repository root.
Build the matrix of all the samples throughout different frameworks.
Translate the Azure SDK sample from python to C# and generate markdownn file for the sample. Parameters: <cs_root> C# SDK repository root; <python_root> python SDK repository root; <package_name> Package name: one of Azure.AI.Projects, Azure.AI.Projects.Agents or Azure.AI.Extensions.OpenAI; <sample_name> The name of sample file in Python SDK repository.
长篇网文写作。从大纲到正文，辅助长篇网络小说的创作，包括世界观、人物、情节线管理。触发方式：/story-long-write、/写长篇、「帮我开书」「写大纲」「日更」「续写」「继续写」「修改第X章」「回炉」「重写第X章」。
长篇网文拆文。深度拆解爆款长篇小说的黄金三章、人设架构、爽点设计、节奏控制。单一深度拆解管道：跑完黄金三章（Stage 1）后产出快速预览报告并询问是否继续全量拆解，确认后从 Stage 2 续跑逐章摘要、聚合分析、设定关系、汇总报告，全程产物落盘 拆文库/{书名}/。触发方式：/story-long-analyze、/长篇拆文、「帮我拆这本书」「拆这本书」「分析黄金三章」「深度拆解」「完整拆解」「系统拆解」或提供小说文本文件路径——全部进入同一管道。
逆向导入已有小说。将已写好的小说（半成品或完本）反向解析为标准项目目录结构，兼容 story-long-write / story-short-write 后续写作流程；内部复用 story-long-analyze / story-short-analyze 的拆解管道，按篇幅自动分流。触发方式：/story-import、「导入小说」「反向解析」「导入」「把我的书导进来」。
网文去AI味。检测并清除文本中的AI写作痕迹，让文字回归自然、非模板化。触发方式：/story-deslop、/去AI味、「去AI味」「这篇太AI了」「网文去AI味」。
多视角对抗式审查。full/lean 模式在已部署 reviewer agents 时并行 spawn；缺失/异常 agents 或 spawn 失败时自动降级 solo，参考文件不可读时使用内置 rubric fallback。触发方式：/story-review、/审查、「审查一下」「帮我审一下」。
网文写作工具集基础设施部署。为 Claude Code / OpenCode / Codex / ZCode / OpenClaw / Reasonix 提供内置适配；Web AI / 通用 Agent 可走 skills + AGENTS.md 文件模式。触发方式：/story-setup、$story-setup、「准备写书」「帮我搭一下环境」「配置写作项目」。
短篇网文拆文。拆解爆款短篇小说（番茄短篇 / 故事会 / 知乎盐选 / 追妻 / 世情 / 重生 / 虐渣等通俗题材）的故事核、结构、情感线、反转设计、写作手法、共鸣层次。单一全量拆解管道：跑完 Stage 2-6 产出完整拆文报告，落盘到 拆文库/{书名}/，下游 story-short-write 同时读拆文报告 + 情节节点 + 写作手法 + 原文 + _meta.json 写下一篇。触发方式：/story-short-analyze、/短篇拆文、「拆短篇」「拆这篇短文」「短篇拆文」「精细拆解短篇」「8000 字短篇拆解」「番茄短篇拆文」「故事会拆解」「盐言故事拆解」「分析这篇短篇」——均进入同一管道。
网络小说工具箱主入口。根据用户需求自动路由到对应 skill，并可启动本地 Dashboard 查看拆文库、写作项目和编辑文本。触发方式：/story、$story、/story dashboard、$story dashboard、/网文、「我想写小说」「打开工作台」「检查更新」。
短篇网文写作。辅助短篇小说创作，从构思到成稿，聚焦情绪拉扯与节奏把控。触发方式：/story-short-write、/写短篇、「帮我写一篇短篇」「写个盐言故事」。
Solve a user-specified web task code-as-action style by driving a local Playwright browser through one bash command at a time, saving screenshots and an action log into `final_runs/run_<id>/`, and visually verifying the result. Use when the user asks to automate a web task (search, filter, form-fill, multi-step flow, data extraction) and wants reusable scripts plus screenshot evidence rather than a one-shot answer.
> Help create a minimal reproduction for a TypeSpec compiler or emitter bug. Use when a user provides TypeSpec source (pasted code or a GitHub URL) and describes an issue. Reproduces locally and reduces to a single-file repro.
> a changeset, and push. This skill is specifically for the language emitter packages (http-client-python, http-client-csharp, http-client-java) - NOT for core TypeSpec packages like compiler, http, openapi3, etc. Use when the user wants to finalize emitter changes, says things like "prep for pr", "prepare for PR", "validate and push", "add changeset", or "finalize changes".
Format the codebase with pnpm and recover from common formatting failures.
Discovers and implements gaps in Spector test coverage for the C# HTTP client emitter. Use when asked to find missing Spector scenarios, add Spector test coverage, or implement a specific Spector spec for the C# emitter.
Writes TypeSpec http-client-python generator mock API tests (azure/unbranded/shared) from a Spector case. Use when given a Spector case link or a PR link that modifies Spector cases under http-specs/azure-http-specs.
> Generate Python SDK code from a TypeSpec specification using the local emitter. Use this skill when the user wants to generate/regenerate a Python client from a TypeSpec spec, provides a GitHub URL or local path to a TypeSpec project, or says things like "generate from this spec", "emit Python from this tsp", "regenerate the SDK", or "compile this TypeSpec for Python".
> Regenerate the local emitter and diff the generated code against the upstream baseline checked into autorest.python. Use this skill when the user wants to see how their emitter changes affect generated code compared to what's currently in production, says things like "diff upstream", "compare to baseline", "what changed vs production", "show me the diff", "how does this affect generated code", or wants to validate their changes produce the expected output differences.
Create a PR to bump TypeSpec/Azure Tools dependencies, update peer dependencies, or release a new version of the http-client-python package.
> Build and test the @typespec/http-client-python emitter. Use this skill whenever the user wants to test their local changes to the emitter, run the generator test suite, check if their http-client-python changes are passing, or validate a fix. Triggers on phrases like "test the emitter", "run tests", "check if my changes in the emitter package.
Implement tasks from an OpenSpec change. Use when the user wants to start implementing, continue implementation, or work through tasks.
Archive a completed change in the experimental workflow. Use when the user wants to finalize and archive a change after implementation is complete.
Creates accessible hand-authored inline SVG architecture and sequence diagrams for documentation. Use when adding, replacing, or reviewing docs diagrams, especially Mermaid flowcharts.
Create and publish concise Rivet launch or changelog posts through an approval-gated workflow, including release research, a required user-selected hero variation, local HTML-rendered social and technical images, an R2 hero upload, MDX authoring, a reviewed draft GitHub PR for manual merge, and a scheduled and verified Buffer thread for @rivet_dev. Use when asked to launch, announce, ship, or prepare and schedule a Rivet feature or release announcement.
Methodically run the RivetKit driver test suite file by file across the native (NAPI) and wasm runtimes, tracking progress in ~/.agents/notes/driver-test-progress.md. Use when you need to validate the driver test suite after changes, bring up a new driver, or debug test failures systematically.
Bulk-merge a Graphite stack into main via admin-bypass fast-forward push. Replaces the Graphite merge queue for rivet-dev/rivet. Invoke when the user says "merge the stack at <branch>", "ship everything through <branch>", "bulk-merge up to <branch>", "fast-forward main to <branch>", or any request to land multiple stacked PRs at once in one shot. Requires repo admin permissions (bypasses branch protection), Graphite (gt) CLI, and GitHub (gh) CLI. After the FF push, closes all in-scope PRs explicitly with `gh pr close` in parallel — GitHub does not auto-mark them as MERGED because their bases point at sibling stack branches, not main.
Continue working on an OpenSpec change by creating the next artifact. Use when the user wants to progress their change, create the next artifact, or continue their workflow.
Guided onboarding for OpenSpec - walk through a complete workflow cycle with narration and real codebase work.
Fast-forward through OpenSpec artifact creation. Use when the user wants to quickly create all artifacts needed for implementation without stepping through each one individually.
Archive multiple completed changes at once. Use when archiving several parallel changes.
Enter explore mode - a thinking partner for exploring ideas, investigating problems, and clarifying requirements. Use when the user wants to think through something before or during a change.
Start a new OpenSpec change using the experimental artifact workflow. Use when the user wants to create a new feature, fix, or modification with a structured step-by-step approach.
Sync delta specs from a change to main specs. Use when the user wants to update main specs with changes from a delta spec, without archiving the change.
Verify implementation matches change artifacts. Use when the user wants to validate that implementation is complete, correct, and coherent before archiving.
Generate a clear, concise GitHub PR title and description from the diff between two local git branches, and save it to prDescription.md in the repo root. Use this whenever the user asks to write, generate, draft, or update a PR description or PR title from local branch changes — including phrasing like "summarize this diff into a PR description," "write a PR description for my current branch," "create a PR title and description," or any request to compare a base and target branch for PR purposes. Trigger even if the user doesn't name specific branches; this skill knows how to default them.
Use when writing or editing Javadoc for Lettuce public API — new methods, classes, deprecations, or when a reviewer asks to fix or improve doc comments. Points to the full house ruleset in .agents/docs/javadoc.md (imperative method summaries, fixed tag order, @param/@return/@throws/@since/@deprecated house forms) and the rule that command-interface Javadoc is edited in the template, not the generated files. Trigger on "write javadoc for", "document this method", "add a deprecation notice", "fix the doc comment".
Use when adding a new Redis command — or a new overload/variant of one — to the Lettuce client. Covers the full flow: writing the command specification, designing the Lettuce API, adding argument types and the API template, running the interface generators, adding the builder/async/reactive/Kotlin implementations, and adding unit + integration tests. Trigger on requests like "add support for the <X> command", "implement <REDIS COMMAND> in Lettuce", "wire up a new command", or adding a new argument/overload to an existing command.
Reviews code changes and provides actionable feedback. Use when the user asks to review a PR, diff, commit, or code changes. Triggers on "/review", "review this PR", "review my changes", "code review".
This skill encodes Emil Kowalski's philosophy on UI polish, component design, animation decisions, and the invisible details that make software feel great.
Guides a user through collecting the credentials needed to deploy their own copy of Open Harness, deploying this repo on Vercel, and completing first-run setup. Use for requests about deploying, self-hosting, configuring credentials, or getting started with a fork of this app.
Validates animation durations, enforces typography scale, checks component accessibility, and prevents layout anti-patterns in Tailwind CSS projects. Use when building UI components, reviewing CSS utilities, styling React views, or enforcing design consistency.
Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, artifacts, posters, or applications (examples include websites, landing pages, dashboards, React components, HTML/CSS layouts, or when styling/beautifying any web UI). Generates creative, polished code and UI design that avoids generic AI aesthetics.
Automates browser interactions for web testing, form filling, screenshots, and data extraction. Use when the user needs to navigate websites, interact with web pages, fill forms, take screenshots, test web applications, or extract information from web pages.
React and Next.js performance optimization guidelines from Vercel Engineering. This skill should be used when writing, reviewing, or refactoring React/Next.js code to ensure optimal performance patterns. Triggers on tasks involving React components, Next.js pages, data fetching, bundle optimization, or performance improvements.
Removes Open Harness hosted demo restrictions from a fork. Use when a maintainer wants to remove managed-template trial caps, hosted deployment gating, or "deploy your own" limits. Triggers on "remove demo limits", "remove trial limits", "remove hosted restrictions", "open this up for my fork", "remove managed template restrictions".
Holistic, system-aware planning before implementing non-trivial tasks. Use when the task involves new features, architectural decisions, multi-file changes, unclear requirements, or multiple valid approaches. Triggers on "/plan", "plan this", "design an approach", "let's plan first".
Claude Skills — questions
Answers built from the skills we actually parsed.