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.
Trigger, re-run, and unblock ONNX Runtime CI checks on a GitHub pull request. Use this skill when a required check is stuck, missing, failed, or needs re-running. Nearly all ORT CI runs as GitHub Actions workflows; only the "Linux Android Emulator QNN CI Pipeline" remains on Azure Pipelines, plus the bot-driven "license/cla" and "Python format" lint checks. Triggers on: rerun CI, retrigger checks, stuck check, missing pipeline, failed CI, license/cla, Python format failure, Doc Gen CI failure, operator docs out of date, /azp run.
Audit and fix out-of-range output writes in ONNX Runtime operator shape-inference functions. Use when reviewing or fixing a contrib (or standard) op TypeAndShapeInference where a getNumOutputs() guard precedes a write to a higher output index - optional trailing outputs make a smaller output count schema-valid, so getOutputType(index) can run one past the declared outputs at Graph::Resolve.
Step-by-step checklist for bumping the pinned ONNX dependency / opset in ONNX Runtime (e.g. ONNX 1.21 / opset 26 → 1.22 / opset 27). Use when integrating a new ONNX release or release-candidate, updating the cmake/deps.txt onnx pin or the cmake/external/onnx submodule, regenerating cmake/patches/onnx/onnx.patch, raising kMaxSupportedOpset, or adding a new opset's CPU kernels. Covers the file taxonomy, archive-hash procedures, patch rebase/mirror rules, the RC→formal strategy, and the optimizer/EP gotchas that the automated audit script misses.
Run the ONNX Runtime transformers Python tests (onnxruntime/test/python/transformers) against a GPU wheel, and confirm real cuDNN/flash SDPA dispatch. Use when a transformers pytest fails with ModuleNotFoundError onnxruntime.capi, when torch's bundled CUDA/cuDNN libs shadow the ORT-built ones (wrong-version dispatch or load errors), or when you must PROVE a test exercised the cuDNN SDPA decode tier instead of silently skipping/falling back to MATH.
Use when editing a boundary-safe shared header meant to be included by both in-tree and shared-provider/plugin-bridge code (e.g. include/onnxruntime/core/framework/workspace_requirement.h, or any future header supporting OrtKernelWorkspaceEstimateFunc / DeclareWorkspaceRequirements per issue #29775's Phase-A workspace-estimation roadmap), or when a workspace-estimation math helper needs to be callable from a future plugin EP DLL. Covers a Node forward-declaration ODR trap and the math-helper vs. graph-parsing-wrapper reuse boundary discovered while implementing PR #29811 (MatMulNBits pilot).
Build and run ONNX Runtime WebGPU provider tests on Linux WITHOUT a real GPU, using a software Vulkan adapter (Mesa lavapipe). Use when you need to exercise WebGPU EP kernels off-Mac — the Linux webgpu CI leg is build-only, so software Vulkan is how you actually run WebGPU correctness tests locally. SCOPE - lavapipe only validates host-side enforce/shape bugs and MatMul-free kernels; any graph containing MatMul (including the expanded-Attention node tests) crashes lavapipe and runs ONLY on macOS-arm64 Metal, which is the source of truth for those. Covers install (dnf on Azure Linux), the --use_webgpu build flag, the onnxruntime_provider_test target, VK_ICD_FILENAMES, and the lavapipe MatMul crash gotcha.
When reviewing or fixing Python code that uses setattr() with user-controlled kwargs to configure C++ extension objects (SessionOptions, RunOptions, etc.) in ONNX Runtime. Use this to apply the allowlist pattern that prevents arbitrary file writes and other attacks via reflected property access.
Unified meta-skill engine for distilling colleague, relationship, or celebrity characters into reusable Skills. | 统一的 meta-skill 引擎，把 colleague、relationship、celebrity 三类对象蒸馏成可复用 Skill。
Set up a local development environment for the ADK Python project. Use when the user wants to get started developing, set up their environment, install dependencies, or prepare for contributing.
Use when debugging ADK agents, inspecting sessions, testing agent behavior, troubleshooting tool calls, event flow issues, or diagnosing LLM/model problems.
ADK architectural knowledge — graph orchestration, resumption, execution flow, node contracts, observability, and LLM context orchestration. Use this skill whenever you need to understand the architecture, event flow, or state management of the ADK system, or when designing or modifying core components. Triggers on "how does X work", "design of", "architecture of", "event flow", "resumption state", "checkpoint", "BaseNode", "NodeRunner".
Central hub for building, testing, and iterating on ADK agents. Trigger this skill when the user wants to create a new agent, configure modes (task, single-turn), or build graph-based workflows.
Use for any git operation (commit, push, pull, rebase, branch, PR, cherry-pick, etc.). Provides commit message format and conventions.
Reviews all local changes in the repository for errors, styling compliance, unintended outcomes, and necessary documentation/test/sample updates. Generates a report and assists in fixing identified issues on-demand. Triggers on "adk-review", "review changes", "pr review", "check code style", "verify changes".
Author new samples for the ADK Python repository. Use this skill when the user wants to create a new sample demonstrating a feature or agent pattern (e.g., dynamic nodes, standalone agents, fan-out/fan-in) or when adding examples to subdirectories under `contributing/`.
ADK development style guide for routine nits — Python idioms, codebase conventions, imports, typing, Pydantic patterns, formatting, logging, async/concurrency, and file organization. Use this skill whenever writing code, tests, or reviewing PRs for the ADK project to ensure compliance with styling and coding conventions. Triggers on "code style", "how should I format", "naming convention", "lint", "nit", "imports", "typing", "Pydantic patterns", "testing rules", "async", "io".
Creates or updates code unit design documents for source code documentation.
Creates detailed code unit guides for source code documentation.
> Extracts and verifies the runnability and code coverage of all Python code blocks inside a Markdown file. Generates a detailed compilation and execution report.
| Skill for BigQuery AI and Machine Learning queries using standard SQL and `AI.*` functions (preferred over dedicated tools).
| Skill for Graph Query Language (GQL) or SQL/PGQ queries against a property graph. Includes path finding, multi-hop traversal, topological connection, shortest path, node reachability, edge connectivity, and semantic graph queries.
> Guidelines and SOP for synchronizing public C++ API changes (methods, enums, options structs) to Java (Android JNI) and JavaScript/TypeScript (Web/WASM Embind).
> Build, deploy, run, and benchmark Filament binaries on connected Android devices or emulators. Use this skill for compiling, pushing, and executing Android tests or benchmarks.
> Enforce the strict topological header inclusion layering and reordering rules in Filament. Use this skill when adding or modifying `#include` directives in C++ source or header files.
> Clean and build Filament targets for development, debugging, and production. Use this skill whenever you need to clean the workspace or compile desktop targets.
> Enforce strict header self-containment so that every header file compiles independently. Use this skill when creating or modifying C++ header files.
> Execute unit tests and performance benchmarks for Filament on desktop platforms. Use this skill to run and filter tests or benchmarks locally.
> Enforce C++ static thread safety annotations and correct synchronization primitives. Use this skill when designing multi-threaded classes or editing guarded member fields.
> Enforce preprocessor guard rules and macro-dependent inclusion hygiene in C++. Use this skill when modifying conditional imports or preprocessor directives.
> Standard verification pipeline to execute after modifying C++ source or header files. Use this skill to format includes, build the engine, and run core tests.
> Enforce correct Filament object creation and destruction lifecycles. Use this skill when initializing rendering pipelines or allocating/deallocating GPU buffers and entities.
> Enforce correct mathematical primitives and naming conventions in Filament code. Use this skill when performing coordinate transformations, vector math, or projection setups.
>- Review and optionally combine at most 11 open individual Dependabot patch and minor pull requests into a validated draft rollup PR. Use this skill as a local or cloud-agent fallback to native Dependabot groups without adding a custom scheduled GitHub Actions workflow. Always presents a dry-run plan and requires explicit approval before changing branches or GitHub pull requests.
Scaffold a new v9 component with all required files following Fluent UI patterns (hook, styles, render, types, tests, stories, conformance)
Find the matching Fluent UI design token for a hardcoded CSS value (color, spacing, font size, border radius, shadow)
Create a beachball change file for the current changes. Determines change type (patch/minor) and generates a description from the diff.
Review a PR for correctness, pattern compliance, testing, accessibility, and safety. Produces a confidence score for merge readiness.
Run lint on affected packages, parse errors, and auto-fix common issues (design tokens, React.FC, SSR safety, import restrictions)
Quick lookup for a Fluent UI package — path, dependencies, owner team, Nx project details, and relevant docs
>-
Visually verify a component by launching its Storybook story and taking a screenshot with playwright-cli. Use after making visual changes to a component.
Bitwarden database architecture, migrations, and dual-ORM strategy. Use when working with `.sql` files, stored procedures, EF migrations, or database schema changes. Also use when deciding whether a change needs both Dapper and EF Core implementations, or whether a breaking stored-procedure change requires `_V2` versioning.
Read-only exploration of a local Bitwarden development database — answer business questions from live data, verify seeded fixtures, and introspect schema. Use whenever the user wants to query, count, look up, verify, or explore data in a local Bitwarden database ("how many orgs/users/ciphers", "show me collections", "check what the seeder created", "look up user X", "which orgs have feature Y"), even without the word SQL. Not for authoring stored procedures, migrations, or repository code (use writing-database-queries), and not for seeding or modifying data.
Bump the server's util/RustSdk `bitwarden-crypto` git-rev pin to a bitwarden/clients release — map the client's sdk-internal version to a commit, fix breaking changes, then verify.
Implementing Dapper repository methods and stored procedures for MSSQL at Bitwarden. Use when creating or modifying Dapper repositories, writing stored procedures, or working with MSSQL-specific data access in the server repo. Also use when writing MSSQL migration scripts under `util/Migrator/DbScripts/` or touching SSDT schema under `src/Sql/dbo/`.
Implementing Entity Framework Core repositories and migrations for PostgreSQL, MySQL, and SQLite at Bitwarden. Use when creating or modifying EF repositories, generating EF migrations, or working with non-MSSQL data access in the server repo. Also use when editing `EntityTypeConfiguration<T>` classes or debugging provider-specific LINQ translation issues.
Bitwarden server code conventions for C# and .NET. Use when working in the server repo, creating commands, queries, services, or API endpoints. Also use when writing xUnit tests with `SutProvider`/`BitAutoData`, registering DI, or generating entity IDs.
Train and fine-tune transformer language models using TRL (Transformers Reinforcement Learning). Supports SFT, DPO, GRPO, KTO, RLOO and Reward Model training via CLI commands.
查询 AI HOT 的中文 AI 资讯、精选、当前热点和日报。用户询问今天或最近的 AI 新闻、AI 圈动态、大模型或产品发布、OpenAI／Anthropic／Google 最新消息、AI 论文、AI 日报、AI HOT 精选、当前最热事件，或需要同步当前全部精选时使用。必须通过 aihot.virxact.com 的匿名只读 API 获取当前数据，不凭训练记忆回答新闻；不需要 API Key 或 MCP server。
| 横纵分析法（Horizontal-Vertical Analysis）深度研究Skill。由数字生命卡兹克提出，融合了索绪尔的历时-共时分析、社会科学的纵向-横截面研究设计、商学院案例研究法与竞争战略分析的核心思想。 当用户想要系统性研究一个产品、公司、概念、技术或人物时使用。核心是双轴分析：纵轴追踪从诞生到当下的完整生命历程（以叙事故事呈现），横轴在当下时间截面上与竞品/同类进行系统性横向对比，最后交叉两条轴产出独到洞察。最终产出一份排版精美的PDF研究报告。 触发词包括但不限于：横纵分析、研究一下、帮我分析、深度研究、做个研究、调研一下、竞品分析、帮我看看这个东西怎么样、这个产品/公司/概念是怎么回事、帮我摸清楚、帮我搞懂、帮我做个deep research。 即使用户只是说"帮我了解一下XX"或"XX是什么来头"，只要上下文暗示需要系统性的深度研究（而非简单的概念解释），都应该触发。也适用于用户丢来一个产品名、公司名、技术名词说"帮我研究一下这个"的场景。 不要用于简单的名词解释（用户只是问"XX是什么"）、不要用于公众号写作（那个用khazix-writer）、不要用于纯标题摘要生成（用wechat-title）。
| 数字生命卡兹克（Khazix）的公众号长文写作skill。当用户需要撰写公众号文章、写稿子、续写文章、根据素材产出长文时使用。触发词包括但不限于：写文章、写稿子、帮我写、续写、扩写、公众号文章、长文、出稿、按我的风格写。即使用户只是说"帮我把这个写成文章"或"用我的风格写一下"，只要上下文涉及内容创作和公众号输出，都应该触发。也适用于用户丢过来一个PDF、brief、新闻链接、语音转文字或任何素材说"帮我写篇文章"的场景。不要用于短内容（小红书帖子、推特、朋友圈）或纯标题摘要生成（那个用wechat-title skill）。
把一句话的想法拆成 AI agent 能独立跑完的目标任务书。用户说「帮我给 agent 写个目标」「帮我详细拆一下这个目标」「写个任务书/brief 给 agent」「写个 goal 提示词」「让 agent 自己跑这个项目」「把活分给几个 agent 并行」时使用。先进代码库实测、必要时联网调研，再一次性提问（≤5 个），产出一份 ≤4000 字符、直接粘进 /goal 就能跑的任务书，含实测数字、白名单地界、防作弊验收和断点续跑。执行型与探索型（调研/选型/找方案）自动分流。
Claude Skills — questions
Answers built from the skills we actually parsed.