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. 79 404 files from 1 741 authors, of which 61 763 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.
> 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.md/AGENTS.md), authorized agent memory, and workspace residue with what the code and runtime actually do, so the next session or the next person starts from one current answer. Trigger when the user names "neat-freak", "洁癖", or "/neat" — and also on clear knowledge-closeout development ("把文档和记忆整理一下", "收尾时把文档同步掉", "docs 和代码对不上了"), stale or conflicting CLAUDE.md/memory, a clean handoff to a teammate or a fresh session, or auditing whether workspace rules are actually followed. Do not trigger for pure coding/refactoring/debugging tasks, tidying data or prose (JSON, 周报, changelog announcements), or a bare "整理" with no project-knowledge context.
> macOS / Windows 只读存储分析助手（自动识别系统）。扫描整机磁盘占用，找出 占空间大户，把每一项分成 🟢可自动清理 / 🟡需人工判断 / 🔴谨慎清理 三级并给出 可执行处置方案，生成排版精美、可折叠、命令可一键复制的交互式 HTML 报告，并可 起本地服务在网页上一键删除（移废纸篓/直接删）。扫描全程只读。务必在以下场景 使用：用户说"存储分析""磁盘满了""C盘/硬盘满了""空间不够""清理空间" "清理磁盘""占空间""哪些东西占地方""帮我看看存储""看一下电脑存储/空间" "存储空间""电脑空间不够""内存满了/不够/不足""看下内存/存储"（中文口语里 "内存"常指存储空间）"storage analysis""disk cleanup""清缓存""磁盘清理"； 或用户抱怨电脑没空间、想知道什么东西吃硬盘、想要清理建议时。注意：若用户明确 指运行内存/RAM（如"哪个进程吃内存""内存占用高"想看活动监视器），那是 RAM 不是存储，不属于本 skill。
> (1) Adding a brand-new syscall that currently returns ENOSYS or is missing from the table. (2) Adding missing flags/options to an existing partially-supported syscall (e.g., a new prctl option, ioctl command, or socket option). Use when asked to implement a syscall, add a flag, or improve compatibility for a specific syscall.
Train or fine-tune sentence-transformers models across `SentenceTransformer` (bi-encoder; dense or static embedding model; for retrieval, similarity, clustering, classification, paraphrase mining, dedup, multimodal), `CrossEncoder` (reranker; pair scoring for two-stage retrieval / pair classification), and `SparseEncoder` (SPLADE, sparse embedding model; for learned-sparse retrieval). Covers loss selection, hard-negative mining, evaluators, distillation, LoRA, Matryoshka, and Hugging Face Hub publishing. Use for any sentence-transformers training task.
Edit any video by conversation. Transcribe, cut, color grade, generate overlay animations, burn subtitles — for talking heads, montages, tutorials, travel, interviews. No presets, no menus. Ask questions, confirm the plan, execute, iterate, persist. Production-correctness rules are hard; everything else is artistic freedom.
Production pipeline for mathematical and technical animations using Manim Community Edition. Creates 3Blue1Brown-style explainer videos, algorithm visualizations, equation derivations, architecture diagrams, and data stories. Use when users request: animated explanations, math animations, concept visualizations, algorithm walkthroughs, technical explainers, 3Blue1Brown style videos, or any programmatic animation with geometric/mathematical content.
Write and run markdown-driven e2e tests for Relay. Covers fixture format, server/client code patterns, interaction DSL, snapshots, and running tests.
>- Performance best practices for Relay applications. Use when optimizing data fetching, reducing re-renders, configuring caching, or improving time to first meaningful paint. Covers query placement, @defer, pagination, fetch policies, garbage collection, fragment granularity, and server-side filtering. Companion to the relay-best-practices skill which covers correctness and architecture.
>- Best practices for writing idiomatic Relay code. ALWAYS use this skill when writing or modifying React components that use Relay for data fetching. Covers fragments, queries, mutations, pagination, and common anti-patterns. Use when you see `useFragment`, `useLazyLoadQuery`, `usePreloadedQuery`, `useMutation`, `usePaginationFragment`, `graphql` template literals, `react-relay` imports, or `__generated__/*.graphql` files. Also use when asked to explain Relay concepts, debug Relay issues, or review Relay code.
Complete API for Google NotebookLM - full programmatic access including features not in the web UI. Create notebooks, add sources, generate all artifact types, download in multiple formats. Activates on explicit /notebooklm or intent like "create a podcast about X
> Delegation mode for open-code-review (OCR). Instead of OCR calling an LLM endpoint, this skill instructs the host agent to perform the code review rule resolution. Use when the host agent should drive the review with its own LLM capabilities.
> Performs AI-powered code review on Git changes using the `ocr` CLI from alibaba/open-code-review. Use when the user asks to review code, review a pull request, review staged/unstaged changes, review a commit, or compare branches for code quality issues. Produces line-level review comments and can automatically apply fixes when requested. With appropriate review rules, can detect various types of issues including bugs, security vulnerabilities, performance problems, and code quality concerns.
> Delegation mode for open-code-review (OCR). Instead of OCR calling an LLM endpoint, this skill instructs the host agent to perform the code review rule resolution. Use when the host agent should drive the review with its own LLM capabilities.
> Performs AI-powered code review on Git changes using the `ocr` CLI from alibaba/open-code-review. Use when the user asks to review code, review a pull request, review staged/unstaged changes, review a commit, or compare branches for code quality issues. Produces line-level review comments and can automatically apply fixes when requested. With appropriate review rules, can detect various types of issues including bugs, security vulnerabilities, performance problems, and code quality concerns.
Bump the default Redis docker test image (redislabs/client-libs-test) in the shared DEFAULT_DOCKER_CONFIG and the CI matrix, then force-push the bump-test-image branch and open a PR against upstream. User-invoked only.
A comprehensive collection of Agent Skills for context engineering, harness engineering, multi-agent architectures, and production agent systems. Use when building, optimizing, evaluating, or debugging agent systems that require effective context management and reliable operating loops.
This skill should be used for advanced LLM evaluation: LLM-as-judge systems, direct scoring, pairwise comparison, rubric calibration, evaluator bias mitigation, confidence scoring, and automated quality assessment.
This skill should be used when modeling agent mental states with BDI concepts: beliefs, desires, intentions, RDF-to-belief transformations, rational agency traces, cognitive agents, BDI ontologies, and neuro-symbolic AI integration.
This skill should be used when long-running agent sessions need context compression, structured summarization, compaction, token-per-task optimization, or durable handoff summaries that preserve decisions, files, risks, and next actions.
This skill should be used for diagnosing and mitigating context degradation: lost-in-middle failures, context poisoning, context clash, context confusion, attention-pattern issues, and agent performance degradation caused by accumulated or conflicting context.
This skill should be used to explain or reason about the foundational concepts of context engineering: what context is, the anatomy of a context window, how attention mechanics work, the U-shaped attention curve, why context quality matters more than quantity, and the mental models needed to interpret every other context-engineering decision. Use this for conceptual explanation, onboarding, and background reading. Route operational work to the specialized skills: debugging attention failures goes to context-degradation, token-efficiency work goes to context-optimization, conversation summarization goes to context-compression, and project-shape decisions go to project-development.
This skill should be used for improving context efficiency: context budgeting, observation masking, prefix or KV-cache strategy, partitioning, token-cost reduction, retrieval scoping, and extending effective context capacity without lowering answer quality.
This skill should be used when building agent evaluation systems: deterministic checks, regression suites, multi-dimensional rubrics, quality gates, production monitoring, baseline comparison, and outcome measurement for agent pipelines.
This skill should be used when agent work needs file-backed context: durable scratchpads, tool-output offloading, just-in-time discovery, cross-agent handoff files, filesystem memory, or cleanup policies for context stored outside the prompt.
This skill should be used when designing autonomous agent harnesses: research loops, evaluation scaffolds, locked and editable surfaces, durable logs, novelty gates, pruning, rollback, PR preparation, and human approval boundaries.
This skill should be used when designing hosted or background agent infrastructure: sandboxed execution, remote coding environments, warm pools, session persistence, multiplayer collaboration, self-spawning agents, or Modal-style sandboxes.
This skill should be used when the user asks to \"share memory between agents\", \"KV cache compaction for multi-agent\", \"orchestrator worker context\", \"latent briefing\", \"reduce worker tokens\", \"cross-agent memory without summarization\", or discusses Attention Matching compaction, recursive language models with workers, or token explosion in hierarchical agents.
This skill should be used when writing, enhancing, or evaluating the launch prompt for a long-running autonomous agent or a parallel multi-agent orchestration attacking a hard problem: pseudo-formal task briefs that define terms and an exact success predicate linguistically, enumerate non-counting outcomes, set persistence rules with explicit stop and return conditions and effort floors, manage a diverse portfolio of parallel approaches with an approach registry and blocked-route bookkeeping, and gate the return on adversarial audit. Route agent topology and coordination protocols to multi-agent-patterns, runtime control surfaces and loop governance to harness-engineering, evaluator and quality-gate construction to evaluation, judge design to advanced-evaluation, and compaction or memory mechanics to context-compression and memory-systems.
This skill should be used for persistent semantic memory in agent systems: cross-session knowledge retention, entity tracking, temporal validity, graph or vector retrieval, memory consolidation, and memory benchmark selection. Route file-backed scratchpads to filesystem-context, handoff summaries to context-compression, and token-efficiency tactics to context-optimization.
This skill should be used when designing multi-agent systems that need context isolation, supervisor or swarm coordination, explicit handoffs, parallel execution, or a decision on whether multiple agents are justified.
Claude Skills — questions
Answers built from the skills we actually parsed.