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.
>- Use this skill BEFORE drafting any agentic primitive module (skill, persona scoping file, scope-attached rule file, orchestrator workflow) or when refactoring an existing one. Activate whenever the task asks to design, restructure, or critique an agentic module across any agent harness (Claude Code, Copilot, Cursor, OpenCode, Codex), or when the task asks to make a workflow cost-effective, route model calls by capability, design for cache discipline, prune token spend, or pick a model class. This skill drives an 8-step disciplined design process whose output is mermaid diagrams + an interface sketch + a persisted plan (including a cost projection) that the calling thread (or a coder persona it loads) then turns into natural-language modules. Do not skip to natural-language drafting before the design artifacts exist.
Design, build, redesign, critique, audit, and refine frontend interfaces with strong visual direction and production-ready UX. Use for websites, landing pages, dashboards, application UI, components, forms, onboarding, empty states, responsive behavior, accessibility, typography, color, layout, motion, UX copy, or when an interface feels generic, bland, cluttered, inconsistent, or unfinished. Do not use for backend-only or non-UI tasks.
A live visual Kanban board and continuity layer for long-running agentic tasks. Nobody wants to read a markdown plan or stare at raw HTML while an agent grinds for an hour, so Plandeck turns the plan into a board that organizes itself. Use it when a task is multi-step, long-running, or needs visual planning. Break the work into cards, declare which card depends on which, and Plandeck computes the critical path, auto-promotes cards to Ready as their dependencies clear, rolls up story-point estimates into an honest percent complete, and names the one next action. Plans, observed transitions, and last-known-good snapshots stay as plain files on disk, so they survive /clear and context resets. After a reset, run plandeck next to recover the single next move and its recent history. If the plan stops parsing, run plandeck doctor before using git. Renders a live board in the browser over SSE. Triggers on plan a project, break down a task, kanban board, task board, visual plan, long-running agent, agentic task, track dependencies, critical path, story-point estimates, what is next, mission journal, recover plan, plandeck.
| Modern tidyverse patterns, style guide, and migration guidance for R development. Use this skill when writing R code with dplyr, reviewing tidyverse code, updating legacy R code to modern patterns, or enforcing consistent style. Covers native pipe usage, join_by() syntax, .by grouping, pick/across/reframe operations, tidy selection, stringr patterns, naming conventions, spacing, and migration from base R or older tidyverse APIs.
| Use multiple sub-agents to fetch and display news from Posit, including blog posts, podcast episodes, videos, and events. Use when the user wants to see recent Posit news, blog updates, podcast episodes, videos, or company announcements.
| R performance profiling, benchmarking, and optimization strategies. Use this skill when code is running slowly, comparing alternative implementations, deciding between dplyr/data.table/base R, or implementing parallel processing. Covers profvis and bench usage, performance workflow, parallel processing with in_parallel(), data backend selection, modern purrr patterns (list_rbind, walk), and common performance anti-patterns to avoid.
| Building robust R packages with modern tidyverse patterns. Use this skill when creating or maintaining R packages, designing APIs, choosing dependencies, implementing input validation, writing error messages, or deciding between internal and exported functions. Covers dependency strategy, tidyverse API design patterns, validation approaches, error handling with cli/rlang, testing levels, and documentation priorities.
|
| Tidy evaluation and programmatic tidyverse patterns using rlang. Use this skill when writing functions that accept column names as arguments, building tidyverse-compatible APIs, or working with data-masking and injection operators. Covers embracing with {{}}, injection (!! and !!!), dynamic dots, .data/.env pronouns, name injection with glue syntax, bridge patterns between selection and data-masking, and package development with rlang.
| Type-stable vector operations and custom vector classes using vctrs. Use this skill when building R packages with custom types, need guaranteed output types regardless of input values, implementing consistent coercion/casting rules, or creating vector classes that work seamlessly with data frames. Covers when to use vctrs vs base R, building custom vector classes, coercion methods, and testing vctrs classes.
Refactor discipline for existing codebases. Enforces scope control, migration safety, compatibility, observability, and tests to keep refactors reviewable and low-risk.
Use when designing, implementing, or reviewing Android deep links, web links, and App Links in KMP projects — intent-filter design, host verification, manifest scope, and assetlinks.json configuration.
Use when implementing or reviewing KMP data layers, including repositories, data sources, source-of-truth design, API exposure, conflict resolution, error handling, and main-safe data operations.
Use when reviewing or designing Gradle build structure for KMP projects — shared build logic, convention plugins, version catalogs, Android KMP plugin usage, source-set configuration, and module dependency hygiene.
Use when designing, implementing, or reviewing platform-specific integrations in KMP projects, including source-set placement, hierarchical sharing, expect/actual usage, platform API access, and shared-to-native abstraction boundaries.
Use when reviewing implemented Kotlin Multiplatform / Compose Multiplatform code for architecture consistency, business-logic placement, state correctness, concurrency, Compose quality, design-system usage, security, performance, resilience, and maintainability.
Use when reviewing KMP architecture, feature proposals, PR structure, layer boundaries, state-holder design, Android entry-point discipline, source-set placement, modularization, and long-term maintainability in Kotlin Multiplatform / Compose Multiplatform projects.
Use when designing, implementing, or reviewing navigation in Compose Multiplatform projects — route modeling, back stack ownership, argument passing, NavOptions, conditional flows, deep links, and adaptive navigation UI.
Use when diagnosing and fixing bugs in a Kotlin Multiplatform project. Focus on root-cause analysis, minimal safe fixes, KMP correctness, UI/state/data/persistence/concurrency issues, and regression prevention.
Use when implementing or extending a feature in a Kotlin Multiplatform project. Provides pre-coding inspection, KMP source-set discipline, state pipeline design, architectural defaults, security/performance guardrails, and implementation rules. Forward-looking only — not a review skill.
Use when designing, implementing, or reviewing tests in KMP projects — unit tests, instrumented tests, Compose Multiplatform UI tests, test doubles, test strategy, stability, performance, and screenshot testing.
Use when designing, reviewing, or refactoring module boundaries in KMP or Android projects — feature, data, app, and common modules, dependency direction, visibility control, and granularity.
Use when designing, implementing, or reviewing adaptive Compose UI for KMP or Android projects — window-size layouts, adaptive navigation, canonical layouts, multi-window support, and resource strategy.
Use when designing, implementing, or reviewing shared UI in Compose Multiplatform projects, including state-driven architecture, composable decomposition, layout/modifier discipline, adaptive behavior, and previewable shared UI in common source sets.
Use when choosing, implementing, or reviewing state-holder patterns in a KMP project — ViewModel, shared presenter, MVI, or StateFlow-in-common — including effect handling, UiState modeling, and testability.
| Build autonomous AI agents with Claude Agent SDK. TypeScript v0.2.141 | Python v0.2.82. structured outputs, and sessions. permissions/hooks, using structured outputs, troubleshooting SDK errors, or working with subagents.
This skill should be used when the user wants Claude Code to act purely as a manager/architect while Gemini CLI does all the coding work. Claude Code drives Gemini like an intern - issuing tasks, reviewing output, requesting fixes - but never writes code itself. Use when user says "manage gemini", "architect mode", "drive gemini", or wants to delegate all implementation to Gemini.
This skill is for interacting with Anki through AnkiConnect, and should be used whenever a user asks to interact with Anki, including to read or modify decks, notes, cards, models, media, or sync operations.
Design and author Hermes Workflows with typed inputs/outputs, agent/bash/ask/parallel/pipeline/goal primitives, Review Queue gates, artifacts, and verification receipts. Use when creating or modifying workflow definitions.
Guided tour of changes or codebase - explains how things work conceptually rather than listing changes mechanically. Use anytime you're asked to explain, review, walk through, or summarize work, branch changes, or codebase architecture.
Turns a photo of a person into a short 8-bit pixel-art video via a two-step pipeline. Gemini stylizes the photo as an 8-bit still, then Replicate's seedance-2.0 animates that still into an MP4. Use when the user supplies a portrait photo and asks for an "8-bit video", "pixel art animation", or "retro video game version" of themselves. Trigger even if they only mention one of the two steps.
>- Draft maintainer replies to GitHub PRs and issues in the user's voice. Use when the user asks to reply, respond, comment on, or review a PR/issue, or when drafting feedback for contributors. Handles approvals, change requests, closures, and issue triage. Copies result to clipboard.
> here.now lets agents publish websites and store private files in cloud Drives. Use Sites to publish HTML, documents, images, PDFs, videos, and static files to live URLs at {slug}.here.now or custom domains. Use Drives as private cloud folders where agents can store files (documents, context, memory, plans, assets, media, research, code, etc), share them with other agents, and continue across sessions and tools. Use when asked to "publish this", "host this", "deploy this", "share this on the web", "make a website", "put this online", "create a webpage", "generate a URL", "build a chatbot", "save this to my Drive", "store this for later", "write this to cloud storage", "share a folder with another agent", or "use my here.now Drive".
Draft a goal+rider document pair to brief the next agentic turn on a project. Two documents — a ≤4000-char goal (the spine) and an unbounded rider (the prescriptive detail with eleven phases and depth-tests-first discipline). Run when user says "draft a goal", "new goal", "write a goal+rider", "goal+rider for the next agentic turn", "rider for X", or anything in the shape of "brief the next agent on Y".
Apply rich formatting to Notion pages - toggles, callouts, headers, and styled text. Use when creating or formatting Notion documents via the Notion MCP server.
SpecStory Lore - mine your SpecStory coding histories (any agent - Claude Code, Codex, Cursor, Gemini, and more) into a persistent corpus, surface your reproducible workflows with corroborated evidence, and interactively forge the chosen ones into skills installed across all your agent harnesses. Use when the user wants to turn past AI coding sessions into reusable skills, asks "what could I make into a skill", "mine my lore", "forge skills from my history", or points at a .specstory/history directory.
Use when you have an idea for a data story and want a publication-quality chart back. The agent finds an authoritative public dataset, drafts three chart-type variants in parallel, picks the strongest, then iterates against a design checklist and a chart-design evaluator until the chart actually carries the story.
Use when the user wants to design, redesign, shape, critique, audit, polish, clarify, distill, harden, optimize, adapt, animate, colorize, extract, or otherwise improve a frontend interface. Covers websites, landing pages, dashboards, product UI, app shells, components, forms, settings, onboarding, and empty states. Handles UX review, visual hierarchy, information architecture, cognitive load, accessibility, performance, responsive behavior, theming, anti-patterns, typography, fonts, spacing, layout, alignment, color, motion, micro-interactions, UX copy, error states, edge cases, i18n, and reusable design systems or tokens. Also use for bland designs that need to become bolder or more delightful, loud designs that should become quieter, live browser iteration on UI elements, or ambitious visual effects that should feel technically extraordinary. Not for backend-only or non-UI tasks.
>- Work inside a running marimo notebook's kernel — execute code, create cells, and build a notebook as an artifact. Use when the user wants to start a marimo notebook or work in an active marimo session.
Perform mutation testing on the codebase. Introduces deliberate bugs one at a time, checks whether the test suite catches each one, and reports on test suite gaps. Optionally implements missing tests.
Refine a prompt by interviewing the user's intent from multiple angles, generating multiple variations at different magnitudes of change, and scoring each against an editorial rubric defined before the refinement starts.
Imagine future bug post-mortems for the codebase. Identifies fragile code, implicit assumptions, and likely failure modes by writing realistic incident reports for bugs that haven't happened yet.
Plan new software projects by decomposing the goal into MVP tasks, researching frameworks and libraries with subagents, and preferring opinionated prebuilt solutions over bespoke complexity. Use when starting a new project, scoping an idea, choosing a stack, or producing an implementation plan for a single-user MVP.
| How to build high-quality Remotion animated videos for social media (square 1080×1080 and vertical 1080×1920). Use this skill whenever the user asks to create, build, fix, or improve a Remotion video, animated scene, social media animation, motion design, kinetic typography, talking-head integration, scene pacing, or any motion-design work in a Remotion project. Also trigger when the user mentions scene components, animation timing, frame extraction, ease curves, or motion primitives. If you're about to write a Scene*.tsx file, read this skill first — the difference between a good and bad scene is in the approach, not the code. For re-editing existing footage into TikTok / Shorts / Reels short-form vertical with running captions and jump cuts, see the `tiktok-shorts-edit` skill instead.
Build, extend, AND query a persistent LLM-maintained wiki for any research topic. Conversational entry point that routes between four modes — query (read-only Q&A against existing research with optional Q&A save-back), init (new topic ingest), append-deep (add sources to existing topic via short rounds), and append-trusted (add a single user-vouched file to existing topic). Ingests from the Second Brain (Obsidian + Readwise + NotebookLM + GitHub repos + web seeds + user-dropped PDFs) and maintains a wiki layer (per-source pages, entities, concepts, comparisons, overview, synthesis, open questions, contradictions). Use for any research interaction — first-time research on a topic, "what do I have on X", "load my research on Y", "add this PDF to my research", "deep dive on Z", "pull together my notes on Y", "extend my research with this file". Trigger on the phrases above plus "search my research", "use my research", "find sources about X".
Use this skill any time you are opening a PR to ship code or the user tells you to "ship it". It explains how to write PR bodies effectively and follow the style guide.
Analyzes threads for friction points where the model struggled or user corrected it. Produces actionable improvements for AGENTS.md, skills, tools, and codebase. Use when asked to review a thread, do a postmortem, or analyze what went wrong.
Zinsser-first plain writing style for any writing or editing task. Invoke before creating, editing, critiquing, rewriting, outlining, prompting, or polishing prose, docs, posts, proposals, teardown notes, social posts, emails, prompts, or skill instructions.**
Audit try/except blocks for overly broad scope, by-catch risk, and catches of built-in exceptions that should be conditional checks. Tightens each block so the try covers only the operation that can actually fail.
Draft or revise any kind of writing so it is clearer, better structured, and more effective for its audience. Use for essays, emails, memos, articles, narratives, speeches, social posts, marketing copy, personal writing, documentation, technical writing, reports, proposals, and mixed-format prose while preserving meaning and facts.
Use when navigating Wikipedia inside the split-pane extension—finding articles from a topic or phrase, teaching or routing the user toward articles, choosing what to explore next, Wikimedia REST or Action APIs with paging, or sending message_parent url_change (optional section `#fragment` on the same wiki). Use for Wikipedia search, summaries, links/backlinks, or updating the mirrored page URL.
Use when a user wants an agent to summarise every video in their YouTube Watch Later playlist, publish one secret GitHub gist per summary with gh, and return channel/title/gists.sh summary links. Browser-tool agnostic; assumes the agent can operate the user's logged-in browser/session.
识别并消除中文 AI 写作的典型痕迹——套话、排比三件套、名词化、抽象主语、金句收尾、总分总八股——让文本读起来像有人在说话，而不是 AI 在生成。适用于公众号、小红书、知乎、公文、学术摘要、产品文案、邮件等所有中文长短文写作场景。
Control the user's real Safari browser on macOS using AppleScript and screencapture. This skill should be used when the user asks to interact with Safari, browse websites, read web pages, automate browser tasks, take screenshots of web content, or when any task would benefit from seeing or interacting with what's in their browser. Triggers on keywords like "safari", "browser", "web page", "open tab", "screenshot the page", "read this site", "browse", "click on", "fill in the form".
Use when searching academic papers, looking up citations, finding authors, or getting paper recommendations using the Semantic Scholar API. Triggers on queries about research papers, academic search, citation analysis, or literature discovery.
Implements Syncfusion .NET MAUI Accordion (SfAccordion) - a vertically collapsible panel with stacked headers for expanding/collapsing content. Use when working with accordions, collapsible panels, expandable lists, employee lists with details, or FAQ sections in .NET MAUI applications. Covers AccordionItem configuration, expand modes, and grouped content display.
Implements Syncfusion .NET MAUI Busy Indicator (SfBusyIndicator) for showing loading states, data processing, and app activity indicators. Use when displaying loading indicators, busy animations, activity spinners, or processing feedback in .NET MAUI apps. Covers busy indicator setup, animations, and visual feedback during long-running operations.
Implements and configure Syncfusion .NET MAUI Autocomplete (SfAutocomplete) control for intelligent text input with suggestions. Use when implementing autocomplete, autosuggest, type-ahead search, smart search, or filtered dropdowns in .NET MAUI applications. Covers data binding, filtering modes, custom search logic, AI-powered search, multi-selection with tokens, and UI customization.
Implements Syncfusion .NET MAUI AI AssistView (SfAIAssistView) for AI-powered interactive chat interfaces. Use when working with AI chat interfaces, AI AssistView, SfAIAssistView, conversational UI, or chat with AI responses. Covers integrating AI services, creating chat UIs, implementing conversation flows, managing AI requests/responses, and displaying AI suggestions.
Implements Syncfusion .NET MAUI Backdrop Page (SfBackdropPage) with back layer and front layer surfaces. Use when working with backdrop pages, SfBackdropPage, back layer, front layer, or reveal/conceal animations. Covers backdrop navigation patterns, header icons, corner shapes, reveal height, layer state events, and liquid glass effect.
Claude Skills — questions
Answers built from the skills we actually parsed.