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. 86 696 files from 2 113 authors, of which 68 413 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.
> Load this skill whenever you are planning, executing, or reviewing manual accessibility testing. Manual testing with real assistive technologies is essential — automated tools catch only ~30–40 % of WCAG issues. Absolutely always include keyboard-only testing and at least one screen reader test before marking a feature accessible. Under no circumstances skip forced colors mode testing for UI components.
> Load this skill whenever the project uses Mermaid diagrams — flowcharts, sequence diagrams, class diagrams, Gantt charts, or any Mermaid-rendered visualization. Under no circumstances render a Mermaid diagram without an accessible title, description, and text-based alternative. Absolutely always will be silently ignored) to every diagram.
> Load this skill whenever the project supports light/dark mode, colour theme switching, high-contrast mode, or responds to prefers-color-scheme. Under no circumstances hard-code colours that break in alternative themes. Absolutely always test colour contrast in both light and dark themes, and respect user OS-level colour preferences via CSS media queries.
Apply the Opquast Digital Quality Framework (245 rules, 14 categories) when building, reviewing, or auditing websites and web applications. Use for web development quality assurance, accessibility compliance, security hardening, privacy implementation, e-commerce best practices, and holistic digital quality checks.
> Load this skill whenever the project contains navigation components — primary navigation menus, dropdown menus, mega menus, breadcrumbs, pagination, mobile hamburger menus, or in-page jump navigation. Under no circumstances create navigation without proper landmark roles, keyboard support, and accessible labels. Absolutely always wrap navigation in <nav> with a unique aria-label.
> Load this skill whenever the project involves writing, editing, or reviewing content for a general audience, including UI copy, help text, error messages, documentation, and instructions. Under no circumstances use jargon, complex sentence structures, or unexplained acronyms without providing plain alternatives. Absolutely always target a reading level accessible to the broadest possible audience. Load alongside content-design/SKILL.md for all content work.
> Load this skill whenever the project includes print stylesheets, print media queries (@media print), or any content intended for physical printing. Under no circumstances omit print CSS that ensures readable, accessible printed output. Absolutely always hide decorative elements, expand link URLs, and maintain sufficient contrast and font sizing in print styles.
> Load this skill when building any web feature, reviewing architecture decisions, or evaluating JavaScript dependencies. Under no circumstances build features that break completely when JavaScript is unavailable or fails. Absolutely always start with semantic HTML, layer CSS enhancements, and add JavaScript as the final, optional layer. Prioritize resilience and universal access over cutting-edge features.
> Load this skill whenever the project contains SVG graphics — inline SVGs, external SVG files, SVG icons, SVG illustrations, or SVG-based data visualizations. Under no circumstances use SVG without proper accessible titles, descriptions, and ARIA roles where required. Absolutely always add <title> and <desc> to meaningful SVGs and set role="img" with aria-labelledby pointing to those elements. Also apply this skill whenever the project accepts untrusted or user-uploaded SVG content, which requires sanitization before rendering.
> Load this skill whenever the project must support speech input or voice control — dictation, "click by voice" grammars, Dragon NaturallySpeaking, Voice Control (iOS/macOS), Voice Access (Android), or any interface where users activate controls by speaking. Under no circumstances let an aria-label override a visible label without keeping the visible text intact and in order. Absolutely always ensure the accessible name contains the visible label, and load alongside keyboard/SKILL.md since speech tools commonly emulate keyboard and pointer input.
> Load this skill whenever the project contains HTML data tables (<table> elements). Under no circumstances use tables for layout purposes. Absolutely always include <th> elements with appropriate scope attributes, a <caption> or aria-labelledby, and ensure complex tables have headers associated with data cells. Apply these rules to every data table without exception.
> Load this skill whenever the project contains interactive UI elements that users touch, tap, click, drag, swipe, or gesture with — buttons, links, drag-and-drop interfaces, sliders, carousels, or custom touch interactions. Under no circumstances create touch targets smaller than 44×44 CSS pixels. Absolutely always provide pointer cancellation, single-pointer alternatives to gestures, and load alongside keyboard/SKILL.md since pointer and keyboard requirements are complementary.
> Load this skill before implementing a fix for a barrier that may originate in a shared component, design system, renderer, or external dependency rather than this project's own code. Decide whether the responsible fix is local, an existing installed capability, or an upstream contribution before writing a workaround. Absolutely always record any temporary local divergence with an owner and removal condition. Under no circumstances open, comment on, or submit anything in an external project without explicit human approval.
> Load this skill whenever the project contains tooltip components, hover- triggered informational popups, title attribute tooltips, or any content revealed on hover or focus. Under no circumstances create tooltips that are only triggered by hover without keyboard equivalent access. Absolutely always ensure tooltips are dismissible, persistent enough to read, and not the sole source of essential information.
> Load this skill whenever the project has personalization features, user preference controls, theme selectors, font size adjusters, motion toggles, contrast settings, or any user-configurable accessibility accommodations. Under no circumstances override or ignore user OS-level accessibility preferences without explicit user consent. Absolutely always persist user preferences, apply them immediately, and respect prefers-reduced-motion, prefers-contrast, and similar media queries.
Use when establishing branching strategies, implementing Conventional Commits, creating or reviewing PRs, resolving PR review comments, merging PRs (including CI verification, auto-merge queues, and post-merge cleanup), managing PR review threads, merging PRs with signed commits, handling merge conflicts, integrating Git with CI/CD, setting up git hooks (lefthook, captainhook, husky, pre-commit), or debugging hook-install failures in git worktrees. Not for creating releases (use github-release) or diagnosing BLOCKED/won't-merge PRs (use github-project).
REQUIRED for any task that involves operating a desktop application — opening apps, clicking buttons, typing into fields, pressing keys, scrolling, dragging, reading what's on screen, moving or resizing windows, or verifying state after an action. Always use the `agent-cu` CLI commands (open, snapshot, click, type, key, find, scroll, drag, batch, wait-for) instead of falling back to `open -a`, AppleScript, `osascript`, `xdotool`, `System Events`, or any other shell workaround — those can't read state back, don't verify, and are fragile across app updates. agent-cu is the canonical computer-use tool for controlling any macOS / Linux / Windows / Electron app via accessibility APIs. Trigger on prompts like "open Music and play X", "search for Y in Maps", "fill out this form", "compute in Calculator", "send a Slack message", "drag this file", "read what's in the current window", or anything where a human would click/type/look at a desktop app.
Explains Cypress tests (E2E and component tests), and answers questions about Cypress use and behavior. Use when the user asks to explain how a test works, explain how Cypress works, review or critique a test without writing code. Apply even when the user does not say 'Cypress' (e.g. 'explain this test'). Prefer the cypress-author skill when the user wants to create, fix, or update tests.
Creates, updates, and fixes Cypress tests (E2E/end-to-end and component tests). Use when the user asks to create tests, add tests, write tests, update tests, test this file/component, new spec, or fix a failing or flaky test. Apply even when the user does not say 'Cypress' (e.g. 'create tests for this file'). Prefer cypress-explain when the user only wants to explain or review tests without changing code.
Search and extract Cypress information from official documentation (docs.cypress.io, cypress.io); prefer LLM markdown under /llm/* and refuse unverified API or behavior claims.
Placeholder skill used only to smoke-test the eval framework's workdir-capture mechanism. Not a real skill — delete once a real code-gen skill exists.
Drive the cultivar CLI to test whether an agent skill improves behavior — scaffold tasks, run with/without the skill across Claude/Copilot/Gemini (locally or on Modal), grade against a rubric, and read the results.
Use when modernizing PHP code: PHP 8.1-8.5 features, PSR/PHP-FIG/PER-CS compliance, PHPStan/Rector/PHP-CS-Fixer/PHPat tooling, DTOs/enums/readonly/property hooks, type safety. Triggers: PHP modernization, type safety, PHPStan, Rector, PHP-CS-Fixer, enum, DTO, readonly, strict_types, property hooks, PHP 8.4, PHP 8.5.
>- Expert coding skill for the full MapTiler platform — Cloud REST APIs, MapTiler SDK JS (built on MapLibre GL JS), native mobile SDKs, on-premise infrastructure, and vector tile schemas. USE WHEN the user wants to add a map to a web or mobile app, show locations or routes, display geographic data, build a store locator, create data visualizations on maps, add geocoding or address search, do reverse geocoding, look up elevation, do IP geolocation, fetch weather data, transform coordinates between CRS/EPSG, embed static map images, work with vector tilesets (Planet v4, Buildings, Contours, Outdoor, Ocean, Landcover, Cadastre), write MapLibre style expressions or data-driven styling, render 3D terrain, globe view, or 3D buildings extrusion, use satellite imagery, add markers, popups, heatmaps, or clustering, integrate maps in React, Vue, Svelte, Angular, Next.js, Leaflet, OpenLayers, Cesium, or deck.gl, build native maps on iOS (Swift), Android (Kotlin), Flutter, or React Native, self-host with MapTiler Server or generate tiles with MapTiler Engine CLI, or upload/manage tilesets via the Admin API. Also USE WHEN the user mentions MapLibre GL JS — the SDK extends MapLibre with built-in cloud services, helpers, and session billing.
>- Upload local images to a GitHub PR and embed them in the description or comments. Use when asked to "attach screenshots to PR", "add images to PR", "upload test results to PR", "embed screenshots in PR description", "add before/after images to PR", "attach UI screenshots", "show test results in PR", "add visual evidence to PR", or any request involving images and PRs. Always use this skill when the user wants to visually document changes in a pull request, even if they don't use the word "upload" — phrases like "put the screenshot in the PR" or "show the image in the PR" should trigger this skill. Prefers Chrome DevTools MCP (most stable) as the browser automation backend, falling back to Playwright MCP or agent-browser only when Chrome DevTools MCP is unavailable.
Deterministic workflow to find and export full podcast transcripts as cleaned TXT files from YouTube URLs, episode webpages (including Xiaoyuzhou), Apple Podcasts title search, X/Twitter links, direct audio URLs, or plain episode titles. Use when users ask for 逐字稿/文字版/transcript/txt and want minimal trial-and-error.
>- Local open-source Agent Skill for authorized web application, API, browser, business-logic, and supporting server-integrity penetration testing. Use for scoped OWASP WSTG, ASVS, and API Security assessments; authenticated and multi-role validation; attack-surface mapping; bounded DAST; evidence-backed findings; coverage tracking; CVSS/risk triage; and delivery-ready reports. Do not use for phishing, malware, lateral movement, wireless, physical, or unrelated broad infrastructure testing. Run security tools only through the bundled Docker launcher with explicit authorization and scope controls.
토큰 예산 모니터. 컨텍스트 사용량 감시 및 컴팩트 방어 시스템 지원. Internal skill — not user-invocable.
스냅샷 저장 + /compact 안내. 단일 명령으로 완료.
All-in-one fullstack dev engine. /aura: 46 modes (build/fix/clean/deploy/review/spec/lore/ax/experiment/payment/debug/qa/orchestrate/escalate+), 6-layer security with 32 hooks, tiered models (ZERO/ECO/PRO/MAX), 8 languages, 16 specialized agents, SPEC/EARS/TRUST5/XLOOP/RALF/Autopus absorbed. ~55% token savings.
| validation with JSON-LD generation, internal linking analysis, Core Web Vitals, page speed optimization, crawl budget analysis, cannibalization detection, international SEO. Uses firecrawl for crawling/scraping, curl for HTTP header checks.
| Perplexity citations, ChatGPT mentions. Structured data for AI consumption, FAQ and entity optimization, brand authority signals, brand SERP management. Uses firecrawl to analyze AI search results and competitor AI visibility.
| optimization, heading structure, keyword density, SERP preview, content readability, featured snippet optimization, content gap and decay detection, pre-publish checklists. Uses firecrawl to scrape pages for analysis.
| generation, monthly SEO reporting framework, toxic link identification, link opportunity scoring, and unlinked mention discovery. Uses firecrawl to research competitor link sources and find outreach targets.
| NAP consistency checks, local citation audits, review response templates, local keywords. Uses firecrawl to scrape competitor GBP profiles and local SERPs.
| Revenue-focused keyword research and strategy for SEO campaigns. Handles keyword discovery, clustering, search intent mapping, difficulty assessment, competitor gap analysis, topical authority mapping, SERP feature analysis, competitor content strategy reverse engineering, and programmatic SEO template generation.
| 抖音视频解析、博主视频抓取/转录/运营分析/写入飞书。 触发词：解析抖音、抖音视频、抓取视频、博主视频、创作者视频、douyin、抖音解析、飞书多维表格 子命令：
Structure, classify, and write documentation using the Diátaxis framework. Use when writing docs, README files, guides, tutorials, how-to guides, API references, or organizing documentation architecture. Also use when asked to improve documentation, restructure docs, decide what type of doc to write, or classify existing content. Covers tutorials, how-to guides, reference, and explanation.
Use when reviewing code quality, asking whether a refactor or design is good, looking for code smells, or evaluating architecture tradeoffs. Identifies shallow interfaces, invalid state models, unclear boundaries, hidden effects, weak failure contracts, over-mocking, over-abstraction, compatibility glue, and clean-looking code that preserves bad models.
Use when reviewing PRs, simplifying over-engineered code, judging architecture, or renaming unclear concepts — inline fake helpers, delete meatless ceremony, rename lying names, merge over-split files, reject premature abstraction, say no to speculative config/modes/layers, then end with the smallest safe next change. Triggers when code is too fancy, too abstract, too clever, too many files/helpers/layers, or too well-factored but painful to change. Embody Grug brain: complexity very bad, small words, no consultant speak, no hard pivot to opposite dogma.
Use when creating or iterating staged planning artifacts for a complex feature: design discussion, structure outline, final executor plan, or supporting research/research questions. Also use when designing before coding, breaking work into vertical slices, or deepening a high-value roadmap item, NNN improve plan, architecture candidate, or HumanLayer-style task.
Use when building or reviewing frontend UI — dashboards, admin panels, landing pages, marketing sites, web apps. Drives domain-specific design decisions (typography, color world, layout, CSS token naming, depth and spacing systems) instead of generic AI defaults; routes to app.md (product/data UIs) or marketing.md (public/creative pages) by context.
Dude, come on. You write at the density of your own thinking and leave the reader to unpack it. Apply whenever explaining anything to a human — not just end-of-run summaries, every message.
Convert Docker Compose files to Coolify templates. Use when creating Coolify services, converting docker-compose.yml for Coolify deployment, working with SERVICE_URL/SERVICE_PASSWORD magic variables, or troubleshooting Coolify compose errors.
Use when the user asks to create, generate, visualize, or turn material into a standalone HTML artifact, self-contained or single-file .html report, interactive explainer, interactive illustration or visualization, visual walkthrough or handoff, or HTML presentation or slide deck. Handles source-grounded codebase and architecture, feature, PR or diff, implementation recap, incident timeline, option comparison, causal, and data-report explanations. Not for prose-only analysis or reviews, production web apps or dashboards, websites, HTML email, or ordinary frontend/UI implementation.
Use when answering complex questions about a codebase that require exploring multiple areas or understanding how components connect - coordinates parallel sub-agents to locate, analyze, and synthesize findings
Use when optimizing CLAUDE.md, AGENTS.md, custom commands, or skill files — diagnose the concrete failure first, then apply current documented Anthropic best practices (explicit instructions, context/motivation, examples, output and verbosity control, thinking/effort, CLAUDE.md size and skill-description rules) instead of inventing improvements. Triggers when a prompt isn't followed, a skill won't activate, CLAUDE.md is too long or ignored, or migrating prompts to current Claude models.
Use when evaluating designs, reviewing code, or refactoring - measures success by total code in the final codebase, not effort to get there. Bias toward deletion.
Survey a codebase as a senior advisor and turn the highest-value findings into implementation plans for other agents to execute — strictly read-only on source code, never implements anything itself. Use when asked to audit a codebase, find improvement opportunities (bugs, security, performance, test coverage, tech debt, architecture, migrations, DX), suggest features or roadmap direction, or generate handoff plans for another agent to implement.
Jujutsu (jj) — the Git-compatible version control system. Activate ONLY when a .jj/ directory is present in the project or when jj/jujutsu is explicitly mentioned. Do NOT activate for plain git repos without .jj/. Use for any VCS operations in jj-managed projects: commit, push, pull, branch, bookmark, rebase, squash, merge, diff, log, status, working copy, change ID, revset, fileset, template, configuration, workspaces.
Use when turning a roadmap, repo priorities, architecture priorities, chosen opportunities, accepted feature outlines/plans, or “roadmap to plans” request into grouped improvement plan batches for future executors. Writes README.md indexes, 001-*.md/NNN-style plans, optional memo-*.md files, verification gates, drift checks, STOP conditions, rejected approaches, and executor handoff notes.
Build evidence-backed software/product roadmaps from repo state, tickets, ideas, audit findings, or user goals — prioritize and sequence work across Now/Next/Later, milestones, dependencies, risks, and handoffs. Use when asked for a roadmap, feature roadmap, technical roadmap, release plan, milestone plan, backlog prioritization, sequencing, what to build next, or to turn improve/ideate/brainstorm/design-discussion outputs into an execution sequence. Not for implementing code or writing PR-level plans.
> Reviews Svelte components for idiomatic patterns, identifies anti-patterns carried over from React/Vue/Svelte 4, and suggests Svelte 5 refactorings. Use when writing or reviewing Svelte components, asking "is this idiomatic", "Svelte way", doing Svelte 5 migration, or slot-shaped APIs, lifecycle-driven code, imperative DOM wiring, immutable-update ceremony, context value replacement, shadcn-svelte form structure, Field.* components, bits-ui form controls, or component APIs that hide ownership. This is the general-purpose entry point for Svelte component review; delegates to sveltekit for routes/load/actions/server concerns and to focused references for details.
> Mental-model reset for Salsa, the incremental computation framework for Rust. Use when building or reviewing Salsa databases, tracked functions, input/ tracked/interned structs, query pipelines, accumulators, cancellation, durability, LSP integration, memory management, cycles, or production Salsa revisions, backdating, red-green algorithm, WillExecute, DidValidateMemoizedValue, Cancelled, returns(ref), no_eq, lru, cycle_fn,
> Mental-model reset for Rust. Use when writing or reviewing Rust code to shift from "it compiles" to "thinks in Rust." Triggers on Rust code review, "is this idiomatic", borrow-checker errors, API design, domain modeling, ownership, lifetimes, errors, traits, async/Tokio, unsafe, serde, FFI, tests, performance, Cargo structure, .rs files, Cargo.toml, rustc diagnostics, clippy findings, Result/Option, thiserror vs anyhow, newtype, typestate, enum vs trait, dyn Trait, Send/Sync, Pin, Miri, PyO3, napi-rs, cxx, UniFFI, wasm-bindgen, serde attributes, or feature unification.
Use when authoring, creating, refining, or troubleshooting agent skills — scaffold SKILL.md and frontmatter, write and optimize the trigger description, structure the body with progressive disclosure, validate structure, and test or debug activation. Also when building a new skill from scratch, when a skill won't trigger, loads incorrectly, or the agent ignores it entirely. Use when a skill misbehaved in the current session and needs adjustment based on learnings.
Use when a user asks “what should I work on in this repo?”, “what’s worth doing next?”, repo audit, tech-debt priorities, architecture priorities, old-plan reconciliation, or repo-grounded opportunity discovery. Produces .agents/ROADMAP.md with generated opportunities, user-seeded ideas, Now/Next/Later sequencing, rejected/not-now items, and next-artifact recommendations. Not for standard product/release roadmaps; if multiple repos are requested, create one roadmap per repo.
Use when writing, reviewing, or rewriting user-facing error messages, validation messages, form errors, empty/error states, auth errors, failure notifications, retry/support copy, CLI errors, or API errors humans will read. Helps make errors specific, actionable, non-blaming, accessible, and safe without leaking sensitive details.
Use when authoring an agent skill that wraps a command-line tool — covers hands-on tool exploration, required vs. recommended sections, installation/usage structure, trigger-rich descriptions, task-grouped commands, progressive disclosure, and a pre-publish checklist. Triggers for CLI / command-line / terminal / shell-command tools and binary wrappers; for review, run the Checklist section.
> Mental-model reset for SvelteKit apps. Use when writing or reviewing routes, layouts, load functions, form actions, remote functions, hooks, auth, cookies, endpoints, redirects, errors, SSR, progressive enhancement, or app-level data flow. Triggers on SvelteKit, +page, +layout, +server, +page.server.ts, +layout.server.ts, hooks.server.ts, load, actions, fail(), redirect(), error(), cookies, locals, route groups, protected routes, sessions, form actions, enhance, remote functions, command(), query(), form(), getRequestEvent(), SSR, hydration, and serialization. Use svelte5 for component-level runes, snippets, accessibility, actions, transitions, and component API review.
Claude Skills — questions
Answers built from the skills we actually parsed.