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. 79 870 files from 1 769 authors, of which 62 217 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.
Design reduced-motion alternatives for websites and apps. Use for prefers-reduced-motion, Motion useReducedMotion, CSS media queries, disabling parallax, replacing large movement, simplifying scroll scenes, preserving state feedback, accessibility, vestibular-sensitive animation, and motion QA.
Design non-generic website section layouts. Use when a page needs alternatives to card grids, bento overuse, generic feature blocks, repetitive centered sections, bland stat strips, or template-like section sequencing.
Run responsive visual QA and polish for websites and apps. Use after building or editing any frontend to inspect desktop, laptop, tablet, and mobile widths; fix typography, spacing, overlaps, media crops, interactions, motion, forms, canvas rendering, accessibility, and final build quality.
Discipline React state, derived data, effects, refs, reducers, context, and event handlers. Use when components have duplicated state, unnecessary useEffect, prop-to-state syncing, stale closures, event logic in effects, external subscriptions, DOM integration, network sync, or complex UI state.
Run technical SEO QA for websites. Use for metadata, titles, descriptions, canonical URLs, robots, sitemap, Open Graph, structured data, heading structure, internal links, image alt, crawlability, noindex mistakes, redirects, JavaScript-rendered content, and launch readiness.
Create token-driven Tailwind and CSS variable systems for premium websites. Use for color tokens, typography tokens, spacing rhythm, radius, shadows, gradients, surfaces, responsive constraints, dark/light modes, and avoiding random utility-class styling.
Design surface, shadow, border, material, radius, glass, elevation, overlay, divider, and depth systems for premium websites and apps. Use when cards, panels, modals, nav, product UI, dashboards, luxury sections, or editorial layouts need polished material hierarchy without generic glassmorphism or heavy shadows.
Build responsive Tailwind CSS layouts for premium websites and apps. Use for breakpoints, mobile-first layout, grids, flex, spacing, container widths, aspect ratios, responsive typography, media crops, nav adaptation, dashboard density, and preventing mobile stacking from looking generic.
Create testimonial and proof systems for websites. Use for testimonials, reviews, customer quotes, logo walls, metrics, press quotes, case-study excerpts, ratings, social proof, proof strips, trust sections, and copy that must be credible, approved, and specific.
Use shadcn/ui, Radix-style primitives, and lucide-react icons without producing generic default UI. Use for dialogs, menus, accordions, tabs, forms, buttons, toolbars, icons, inputs, and app controls that need accessibility and polished custom styling.
Direct website imagery, video, generative visuals, product renders, screenshots, gallery crops, hero media, thumbnails, and visual assets. Use when a site needs real or generated media rather than generic gradients, stock-like backgrounds, placeholder images, or uninspected crops.
Compose UI screenshots inside website layouts. Use for product sections, feature blocks, app showcases, case studies, dashboards, mockup stacks, detail crops, callout overlays, annotation systems, responsive screenshot art direction, and avoiding generic SaaS screenshot-card sections.
Use after frontend changes or before delivery to run rendered visual QA with Playwright/browser screenshots, viewport checks, console/network checks, overflow detection, canvas/media verification, before/after comparisons, and responsive polish review.
Inspect, test, and refine frontend visual quality before delivery. Use after building or editing websites, landing pages, portfolios, dashboards, games, interactive tools, cinematic sites, luxury sites, or any UI where Codex should run a second polish pass for responsive layout, typography, spacing, hierarchy, motion, accessibility, and browser-rendered correctness.
Use for premium frontend, website, app UI, landing page, dashboard, redesign, image-to-code, or visual-polish work that needs clearer design intent, adjustable visual direction, motion discipline, less generic output, and a final preflight check before handoff.
Research and translate website references into reusable design constraints. Use when the user mentions Viktor Oddy, Squarespace, Raycast, Linear, Vercel, Framer, Awwwards, Codrops, luxury sites, cinematic websites, product-led sites, portfolios, or any external web design reference that should influence a build.
Prompt generated imagery for premium websites. Use when Codex needs hero images, product scenes, editorial visuals, backgrounds, portraits, venue imagery, campaign art, texture assets, mockups, or image-generation direction for luxury, cinematic, Squarespace-polished, Viktor Oddy-adjacent, or non-generic site visuals.
Define vague website taste words as concrete design decisions. Use when prompts include premium, luxury, cinematic, modern, editorial, minimal, polished, brutalist, avant-garde, classy, clean, high-end, professional, Squarespace-like, Framer-like, or any subjective visual adjective that Codex must translate into layout, typography, color, media, and motion rules.
Create a website blueprint before coding. Use for new sites, redesigns, image-to-site work, premium landing pages, portfolios, brand sites, product sites, and any frontend project where Codex should define pages, sections, assets, tokens, layout, motion, and QA criteria before implementation.
Choose and enforce a precise art direction for modern websites. Use when the user asks for beautiful, premium, luxury, cinematic, editorial, Squarespace-like, Viktor-style, Framer-like, Raycast-like, Linear-like, Vercel-like, portfolio, product, service, agency, commerce, or brand websites.
Apply strict website-building operating rules for any frontend, website, landing page, portfolio, product site, luxury site, Squarespace-like site, modern SaaS/devtool site, or UI build. Use when Codex must inspect first, avoid generic design, explain planned files, run local verification, perform a second visual polish pass, and report tests honestly.
>- Skill Base server deployment guide. Covers starting the Skill Base server (npx skill-base), Docker configuration, port mapping, SQLite database backup, and platform capabilities (collections, tags, GitHub import). For deploying and operating the Skill Base platform itself only.
>- The official Skill Base CLI client. Use the `skb` (Skill Base CLI) command to search, install (single skill or collection), update, delete, publish, and import-from-GitHub skills from Skill Base, as well as configure skb. Triggered when users say "publish skill to skill base", "install collection", "import skill from github", "download/update/delete skill from skill base", "configure skb", "am I logged in", "check skb login", or "configure skill-base-cli".
>- Plan and generate controllable Seedance video using Seedream 5.0 Pro storyboards and Seedance 2.0 today, with a Seedance 2.5 route when available. Use for consistent people, products, objects, food, or scenes; storyboard-to- video; reference-to-video; first-and-last-frame image-to-video; extensions; and Atlas Cloud media generation.
Run external coding agents (Codex, Claude Code, OpenCode, native Grok Build, Gemini) as independent reviewers, repository researchers, or single-agent implementers. Use for multi-model opinions and code review, evidence-backed exploration of local or remote repositories, full-access delegation, steerable long-running work, or reattaching to delegated runs. Not for simple questions answerable directly from docs or the current codebase.
8-step disciplined bug-fix protocol that treats every production bug as two failures — the code defect itself and the testing system that allowed it through. Use when fixing a production bug, investigating a regression, writing a post-mortem, or auditing a missed defect. Triggers on "fix this bug", "production bug", "regression test", "post-mortem", "test gap", "why did the tests miss this".
Copy text to clipboard with optional rich formatting. Triggers on "copy to clipboard", "copy that", "pbcopy", "copy formatted", "copy rich text".
Software-engineering heuristics based on Mark Seemann's Code That Fits in Your Head (2021), updated for agent-driven development. Use when writing or reviewing code, refactoring accidental complexity or a Big Ball of Mud, controlling technical or architectural debt in generated code, designing APIs and invariants, adding a feature through a walking skeleton and acceptance tests, debugging a defect with reproducible tests or bisection, threat-modelling endpoints and trust boundaries with STRIDE, planning a legacy or Strangler migration with rollback, or setting up a maintainable codebase. Covers decomposition and cyclomatic complexity, cohesion, encapsulation, outside-in TDD, separation of concerns, Git/review discipline, safe evolution, and troubleshooting. Not for language syntax, framework tutorials, production incident response, or performance profiling.
Manage hooks and automation for coding agents (Claude Code, Codex CLI, OpenCode). Use when users want to add, list, remove, update, or validate hooks. Triggers on requests like "add a hook", "create a hook that...", "list my hooks", "remove the hook", "validate hooks", or any mention of automating agent behavior with shell commands or plugins.
Audit and improve repositories for reliable agentic work across Codex and Codex App, Claude Code, and OpenCode. Use when reviewing AGENTS.md or CLAUDE.md quality and discovery, instruction routing in monorepos or meta-repos, agent settings, MCP configuration, skills, subagents, context budgets, or repository organization for coding agents.
Fetch a web page (URL) and return clean Markdown via local trafilatura, with Exa MCP as a fallback for JS-rendered or anti-bot pages. Use when the user asks to read, fetch, scrape, summarize, or quote a URL — prefer this over the built-in WebFetch tool. Don't use for binary files (PDFs, images, archives) or for fetching API/JSON endpoints.
First Principles Framework (FPF) — thinking amplifier. Use when user wants to think through a complex problem, architect a system, evaluate alternatives, decompose complexity, classify problems, define quality attributes, plan, apply an FPF pattern to a first useful result, decide under uncertainty, establish causality, reason about time and trends, describe or synthesize architecture, check model fit, recover project/process/case/system subjects, trace outside-use dependencies, distinguish relation kinds or occurrences, govern ontic/U-kind admission, publish multi-view artifacts, refresh SoTA packs, trace provenance, or improve pattern quality. Also triggers on: FPF, bounded contexts, SoTA packs, assurance calculus, decision theory, causal/temporal reasoning, architecture, modularity, transformation-flow networks, narrative rendering, structural adequacy, cultural evolution, quality gates, lexical discipline, FPF Parts A-I. Not for simple task planning, general philosophy, or Agile unrelated to FPF.
Hands-on playbook for macOS disk cleanup, dev-machine optimization, and proactive health alerting. Use when the Mac is full or slow, when a process persistently burns CPU, when a kernel panic / watchdog timeout / vm-compressor-space-shortage / Jetsam event happened, when the user asks to free disk space, audit storage, set up disk/memory/CPU alerts, or restore the same monitoring on a new Mac. Built around Mole (`mo` CLI) for safety guards plus a custom LaunchAgent-based alerter for active warnings. Covers Apple Silicon laptops with heavy AI/Docker workloads. Not for general macOS support, hardware diagnostics, networking issues, GUI / window-manager bugs, Time Machine recovery, or broken app installs.
Universal prompt engineering techniques for any LLM. Use when crafting, optimizing, or reviewing prompts for AI models. Triggers on requests like "improve this prompt", "write a system prompt", "optimize my instructions", "help me prompt engineer", "audit this prompt", "review my prompt", or when building agentic systems that need structured prompts.
Install, upgrade, configure, and verify developer CLI tools safely. Use when a user asks to install a new CLI, command-line app, SDK tool, package-manager binary, GitHub release binary, language runtime tool, or AI/vendor CLI; configure shell PATH/completions; run first login; set API keys, tokens, or env variables for a CLI; migrate an existing CLI install; or troubleshoot a CLI installation while avoiding secret leakage.
Hands-on playbook for Windows 11 disk cleanup, dev-machine optimization, and proactive health alerting. Use when the PC is full or slow, when a BSOD / Kernel-Power 41 / crash dump / commit-memory pressure happened, when the user asks to free disk space, audit storage, set up disk/memory alerts, or restore the same monitoring on a new PC. Built around native Microsoft-supported tooling (Storage Sense, cleanmgr, DISM, pnputil, vssadmin, wevtutil, powercfg) as the safety floor, a drift-protected HTML cleanup UI, and a Task Scheduler + BurntToast alerter. Covers dev machines with heavy AI/Docker/WSL workloads. Not for general Windows support, hardware diagnostics, GPU/driver troubleshooting, antivirus/malware removal, Windows Update repair, networking, or app-specific performance problems unrelated to disk or memory pressure.
Investigate GitHub repository history before risky code changes using git blame/log, GitHub PRs, review comments, squash/rebase/cherry-pick/rename heuristics, and cited evidence. Use when asking why code exists, whether a change is safe, what PR introduced behavior, or before editing API, compatibility, security, concurrency, persistence, migration, or performance-sensitive code.
Create, publish, delete, and submit plugins for coding agents (Claude Code, OpenCode). Use when user wants to (1) create a new plugin with proper structure, (2) create or configure a plugin marketplace, (3) publish plugins to GitHub/GitLab/npm, (4) delete/uninstall plugins, (5) validate plugin structure, or (6) prepare and submit plugins to the official Anthropic directory or the OpenCode ecosystem.
Use this skill when the user asks to plan, design, scope, estimate, or implement a feature, bug fix, refactor, migration, integration, API change, UI change, or other project modification. Enforces a planning gate before editing code — investigate project context, analyze the task, surface ambiguities, contradictions, risks, dependencies, and blockers, ask focused questions, produce an evidence-based step-by-step plan, and implement only after explicit user approval. Not for trivial one-line edits, pure questions about the codebase, or changes the user has already reviewed and approved for direct implementation.
Search, install, configure, update, and remove MCP servers across coding agents (Claude Code, Cursor, VS Code, Claude Desktop, Gemini CLI, Codex, Goose, Zed, and more). Supports multi-agent installation via npx add-mcp, the official MCP registry, and direct config editing.
Create, edit, list, move, and delete subagents and skills for coding agents (Claude Code, Codex CLI, OpenCode). Manage AGENTS.md instructions, custom subagent definitions, and skill packages across user and project scopes.
Deep research over the Semantic Scholar Graph API. Covers endpoints missing from allenai's lookup skill — paper references (backward citations), recommendations, batch paper lookup (up to 500 IDs), snippet search, and multi-hop citation graph traversal (BFS forward/backward). Use when the user asks to build a citation graph, expand a literature seed, find related work, run a reference network traversal, explore what a paper cites or what cites it beyond simple lookup, or batch-resolve many DOI/arXiv/S2 IDs. For multi-step research questions, delegate to the deep-paper-researcher subagent to keep the main context clean. Not for single paper-by-ID lookups (use semantic-scholar-lookup) or topical discovery (use web_search_advanced_exa).
Search, find, discover, install, remove, update, review, deduplicate, list, move, optimise, and iterate on skills for AI coding agents. Use when user asks "find a skill for X", "install skill", "remove skill", "update skills", "list skills", "deduplicate skills", "why are two skills shown", "choose the canonical skill", "check for skill conflicts", "review skill quality", "move skill", "check for updates", "optimise skill", "audit skill edits", "trigger test skill", or "transfer skill across agents". Includes duplicate-free installation preflight and SkillOpt-style training loops. Do not use for creating skills from scratch (use /skill-creator instead).
Rename and refactor C# symbols in a .NET solution or multi-solution monorepo with a one-shot Roslyn CLI. Use when the user asks to rename a symbol, preview impact, update references across a solution, or refactor shared projects across several solutions.
View and configure settings for coding agents (Claude Code, Codex CLI, OpenCode, and others). Covers JSON settings for Claude Code, TOML for Codex CLI, and JSON/JSONC for OpenCode, including permissions, sandbox, model selection, profiles, feature flags, providers, hooks, subagents, and skills.
Use when testing Windows 11 desktop apps (WinForms/WPF/UWP) via UFO UIA/Win32 automation MCP. Triggers on "test this Windows app", "QA the app", "run smoke test", "click the button", "fill the form", "check the UI", "Windows automation", "UFO QA", "verify the dialog", or any Windows desktop UI testing task. Not for web/browser testing (use Playwright), mobile testing, or non-Windows platforms.
| Maintain a project thesaurus (domain glossary) following DDD ubiquitous language modules, database fields, API endpoints, events, files, or directories. Also use when the user asks to "create thesaurus", "update glossary", "add term", "rename to match domain", "check naming consistency", "what should I call this", "domain language", "ubiquitous language", or "naming conventions". Ensures all names in the codebase are consistent, descriptive, and aligned with the shared domain vocabulary. Not for general code style or linting — only for domain term consistency.
>- Write one model-agnostic video prompt spec, then compile it to whichever video model you can actually call. Use for cross-model prompt work, model comparison matrices, reusing one brief across providers, or when the target model is not yet available and the work must proceed on another one.
See, Understand, Act on video and audio. See- ingest from local files, URLs, RTSP/live feeds, or live record desktop; return realtime context and playable stream links. Understand- run analyzers over speech, scenes, objects, OCR, brands and activity; build searchable indexes; then search moments, ask questions about a video, filter and aggregate results with timestamps and auto-clips. Act- transcode and normalize (codec, fps, resolution, aspect ratio), perform timeline edits (subtitles, text/image overlays, branding, audio overlays, dubbing, translation), generate media assets (image, audio, video), and create real time alerts for events from live streams or desktop capture.
Reviews decks, documents, and strategies like a McKinsey engagement manager. Grades each section, flags structural problems, and gives the top 3 fixes. Use after building a deck, writing a strategy doc, or outlining a recommendation — before it goes to stakeholders.
Personal meeting prep tool. Given a meeting (attendees, topic, desired outcome), generates a tight prep packet — 3-bullet pre-read, time-boxed agenda, your top 3 talking points, and the top 3 objections you'll face with rebuttals. Use before any meeting where you're driving an outcome — exec reviews, stakeholder pitches, scope negotiations, manager 1:1s with an ask, vendor calls.
McKinsey-style issue tree framework for breaking down complex problems into MECE (Mutually Exclusive, Collectively Exhaustive) components. Use when users need to decompose strategic questions, structure analysis, create work plans, or prepare for case interviews. Apply hypothesis-driven approach to problem-solving.
Multi-agent pipeline that builds a polished presentation deck from a single topic. Four agents work in sequence — Strategist defines the narrative, Builder creates the deck, Critic reviews it like a McKinsey EM, Fixer applies the top fixes. Use when you need a presentation that survives senior audiences.
Generate McKinsey-style consulting charts as native python-pptx objects (editable inside PowerPoint). Three workhorse types — bar+callout for TAM/single-number stories, stacked column over time for revenue/usage mix, and waterfall for drivers/bridge analysis. Use when you need a chart that looks like it came from an EM-reviewed deck, not from Excel defaults.
Build a Day-1 hypothesis tree — your best-guess answer to the governing question, broken into 2–3 supporting sub-hypotheses, with the test that would prove or kill each one. Different from an issue tree (which decomposes the problem space). This commits to an answer before you do the work, so the work targets what would actually change your mind. Use at the start of any analysis where you'd otherwise "boil the ocean.
Builds a 1-page decision memo (context → options → recommendation → risks → ask) enforcing McKinsey memo DNA — brutal brevity, SCP storyline clarity, decision-forcing output, evidence density. Use when drafting a memo for a leadership decision, a scope cut, a buy/build/partner call, a roadmap slip, or any "should we X?" moment that needs a yes/no from a specific person by a specific date.
Score and prioritize AI use cases for your own job. Given a list of candidate use cases (or a description of your workflow), evaluates each on Value × Feasibility × Safety and tiers them — Do Now / Do This Quarter / Park / Avoid. Use when you've heard "we should use AI more" and need to figure out what to actually build first. Built for the individual IC, not org-wide rollout.
Force the "so what" out of a messy pile of raw inputs — interview notes, customer transcripts, survey results, research dumps, meeting recordings — into 3 insights with evidence and implication. Use when you have more data than you have meaning, and someone is about to ask "ok, so what does this mean?" Different from summarization; output must change how the reader acts.
SCPR (Situation-Complication-Problem-Recommendation) framework for structured problem solving and executive communication. Use when users need to structure strategic arguments, analyze business situations, create executive summaries, or develop clear problem statements using McKinsey-style communication. Apply when structuring recommendations, writing memos, or organizing strategic thinking.
Claude Skills — questions
Answers built from the skills we actually parsed.