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. 79 551 files from 1 750 authors, of which 61 898 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 whenever the user wants to find, shortlist, vet, enrich, or research US professional-services firms — law, marketing, consulting, accounting, IT services, architecture, engineering, HR, PR, design, and similar B2B service providers. Triggers on requests like "find me a PPC agency in California", "shortlist three boutique IP law firms", "build a longlist of 50 mid-size IT consultancies", or "here are 12 agency domains — pull contact info and confirm which are US-based", even when the need is described indirectly without naming a category. Drives the ServiceGraph API (api.servicegraph.co) — a 100k+ US firm catalog with filters for industry, services, location, size, ratings, and third-party listings. Skip when the user is asking for personal/consumer services for themselves (an individual's own legal, tax, or medical needs), non-US firms, individual freelancers, retail/ecommerce/SaaS-product companies, recruiting-an-employee tasks, or general web research that doesn't need a structured firm directory.
Use whenever the user wants to find, shortlist, vet, or enrich US software development firms — custom software, web development, mobile app development, backend/API development, DevOps/cloud, system integration, and hosting. Triggers on "find a software dev shop in Austin", "shortlist three custom-software firms with healthcare experience", "we need a mobile app developer for our iOS launch", or "pull contact info for these 10 dev shop domains", even when described indirectly (build a tool, ship a feature, technical partner). Drives the ServiceGraph API (api.servicegraph.co) — a 100k+ US firm catalog filterable by industry, services, location, size, ratings. Defer to find-web-developer for strictly website/landing-page projects. Defer AI/ML, ML pipelines, model building, and data-engineering asks — those are a sibling industry, not software development. Skip in-house engineer hires, code-writing/debugging tasks, cloud-product comparisons, hardware/civil engineering, non-US firms, individual freelancers.
Use whenever the user wants to find, shortlist, vet, or enrich US web development firms — building, refreshing, or rebuilding marketing sites, landing pages, ecommerce, WordPress/Webflow/Shopify, headless CMS, microsites, and web frontend work. Triggers on "find a web developer for a marketing landing page", "shortlist three Webflow agencies in California", "rebuild our ecommerce site on Shopify", or "pull contact info for these 8 web dev shop domains", even when described indirectly (redesign and rebuild our site, ship a microsite). Drives the ServiceGraph API (api.servicegraph.co) — a 100k+ US firm catalog filterable by industry, services, location, size, ratings. Defer to find-software-developer for custom backend/API/mobile/internal-tool work — anything beyond a website. Defer to find-marketing-agency when scope spans broader marketing beyond the build. Skip in-house web-engineer hires, "how do I build X" DIY questions, hosting/CMS-product comparisons, non-US firms, individual freelancers.
The branded entry point to ServiceGraph — use whenever the user explicitly names **ServiceGraph** — "use ServiceGraph to…", "what datasets does ServiceGraph have", "search ServiceGraph for…", "look this up in ServiceGraph", "pull contacts from ServiceGraph for these domains", "how many credits do I have on ServiceGraph". ServiceGraph is a multi-dataset platform of metrics-enriched business data for founders — where to launch, who to email, who to hire. This skill explains how to drive the API (api.servicegraph.co / mcp.servicegraph.co) against ANY dataset — discover what datasets exist, discover a dataset's schema and filters, search free brief rows, and unlock contact + metric detail with credits. Dataset-agnostic by design — it discovers everything through the API and never assumes which datasets or fields exist. When the user describes an intent WITHOUT naming ServiceGraph (e.g. "find a PR agency in NY"), defer to the matching specific skill (find-pr-agency, find-marketing-agency, find-law-firm, …); this skill is for explicit ServiceGraph requests and for datasets no specific skill covers yet. Skip non-US firms, consumer/personal services, and individual freelancers.
>- Export desensitized governance summary markdown for sharing or machine switch. Trigger on /pm-export and related English phrases for this command.
>- Create, import, discover, approve, or skip project charter; integrates Spec Kit constitution. Trigger on /pm-charter and related English phrases for this command.
>- Claim the single next governance todo (marks in_progress). Trigger on /pm-next and related English phrases for this command.
Project governance workbench (/pm-*). Use for /pm-init, /pm-status, /pm-next, /pm-done, /pm-fix, /pm-all, /pm-outline, /pm-charter, /pm-export, /pm-arch, project health Top3, pasted logs/stacks, Spec Kit constitution discovery, and local .pm governance. Triggers on project management, governance, what should I do today, help me with this error.
>- Generate detailed project outline and draft charter from user intent (empty/new projects). Trigger on /pm-outline and related English phrases for this command.
Generate AI images with FLUX, Gemini, Grok, Seedream, Reve and 50+ models via inference.sh CLI. Models: FLUX Dev LoRA, FLUX.2 Klein LoRA, Gemini 3 Pro Image, Grok Imagine, Seedream 4.5, Reve, ImagineArt. Capabilities: text-to-image, image-to-image, inpainting, LoRA, image editing, upscaling, text rendering. Use for: AI art, product mockups, concept art, social media graphics, marketing visuals, illustrations. Triggers: flux, image generation, ai image, text to image, stable diffusion, generate image, ai art, midjourney alternative, dall-e alternative, text2img, t2i, image generator, ai picture, create image with ai, generative ai, ai illustration, grok image, gemini image
UI/UX design intelligence for web and mobile. Includes 50+ styles, 161 color palettes, 57 font pairings, 161 product types, 99 UX guidelines, and 25 chart types across 10 stacks (React, Next.js, Vue, Svelte, SwiftUI, React Native, Flutter, Tailwind, shadcn/ui, and HTML/CSS). Actions: plan, build, create, design, implement, review, fix, improve, optimize, enhance, refactor, and check UI/UX code. Projects: website, landing page, dashboard, admin panel, e-commerce, SaaS, portfolio, blog, and mobile app. Elements: button, modal, navbar, sidebar, card, table, form, and chart. Styles: glassmorphism, claymorphism, minimalism, brutalism, neumorphism, bento grid, dark mode, responsive, skeuomorphism, and flat design. Topics: color systems, accessibility, animation, layout, typography, font pairing, spacing, interaction states, shadow, and gradient. Integrations: shadcn/ui MCP for component search and examples.
When the user wants to audit, review, or diagnose SEO issues on their site. Also use when the user mentions "SEO audit," "technical SEO," "why am I not ranking," "SEO issues," "on-page SEO," "meta tags review," "SEO health check," "my traffic dropped," "lost rankings," "not showing up in Google," "site isn't ranking," "Google update hit me," "page speed," "core web vitals," "crawl errors," or "indexing issues." Use this even if the user just says something vague like "my SEO is bad" or "help with SEO" — start with an audit. For building pages at scale to target keywords, see programmatic-seo. For adding structured data, see schema-markup. For AI search optimization, see ai-seo.
Use for autoresearch or "optimize X overnight/in a loop"; sets up bounded iterative trials for a measurable optimization target.
Cut a release: bump versions, write changelogs, commit, tag.
Audit JavaScript, TypeScript, and Go comments for verified stale, orphaned, misleading, or redundant claims.
Report active Codex and Claude Code sessions in the current repository by default, with optional machine-wide detail.
Retrospect on a task against local Codex/Claude Code transcripts; propose durable fixes (AGENTS.md, skills).
Use for dependency updates: bump npm/pnpm/yarn/bun packages, check outdated, or run taze.
>- Use for current official documentation about Codex, Codex CLI, or Claude Code behavior, configuration, prompting, skills, permissions, tools, surfaces, capabilities, or troubleshooting; fetch the relevant official URL before answering.
context docs."
Orchestrate read-only Explore research subagents during planning and one to five Haiku, Sonnet, or Opus subagents to implement the approved plan.
command syntax. Use yeet for contribution writes to PRs, issues, comments, or discussions."
messages; encode/decode ABI/calldata; or make RPC calls. For read-only balances/history, prefer evm-atlas."
Orchestrate read-only Codex research agents during planning and one to five Codex CLI agents to implement the approved plan.
"Polish changed code when the user explicitly asks, or when an active workflow requests post-implementation simplification and risk-profiled review over a fixed file scope."
or set up command-runner workflows."
historical/OHLC data."
Open the CoinGecko historical-data page for a coin/date in Chromium via Chrome DevTools MCP.
--staged, --close, or --push."
Use to create/scaffold/init a new agent skill under `.agents/skills` in the working directory where invoked.
Use to find, compare, and recommend current tools, packages, libraries, CLIs, VSCode extensions, agent skills, databases, or infrastructure options for a development task.
Use when creating or substantially redesigning web interfaces, landing pages, dashboards, components, or other frontend UI where visual direction and implementation quality matter. Produces subject-specific art direction, accessible responsive code, and rendered visual verification.
symbol, RouteMesh, wallet balances via Blockscan in Chromium, token/NFT holdings/transfers, tx history, funding origin via Etherscan/Blockscout/Chainscout; Across, Bungee, deBridge, Hop, Layerswap, LayerZero, LI.FI, Relay, Socket, Symbiosis; Uniswap v1-v4, Universal Router, Permit2, 1inch Classic/Fusion/Fusion+, and CoW Swap, CoWSwap, CoW Protocol, or GPv2 swaps, orders, liquidity, approvals, permits, rewards, migrations, wrapping, cancellations, and refunds."
Use for nontrivial Effect-TS work including services/layers, typed errors, Schema/JSONSchema, Config, runtime/concurrency, @effect/vitest, @effect/ai, @effect/sql, or @prb/effect-next.
Audit an entire repository with fresh eyes for correctness errors, bugs, omissions, duplication, inconsistencies, and other evidenced mistakes; fix every safe issue and verify the result.
Squash a feature branch into one commit via soft reset to the merge base, ready for a clean PR.
Discover large source-file refactor candidates and propose cohesion- and risk-driven split plans using available semantic tooling.
Interview the user relentlessly about a plan or design until every branch of the decision tree has an explicit recorded decision and no open questions remain. Use when user wants to stress-test a plan, get grilled on their design, or mentions "grill me".
"Use to find agent skill installs, duplicate skills, cross-dependencies, invocations, and cross-references across the local machine."
Refactor naming and repository structure exhaustively while preserving behavior and external contracts.
"Preview or rename a GitHub upstream repo and matching local project folder, update origin, and preserve Codex CLI and Claude Code continuity references."
Use for interactive HTML debriefs or saved HTML findings/reports from the current task.
Use to build interactive single-file HTML playgrounds, explorers, or tools with visual controls, live preview, and prompt copy-out.
"Use to audit Agent Skills catalogs or installed skill roots for metadata and doc-link issues; optionally apply conservative --fix-safe repairs."
formulas, or create/fix spreadsheets. Do not trigger when tabular data is incidental."
Archive checked TODO.md tasks into `.ai/todos/TODO_UNTIL_YYYY_MM_DD.md`, leaving unchecked tasks.
include yeet."
mocks, testing utilities, and coverage."
Create decision-complete single- or multi-repository task plans under `.ai/task-handoffs/` and return commands for fresh interactive Codex sessions.
tw-animate-css."
> Check whether the claims in public-facing documentation (README, release notes, install/usage docs) are supported by the evidence the user provides — files, manifests, logs, and command outputs supplied in the conversation. Produces per-claim findings with a confidence label (verified / unsupported / stale-suspected / needs-human) and an explicit "input scope reviewed" statement. Advisory only. Use when the user asks to fact-check docs, verify a README against a repo, audit release notes, or find stale or overstated documentation claims. Do NOT use for standalone code review or bug hunting, security audits, fix/patch generation, or pure command-execution tasks. When such requests are mixed with an eligible claim-check, still use this skill for the claim-check portion and decline only the out-of-scope part — by contract it does not execute commands or edit files.
Assess and guide safer github.com repository releases. Use when an existing private GitHub repository becomes public for the first time, or whenever an already-public GitHub repository publishes a new version, and the user needs readiness checks, release-surface decisions, explicit mutation approvals, release notes, settings checks, or post-release verification. Supports read-only Assess and approval-gated Guided modes. Do not use for repository bootstrap, package registries, signing, cloud deployment, security audits, GitHub Enterprise, other providers, force-push, or history rewrite.
Author technical/structured SVG infographics and diagrams, then render them to crisp PNG with a headless browser. Best for architecture diagrams, topology maps, flows, before/after comparisons, nested/onion layer models, roadmaps, decision matrices, and social-ready technical one-pagers. Prefers clean line icons in soft tinted circles. First-class Korean/CJK text. Includes an opt-in "tidy hand-drawn" sketch preset (paper background, Korean handwriting font, rough strokes, highlighter). Not for photo-heavy or illustration-heavy graphics, statistical charts, or mascot/character illustration.
Writing Quality Editor (WQE) composes, assesses, revises, and adapts user-facing writing so it reads naturally while preserving meaning, claims, intent, voice, conditions, numbers, identifiers, exceptions, and risks. Use when a user asks to write, review, polish, fix, improve, supplement, clarify, translate, localize, or make a document sound natural; no skill or mode name is required. Covers README, onboarding, release notes, manuals, UI, errors, gallery copy, research-backed briefs, technical comparisons, and natural English↔Korean adaptation. If a host repository workflow owns document classification, path, indexing, lifecycle, or approval, keep it primary and use this skill only as an optional authoring layer. Locale-neutral design; EN↔KO (`ko-KR`) is the initial profile under validation. Do not game detectors, conceal provenance, invent claims, replace evidence review, or bypass host workflows.
View and manage your cognitive profile — how you think, work patterns, blind spots, and cross-domain connections. Use when the user says 'show my profile', 'how do I work', 'what are my patterns', 'cognitive style', 'blind spots', 'methodology', or at the start of a session to load context. Also use 'rebuild profile' to rescan all session history, or 'list domains' to see all tracked project domains.
Navigate the knowledge graph — trace entity relationships, explore causal chains, drill into memory clusters, and traverse co-access paths. Use when the user asks 'how are these related', 'what connects X to Y', 'show me the knowledge graph', 'trace the relationship', 'what caused X', 'drill down into', 'explore connections', or when you need to understand the web of relationships between concepts, entities, and memories.
Set up automation — prospective memory triggers, neuro-symbolic rules, and CLAUDE.md sync. Use when the user says 'remind me when', 'trigger when', 'create a rule', 'auto-remember', 'sync to CLAUDE.md', 'push insights', 'set up trigger', 'when I open this file', 'when this keyword appears', or when you want to automate memory behavior based on conditions.
Search and retrieve global memories — knowledge that applies across all projects. Use when the user asks 'what are our coding standards', 'what conventions do we follow', 'what's our infrastructure setup', 'do we have a rule about', 'what applies to all projects', 'shared knowledge', 'global rules', or when you need cross-project context like architecture decisions, server configs, or team policies.
Debug and fix memory system issues — validate memories, rate quality, manage protection, forget bad memories, and restore from checkpoints. Use when the user says 'fix memory', 'bad memory', 'wrong memory', 'delete this', 'protect this', 'this memory is wrong', 'memory quality', 'rate this memory', 'restore checkpoint', 'undo', or when memories are returning incorrect or stale results.
Explore the memory system's state, find gaps in knowledge, assess coverage, and get diagnostic information. Use when the user asks 'what does my memory look like', 'show me memory stats', 'what am I missing', 'how good is my knowledge', 'memory health', 'show coverage', 'find gaps', 'what topics are weak', or when you need to understand the state of stored knowledge before a task.
Claude Skills — questions
Answers built from the skills we actually parsed.