Claude Code skills

49,760 tagged Claude Code, measured the same way as everything else here.

Browse within: agentic-ai 319antigravity 277agentic-skills 191ai-workflows 185coding-agents 164claude-code-skills 115agentic-framework 109agentic-workflow 109swarm 109Autonomous Agents 106agent-infrastructure 101claude-cli 100ci 97actions 96

orchestrate

1561

ConnorGriffin/skills

Skill Codex

Flip the session into coordinator mode — the parent agent plans, scopes, reviews, and ships, but delegates all real work (exploration, implementation, review, fixes) to sub-agents routed by an empirically benchmarked model capability table. Use when the user invokes /orchestrate or asks the parent to act as an…

not rated 20 changed 3d ago A 95 tokens

content-pipeline

1562

arturseo-geo/content-pipeline-skill

Skill Claude CodeCodex

Run a multi-agent content production pipeline where specialist agents work together to research, write, edit, optimise for SEO/GEO, and validate against analytics data — with a master agent reviewing all outputs before human approval. Use this skill whenever the user wants to produce content using multiple agents…

not rated 20 5mo ago A 157 tokens original MIT

hush

1563

royashbrook/hush

Skill Claude CodeCodex

Use whenever an agent needs to STORE, GENERATE, or USE a secret such as an API token, signing key, or password. Hush has one hard rule: the agent never sees plaintext, so it never enters chat, transcripts, stdout, logs, the clipboard, or a temp file. A user-provided value enters once through a hidden prompt; a strong…

not rated 20 changed 8d ago A 189 tokens original MIT

looks-expensive

1564

TuahaJawaid/looks-expensive

Skill Claude Code

Full-stack design methodology that makes any website look like a $150k agency build. Nine gated phases: positioning, research, design contract, screen spec, build, subtraction, audit, hardening, handoff. Includes illustration system, animation tiers, 12 hero patterns, 16 section layouts, UX writing guide, icon system…

not rated 20 3mo ago A 173 tokens original MIT

devnomad-byte/cosmosmith

Skill Codex

Generate or update project instruction files for Cosmosmith-governed projects. Use when the user wants AGENTS.md, CLAUDE.md, Cursor rules, Copilot instructions, OpenCode, Trae, or other editor/agent rules created from Cosmosmith conventions, or when they ask how agents should load and follow project rules.

not rated 20 2mo ago A 73 tokens original MIT

setup-connector

1567

kombohq/company-brain

Skill Claude CodeCodex

Enable and configure an existing connector. Use when the user wants to start syncing a data source that already has a connector (Notion, web, repo, Zendesk, Pylon, Granola), set up credentials, enable the CI schedule, or customize filtering and output for an existing connector.

not rated 20 2mo ago A 63 tokens original MIT

stiegler-perspective

1568

tizzy916/scholar-wendao-skill

Skill Claude CodeCodex

An academic analysis lens based on Bernard Stiegler’s work, using concepts, research records, translations, and a mapped intellectual background.

not rated 20 3mo ago A 294 tokens

feynman-tutor

1569

koukekoukej-glitch/feynman-tutor

Skill Claude CodeCodex

A Chinese-language tutoring guide for having ongoing, personalized discussions with a learner. It tells the tutor how to clarify ideas, adapt to the learner's wording, and use notes from earlier sessions.

not rated 20 +1 3mo ago A 76 tokens original MIT

researchclaw

1570

OthmanAdi/researchclaw-skill

Skill Claude Code

Automate setup, configuration, execution, monitoring, and troubleshooting of AutoResearchClaw — the 23-stage autonomous research pipeline that generates conference-grade papers. Use when the user mentions ResearchClaw, wants to write a research paper autonomously, needs to set up or debug the pipeline, or says…

not rated 20 5mo ago B 74 tokens original MIT

dual-brain

1572

sleeplesshan/dual-brain

Skill Claude Code

Two complementary reusable sub-agents collaborate to remember, grill, verify, document, and maintain weighted project memory. A Right Brain (context / pattern / grill) interrogates assumptions against Hot/Warm memory; a Left Brain (logic / verification / code) cross-checks memory, code, and docs; the orchestrator…

not rated 20 3mo ago A 194 tokens original MIT

zom-representation

1573

Accelerated-Innovation/governed-ai-delivery

Skill Claude Code

Zero-One-Many Representation Evolution — use this skill whenever working with existing code that needs to change, grow, or be refactored. Triggers include: "refactor this", "add a new X to this", "this is getting messy", "how should I represent this", "there's a lot of duplication here", or any time numbered…

not rated 20 10d ago A 137 tokens

knack-interview

1574

jordan-gibbs/knack-cli

Skill Claude CodeCodex

Conduct the Knack 6-phase interview with a user to author a new skill. Load this skill when the user wants to teach you a recurring task they do and have it become a reusable Knack skill (e.g. "use knack to capture how I triage support tickets").

not rated 20 1mo ago A 62 tokens original MIT

postmodernist

1575

kgeoffrey/postmodernist

Skill Codex

Critique AI-generated strategy, marketing, and positioning prose. Use for framing-level rewrites that surface hidden assumptions and fake polish, not for factual QA, coding, or basic copyediting.

not rated 20 4mo ago A 42 tokens original MIT

scholar-lab-radar

1576

TaewoooPark/scholar-lab-radar

Skill Claude CodeCodex needs its repo

Profile a research lab (a professor, or a school/department) over the last N years by collecting every paper from OpenAlex, structuring it into a temporal knowledge graph (ontology) — Papers, Researchers, Topics, Themes, Methods, Venues, Citations — and synthesizing a grounded report of the lab's year-by-year output…

not rated 20 2mo ago A 192 tokens original MIT

MCP Server Setup

1577

lukacf/meerkat

Skill Claude CodeCodex

How to configure MCP servers in .rkat/mcp.toml.

not rated 20 yesterday A SkillSpector: warn 18 tokens original Apache-2.0

sleuth

1578

povvo/sleuth

Skill Claude CodeCodex

Use when conducting structured investigative research, OSINT analysis, due diligence, or intelligence-grade inquiry. Activate for tracing beneficial ownership, mapping entity networks, authenticating digital evidence, sanctions screening, resolving fragmented identity records, constructing chronological timelines, or…

not rated 20 4mo ago A 101 tokens original MIT

whisk-proxy

1579

AndyShaman/whisk-proxy

Skill Claude CodeCodex

Generate images with Google Imagen 4 and Nano Banana for free via Flow API. No API key, no paid subscription — just a Google account and Chrome extension. Use when the user asks to generate, create, or make an image, picture, illustration, logo, banner, or avatar. Triggers: generate image, create picture, make…

not rated 20 6mo ago A 128 tokens original MIT

andre-simplifica/oracle-apex-ai-skills

Skill Codex

Use for installing, upgrading, auditing, retaining, uninstalling, and enforcing the cooperative PKDEVOBJECTLOCK runtime before editing, compiling, replacing, or testing versioned PL/SQL and other supported objects in a shared Oracle DEV schema.

not rated 20 20d ago A SkillSpector: pass 53 tokens original MIT

test-skill

1581

martinemde/skillet

Skill Claude Code

A simple test skill that creates a greeting file.

not rated 20 +1 2mo ago A 13 tokens original MIT

agntcms-section-new

1582

agntcms/agntcms

Skill Claude Code

Creates a new section from name and field list: folder, schema, component, config registration.

not rated 20 +1 3mo ago A 25 tokens original MIT

ui-ux-pro-max

1583

whyiyhw/seek

Skill Claude CodeCodex

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…

not rated 20 +1 3d ago B 238 tokens copy · 100% MIT

morning-triage

1584

dshakes/compass

Skill Claude Code

Discovery for an autonomous loop — find this turn's work instead of being handed it. Reads what changed since the last run (failed CI, new issues, merged commits), judges what's actually worth acting on, writes findings to a durable state file, and hands each off to the SDLC loop with a stop-condition. Use as the…

not rated 20 +1 12d ago A SkillSpector: pass 102 tokens original MIT

At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: