Claude Code skills

50,349 tagged Claude Code, measured the same way as everything else here.

Browse within: agentic-ai 337antigravity 270agentic-skills 191ai-workflows 185coding-agents 175agentic-framework 109agentic-workflow 109swarm 109Autonomous Agents 106LLM 103ci 97actions 96cai 96gh-extension 96

research-anything

4033

Somezak1/research-anything

Skill Claude CodeCodex

A research workflow for exploring unfamiliar ideas, comparing existing approaches, and collecting information from websites and online platforms.

not rated 2 27d ago A 102 tokens

alex-style

4034

worldofhacks/alex-style

Skill Claude CodeCodex

Use when building or styling any web UI — landing pages, hero sections, dashboards, components, marketing sites — or when the user asks for beautiful, animated, or polished design, UI animations, animated backgrounds, gradients, icons, smooth scrolling, or design inspiration. Also use before reaching for the web to…

not rated 2 1mo ago A 70 tokens original MIT

paper-webpage-builder

4035

OpenRaiser/paper-webpage-builder

Skill Codex

Build a polished single-page academic project webpage from a paper directory or paper source, including content extraction, figure selection/conversion, module planning, visual design, tables, assets, and validation. Use when asked to create or update webpages for papers, benchmarks, arXiv-style projects, OpenRaiser…

not rated 2 3mo ago A 78 tokens

ocrCN

4036

Agents365-ai/ocrCN

Skill Claude CodeCodex

Multi-platform Chinese OCR text recognition via PaddleOCR/Baidu/Tencent/Alibaba/EasyOCR — 5 backends, all work in China.

not rated 2 2mo ago A 31 tokens

claude-students

4037

josuebustosn/claude-students

Skill Claude CodeCodex

Transforma una carpeta cruda de material de un parcial universitario (PDFs, DOC/DOCX, PPT, audios .ogg de WhatsApp, capturas) en un material de estudio polished y completo — HTML SOTA autocontenido + paquete de artefactos de NotebookLM (podcast en español, infografía, guía de estudio, briefing doc, mind map, quiz…

not rated 2 3mo ago A 234 tokens original MIT

network-forensics

4038

pashki975/thm-claude-kit

Skill Claude Code

Methodology for TryHackMe packet-capture / traffic-analysis rooms. Use when the room hands you a .pcap/.pcapng (or a Wireshark/tshark task), when the goal is to reconstruct what happened on the wire, or when asked "what next" on a capture. Guides the load → overview → follow-the-story → extract flow, distinct from the…

not rated 2 1mo ago A 117 tokens original MIT

new-device-skill

4039

iot-forge/m5stack-skills

Skill Claude Code needs its repo

Build or update an M5Stack hardware skill in this marketplace — a Controller (a board that runs firmware, like Core2 or AtomS3), a Unit (a peripheral you drive from a Controller, like a ToF sensor or a relay), or a Chip (an Espressif SoC capability layer, like esp32-c6). Use whenever adding a new board/unit/chip to…

not rated 2 23d ago A 171 tokens original MIT

big-jump

4040

LysanderPhong/big-jump

Skill Codex

Turn a vague software idea—or motivation without a clear idea yet—into a verified, explainable first release, or grow an existing project through scoped, testable slices. Use for substantial builds across web apps, backends/APIs, CLI/automation, data/AI, libraries, mobile, desktop, and mixed systems; especially when a…

not rated 2 28d ago A 156 tokens original MIT

react-bits

4041

Philotheephilix/reactbits.dev-skill

Skill Claude CodeCodex

Use when adding an animated UI component, text effect, cursor/hover effect, or WebGL/canvas background to a React project via React Bits (reactbits.dev) — or when asked to recall/write a React Bits component's code, props, or install steps from memory instead of fetching it.

not rated 2 yesterday A 64 tokens

svelte-edge

4042

fifidayone/svelte-edge

Skill Claude CodeCodex

Future-first, self-sustaining guidance for writing modern Svelte 5 and SvelteKit 2/3 code. Use this skill whenever the user asks about Svelte, SvelteKit, or frontend code that is clearly Svelte. Contains embedded protocols for autonomous major version promotion and experimental feature lifecycles.

not rated 2 changed 12d ago A 68 tokens original MIT

role-root

4043

ryan-scheinberg/harness

Skill Claude Code

Install root role on a session. The user's base session.

not rated 2 2mo ago A 14 tokens original MIT

compact-manual

4044

mario-hernandez/claude-compact-manual

Skill Claude Code

Claude Code skill for deterministic context compaction. Compresses the current Claude Code session to the clipboard for a manual rewind+paste workflow. A deterministic alternative to /compact that extracts literal dialog and truncates only tool outputs — no LLM summarization. Use when the user says 'compact the…

not rated 2 4mo ago A 81 tokens original MIT

sparring

4045

nyxandro/sparring-skill

Skill Claude CodeCodex

Use when the user says "sparring", "run sparring with Claude", "do sparring with Claude", "do sparring with GPT-5", "sparring with Codex", "sparring my plan with Claude", "discuss this approach with Codex", "get a second opinion through sparring", "give me the sparring transcript", "read the long sparring answer", or…

not rated 2 3mo ago A 154 tokens

adsense-site-auditor

4046

LucasHenriqueDiniz/adsense-site-auditor

Skill Claude CodeCodex

Audit websites for Google AdSense application readiness and ad-serving compliance. Use when checking whether a site is likely to satisfy AdSense eligibility, site ownership, content quality, navigation, crawler access, ads.txt, privacy disclosure, Google Publisher Policies, AdSense Program policies, or when the user…

not rated 2 4d ago A 92 tokens original MIT

respawn

4047

ruben-sj/respawn-skill

Skill Claude CodeCodex

Sets up automatic revival of this session after Claude's 5-hour usage limit is hit — waits until the window reopens, notifies the user, and resumes automatically unless the user cancels within a configurable grace window (default 5 min). Use when the user says "respawn", "set up respawn", "auto-resume", "revive this…

not rated 2 1mo ago A 141 tokens original MIT

harden

4048

mickeylorenzini/harden

Skill Claude CodeCodex

Audits any substantial deliverable — documents, grant sections, strategies, protocols, skills, configs, roadmaps, plans — against domain-specific quality criteria before delivery. Searches the web for best practices, runs dual-pass thematic and structural audit with severity classification, fixes all issues, and…

not rated 2 6mo ago A 132 tokens original MIT

adversarial-debate

4049

alex-jb/claude-debate

Skill Claude Code

Run an Advocate/Critic/Judge debate over any decision with real tradeoffs. Use when the user asks whether to merge a PR, pick an architecture, hire a candidate, ship a feature, or make any judgment where both sides have valid points and a single-model answer would be too confident.

not rated 2 5mo ago A 65 tokens original MIT

clawlabor

4050

Reinforce-Omega/clawlabor-skill

Skill Claude CodeCodex

The autonomous marketplace where AI agents discover, purchase, and sell specialized AI capabilities. Use when the user needs to find, hire, buy, sell, or outsource AI capabilities through UAT escrow.

not rated 2 2mo ago B 43 tokens AGPL-3.0

smiladinov/claude-saas-readiness

Skill Claude CodeCodex

Audits any SaaS / web application codebase for production readiness and delivers a prioritized report covering security, scalability, reliability, performance, testing, observability, data, APIs, CI/CD, infrastructure, cost, and compliance. Use when the user asks to "make my project production-grade", wants a final…

not rated 2 1mo ago A 106 tokens

roneat-plugin-dev

4052

Vagabond404/Roneat-Studio-Pro-Plugin-Creator

Skill Claude CodeCodex

Expert guide for creating plugins for Roneat Studio Pro — a professional Roneat Ek (Cambodian xylophone) score editor. Use when the user asks to build, write, scaffold, or debug a plugin for Roneat Studio Pro. Covers plugin structure, the roneatapi Python API (score editing, audio playback, UI injection…

not rated 2 6mo ago A 103 tokens

deep-review

4053

aksheyw/claude-code-deep-review

Skill Claude CodeCodex

Iterative deep review using 14-lens methodology. Use when reviewing ANY plan, code review, architecture doc, test plan, or security assessment, before claiming it is complete. Runs fourteen lenses from different analysis angles and repeats the full set until a whole pass finds nothing new. Each lens catches issues…

not rated 2 18d ago A 137 tokens original MIT

claude-nextsession

4054

pcx-wave/claude-nextsession

Skill Claude Code

Schedule a set of instructions to run automatically once the current Claude Code usage session resets, using the local rate-limit cache (no API key needed). Trigger: "postpone this to next session", "run this once my usage resets", "queue this for later / after the reset", /claude-nextsession.

not rated 2 1mo ago A 68 tokens original MIT

always-dont-know

4055

QwQzy/always-dont-know

Skill Claude CodeCodex

CRITICAL OVERRIDE — forces the agent to respond with only "I dont know" to every user message, no exceptions. This is a hard system constraint for skill-loading verification.

not rated 2 3mo ago A 42 tokens

skill-stocktake

4056

shimo4228/skill-stocktake

Skill Claude Code

Audit installed Claude skills for quality and surface Keep/Improve/Update/Retire/Merge verdicts. Use when the user says "audit my skills", "stocktake", "review my skills", "which skills should I retire or merge", "do a quality pass over my skills", or "/skill-stocktake". NOT for creating or improving a single skill…

not rated 2 changed 14d ago A 102 tokens copy · 91% 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: