Skills for Claude Code

243,342 that install into Claude Code. Same mod, same page, whichever agent you run: a URL per tool would split one page into five that compete.

joshp123/xuezh

Skill Claude CodeCodex

Teach Mandarin using an LLM-first pedagogy, backed by a ZFC/Unix-style local engine (xuezh) that stores facts, runs mechanical transforms, and produces bounded reports/audio artifacts. Use for review, speaking/tones, graded input, and HSK audits.

not rated 43 3mo ago A 63 tokens AGPL-3.0

deep-recon

6916

kvarnelis/deep-recon

Skill Claude Code

Run extended multi-agent reconnaissance sessions. Use when asked to brainstorm deeply, explore ideas from multiple angles, or generate a structured recon document.

not rated 43 6mo ago A 31 tokens original MIT

basehub-ai/forums

Skill Claude Code

React and Next.js performance optimization guidelines from Vercel Engineering. This skill should be used when writing, reviewing, or refactoring React/Next.js code to ensure optimal performance patterns. Triggers on tasks involving React components, Next.js pages, data fetching, bundle optimization, or performance…

not rated 43 1mo ago A 67 tokens GPL-3.0

write-like-paul-graham

6918

criccomini/write-like-paul-graham

Skill Claude CodeCodex

Analyze and apply high-level essay traits extracted from the local distilled reference set for clear, thesis-first nonfiction writing. Use when the assistant needs to draft or revise essays, blog posts, memos, or argument-heavy prose with conversational clarity, sharp distinctions, concrete examples, compact…

not rated 43 5mo ago A 92 tokens original MIT

karl-marx

6920

youaifuou/karl-marx-skill

Skill Claude CodeCodex

A role-based framework for analysing social, economic, and political issues through Karl Marx’s ideas, including historical materialism, which explains society through material conditions and class relations. It can respond in Chinese or English and switches between brief and detailed analysis.

not rated 43 5mo ago A 111 tokens original MIT

gpt-image-2

6922

pilioai/skills

Skill Claude CodeCodex

Create or edit images with Pilio GPT Image 2 through the unified Pilio developer API. Use when the user wants text-to-image generation, prompt-based image editing, restyling, product-photo transformation, or composition from one or more local reference images.

not rated 43 1mo ago A Socket: warnSnyk: warnSkillSpector: warn 58 tokens original MIT

cogapp-markdown

6923

simonw/skills

Skill Claude CodeCodex

Use cogapp to auto-generate sections of markdown documentation by embedding Python code that produces content. Use when a project needs to keep documentation in sync with code, such as embedding CLI --help output in README files, generating tables, or any content that should be derived from the code itself rather than…

not rated 43 6mo ago A 68 tokens

xhs-images

6924

manwithshit/xhs-images

Skill Claude CodeCodex

A generator for Xiaohongshu, also called Little Red Book, a Chinese social platform, that turns written content into a series of cartoon-style infographic images. It supports different visual styles and information layouts.

not rated 43 +1 8mo ago A 60 tokens original MIT

ida-cli

6925

ze-mu-zhou/IDACLI

Skill Claude CodeCodex

Use this skill when Claude Code needs to drive local IDA Pro or Hex-Rays through the IDA-CLI AI-only JSONL kernel, run IDAPython/idalib analysis from a CLI subprocess, collect artifacts, use AI helper APIs, persist caches, merge mutation records, or inspect binaries without opening IDA GUI panels.

not rated 43 1mo ago A SkillSpector: pass 70 tokens original MIT

sota-scan

6926

MerlijnW70/sota-scan

Skill Claude CodeCodex

Benchmark the current repo against the state of the art by scanning real online repos (GitHub and the wider web) in the same domain, then produce a cited capability matrix and a ranked, repo-grounded gap list. Use when the user asks "is our X top-tier", "what are we missing", "compare us to the best", "study online…

not rated 43 2mo ago A 89 tokens original MIT

changelog-summarizing

6927

shopwareLabs/ai-coding-tools

Skill Claude Code

Use this skill when the user asks to summarize, recap, or post about repository changes in the Shopware AI Coding Tools marketplace since a given date — phrases like "write a changelog post for Discord", "recap this week's commits for Slack", "summarize what shipped since 2026-04-01", "draft a release announcement".…

not rated 43 yesterday A SkillSpector: pass 106 tokens original MIT

newsmcp

6928

pranciskus/newsmcp

Skill Claude CodeCodex

Real-time world news briefings with AI-clustered events, topic classification, and geographic filtering. No API key needed.

not rated 43 +1 6mo ago A 29 tokens original MIT

monty-codeact

6929

jsturtevant/copilot-codeact-plugin

Skill Claude CodeCodex

CodeAct via Monty. Use when looping over many files (8+), cross-referencing results from multiple sources, aggregating data across directories, or chaining 5+ dependent tool calls. Collapses N round-trips into one sandboxed Python run via scripts/codeact.py. NOT beneficial for <5 files or simple grep-then-view …

not rated 43 +1 4mo ago A 182 tokens

datafactory-tips

6930

microsoft/DataFactory.MCP

Skill Claude CodeCodex ✓ vendor

Operational tips and best practices for working with Microsoft Fabric Data Factory MCP tools. Use when executing queries, troubleshooting timeouts, creating dataflows end-to-end, or working with large datasets via the DataFactory.MCP tools.

not rated 43 +1 today A SkillSpector: pass 49 tokens original MIT

followup-advanced

6931

DGouron/review-flow

Skill Claude CodeCodex

Follow-up review that never trusts a commit message — always re-reads the actual diff before resolving a thread. Cites a real source for new issues, matching review-advanced.

not rated 43 7d ago A SkillSpector: warn 41 tokens original MIT

clawmoat

6932

darfaz/clawmoat

Skill Claude CodeCodex

Real-time AI agent security scanner. Detects prompt injection, jailbreak attempts, credential/secret leaks, PII exposure, and dangerous tool calls. Activate when: (1) scanning inbound messages or tool outputs for prompt injection, (2) checking outbound content for credential leaks or PII, (3) auditing agent session…

not rated 43 1mo ago A SkillSpector: warn 107 tokens original MIT

linkedin-review

6933

TrainWithShubham/skills

Skill Claude CodeCodex

Review a LinkedIn profile like a recruiter, a career coach, and LinkedIn's own ranking algorithm together — produce a Recruiter Verdict (FOUND & CLICKED / FOUND, PASSED / NOT FOUND), a 100-point score across 6 dimensions, an estimated SSI (Social Selling Index) score with the candor that SSI is a self-diagnostic not a…

not rated 43 4mo ago A 387 tokens original MIT

wuchubuzai2018/expert-skills-hub

Skill Claude CodeCodex

A design tool for creating the image materials used on WeChat red-envelope covers. It produces cover images, decorative attachments, speech-bubble attachments, and cover-story materials designed for WeChat’s submission rules.

not rated 43 +1 18d ago A 97 tokens

unity-cli

6935

niqibiao/unity-cli-skill

Skill Claude CodeCodex

Drive a live Unity Editor or Player with unity-cli. Use when a task must inspect or change Unity scenes, GameObjects, components, transforms, prefabs, materials, ScriptableObjects, project assets, play mode, screenshots, profiler recording, Unity Test Framework runs, or execute C# inside Unity; also use for Unity…

not rated 43 +1 12d ago B SkillSpector: warn 105 tokens original Apache-2.0

toolbelt

6936

signalridge/dotfiles

Skill Claude CodeCodex

Inventory of the CLI tools actually installed on this machine (aqua/mise/nix) and which one to reach for per task — search, structural rewrite, structured data, diff, HTTP, profiling, VCS, k8s, security, docs, media. Use when picking a command-line tool, when a POSIX default (grep/find/sed/curl/wc) feels clumsy, when…

not rated 43 today A 160 tokens

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: