Everything for Claude Code

Skills, subagents, slash commands, hooks, settings, plugin bundles and MCP servers that install into Claude Code. 389,250 indexed, measured the same four ways as everything else here.

rust-doctor

14713

arthjean/rust-doctor

Skill Claude CodeCodex

Use when Rust code just changed and must not regress, when the user asks to scan, audit or health-check a Cargo workspace, says "rust-doctor", or wants one of its findings explained, tuned or switched off.

not rated 23 changed yesterday A SkillSpector: warn 49 tokens original Apache-2.0

im-media

14714

tmwgsicp/im-cli-bridge

Skill Claude CodeCodex

Send voice messages, generate/send images, and send files/videos through IM. TRIGGER when user asks: send voice/audio, generate/send images, send files/documents, send videos. DO NOT trigger for regular text conversations.

not rated 23 15d ago A 48 tokens

cafe24-smart-design

14715

kimyoungwopo/cafe24-smart-design

Skill Claude CodeCodex

Cafe24 Smart Design module, variable, and modifier reference for building and editing Cafe24 e-commerce store templates. Use when working with Cafe24 skin HTML files, modules (module="..."), variables ({$...}), modifiers (|cut, |display, etc.), or any Cafe24 storefront template code.

not rated 23 changed 9d ago A 67 tokens original MIT

research-gap-finder

14716

LengFeng00/research-gap-finder

Skill Claude CodeCodex

Analyze scientific literature to identify research gaps and generate testable hypotheses. Use when users upload research papers (PDF), ask to "find research gaps", "generate hypotheses", "analyze literature", or "evaluate field progress". Automatically triggers for scientific paper analysis, literature review…

not rated 23 +1 8mo ago A 77 tokens original MIT

mtg-mcp-server

14717

j4th/mtg-mcp-server

MCP server Claude CodeCodexCursor +2

Magic: The Gathering card search, combo lookup, draft analytics, and Commander tools. Runs locally from the mtg-mcp-server Python package. Needs 13 environment variables to run.

not rated 23 +3 28d ago A tokens not measured original MIT

diataxis

14718

keithpatton/diataxis-agent-skill

Skill Claude CodeCodex

Classify, validate, generate, and audit documentation using the Diátaxis framework. Enforces quadrant purity across tutorials, how-to guides, reference, and explanation. Use when creating documentation, reviewing docs, auditing doc sets, restructuring existing content, or when the user mentions Diátaxis, documentation…

not rated 23 9mo ago A 69 tokens CC-BY-SA-4.0

mck-speech-design-skill

14720

likaku/Mck-speech-design-skill

Skill Claude CodeCodex

Generate tailored, persona-fitted speech scripts and presentation talking points from user-provided materials (slides, briefs, notes, docs). This skill should be used when a user wants to write a speech, create talking points, draft a keynote script, prepare presentation notes, or generate an executive speaking…

not rated 23 +1 8mo ago A 174 tokens original Apache-2.0

singlefile-mcp

14721

kwinsch/singlefile-mcp

MCP server Claude CodeCodexCursor +2

MCP server for intelligent web content extraction using single-file and trafilatura. Runs locally from the singlefile-mcp Python package.

not rated 23 1y ago A tokens not measured original MIT

weirdo-tv

14722

BeamusWayne/WeirdoTV-Skill

Skill Claude CodeCodex

A role-playing tool that imitates the extreme speaking styles of more than 20 internet personalities and meme figures. It supports solo responses, random selection, debates, topic comments, and group discussions.

not rated 23 +1 6mo ago A 156 tokens original MIT

tianya-gods-team

14723

momozi1996/tianya-skills

Skill Claude CodeCodex

A Chinese-language multi-agent decision system that asks 20 themed fictional or public-forum personas to analyze a question in parallel, then combines their views into one report.

not rated 23 6mo ago A 230 tokens copy · 100% MIT

claude-code-status-bar

14724

briansmith80/claude-code-status-bar

Plugin Claude Code

Bundles 2 commands · 24 tokens together

Warns you before a rate limit or auto-compact, not after. A pure-bash Claude Code status bar (no jq, Node optional) for macOS, Linux, and Windows: usage pacing + burn-rate forecast, context warnings, live activity, cost, git, and 8 themes.

not rated 23 changed 11d ago A tokens not measured original MIT

connapse

14725

Destrayon/Connapse

MCP server Claude CodeCodexCursor +2

MCP server "connapse" as configured in Destrayon/Connapse. Runs in Docker (ghcr.io/destrayon/connapse:v0.3.2).

not rated 23 +1 yesterday A tokens not measured original MIT

jwt-validate

14726

jsonwebtoken/jwt-skills

Skill Claude CodeCodex

Verify and validate JSON Web Tokens (JWTs) by checking signatures, expiration, claims, and structure. Use when the user wants to verify, validate, or check a JWT — e.g. "verify this token", "is this JWT valid", "check the signature", "validate this token against my JWKS", "is this token expired". Supports HMAC, RSA…

not rated 23 +3 7mo ago A Socket: passSnyk: pass 95 tokens

daily-alpha-scanner

14727

zhuyansen/daily-alpha-scanner

Skill Claude CodeCodex

One-click daily alpha scanner that runs a full 5-step on-chain research pipeline using OKX OnchainOS: (1) Hot Token Discovery with narrative categorization (AI, Meme, DeFi, Infra), (2) Smart Money / KOL / Whale buy-signal tracking with sold-ratio scoring, (3) Meme Coin launchpad scanning (pump.fun, fourmeme) with dev…

not rated 23 6mo ago C 227 tokens original MIT

image-production

14728

danielrosehill/Claude-Image-Production-Plugin

Plugin Claude Code

Bundles 29 skills, 19 commands · 2,027 tokens together

Claude Code plugin for image editing, batch operations, format conversion, and filesystem organisation of image libraries — bucket by resolution, aspect ratio, orientation, format, EXIF capture time, camera, and dedupe duplicates / near-duplicates.

not rated 23 +1 changed 4d ago A tokens not measured copy · 77% MIT

verify-agent

14729

DarioFontanel/verify-agent

Skill Claude CodeCodex

Adversarial cross-model verification of work produced by an AI agent — code, documents, data, config, anything. A different model attacks the work against its brief, Claude arbitrates. Triggers on /verify-agent — or natural language like "verifica il lavoro che ha fatto l'agente", "è corretto quello che ha fatto…

not rated 23 2mo ago A SkillSpector: pass 101 tokens original MIT

srunx

14730

ksterx/srunx

MCP server Claude CodeCodexCursor +2

MCP server "srunx" as configured in ksterx/srunx. Runs locally from the srunx[mcp] Python package.

not rated 23 yesterday A tokens not measured original Apache-2.0

vibemk

14731

chexma/vibeMK

MCP server Claude CodeCodexCursor +2

vibeMK - CheckMK monitoring via LLM - MCP Server. Runs locally from the vibemk Python package. Needs 7 environment variables to run.

not rated 23 changed 1mo ago A tokens not measured GPL-3.0

olk

14732

rlrghb/olkcli

Skill Claude CodeCodex

Microsoft Outlook and OneDrive CLI and MCP for email, calendar, contacts, tasks, and files, for personal and enterprise accounts.

not rated 23 changed 1mo ago A 28 tokens original MIT

cargo

14733

getcargohq/cargo-skills

Plugin Claude Code

Bundles 20 skills, 2 agents · 3,644 tokens together

Cargo is go-to-market infrastructure for AI agents. These 19 skills let your agent build B2B lead and account lists, find and verify work emails, enrich companies and contacts from 50+ licensed data providers, score leads, sync your CRM (HubSpot, Salesforce, Attio and 140+ other tools), and watch buying signals like…

not rated 23 +1 changed yesterday A tokens not measured original MIT

cost-analysis

14734

tinh2/skills-hub-registry

Skill Claude CodeCodex

Analyzes infrastructure costs at 1K-100K user scales by reading the actual codebase, auto-detecting cloud providers, modeling per-action costs, and projecting total monthly spend with optimization recommendations.

not rated 23 +1 21d ago A 44 tokens

open-browser-control

14736

smankoo/open-browser-control

MCP server Claude CodeCodexCursor +2

Give AI agents control of your browser (Chrome or Firefox). Works with any MCP client. Runs locally from the open-browser-control npm package.

not rated 23 +2 6d ago A tokens not measured 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: