Every mod

All nine kinds in one list: what an agent loads, what it runs, what it reads and what bundles the rest. 418,976 of them, each with its token cost per session, a security scan with the line that triggered it, and whether it is the original or one of the copies.

test-writer

9626

anchildress1/awesome-github-copilot

Skill Claude CodeCodex

Write, extend, or review tests in any codebase. Use this skill whenever the user asks to write tests, add test coverage, test a new feature, fix failing tests, or audit existing test files — regardless of language, framework, or project. Also trigger for "add tests for", "write tests for", "cover this with tests"…

not rated 66 11d ago A SkillSpector: pass 130 tokens original MIT

research

9627

hugobowne/show-us-your-agent-skills

Skill Claude Code

Build, extend, AND query a persistent LLM-maintained wiki for any research topic. Conversational entry point that routes between four modes — query (read-only Q&A against existing research with optional Q&A save-back), init (new topic ingest), append-deep (add sources to existing topic via short rounds), and…

not rated 66 +1 1mo ago A SkillSpector: pass 216 tokens original MIT

mcp-zap-server

9628

dtkmn/mcp-zap-server

MCP server Claude CodeCodexCursor +2

MCP server "mcp-zap-server" as configured in dtkmn/mcp-zap-server. Runs in Docker (ghcr.io/dtkmn/mcp-zap-server:v0.8.0). Needs 8 environment variables to run.

not rated 66 today A tokens not measured original Apache-2.0

ss

9629

MartyBonacci/specswarm

Plugin Claude Code

Bundles 10 skills, 34 commands, 6 agents, 4 hooks · 2,084 tokens together

SpecSwarm: complete software development toolkit. Spec-driven workflows, multi-agent orchestration, lifecycle management Build->Modify->Fix->Ship. Commands available at /ss:.

not rated 66 1mo ago A tokens not measured original MIT

minirag-mcp

9630

sfrangulov/minirag-mcp

MCP server Claude CodeCodexCursor +2

Local-first RAG MCP server: hybrid search over your documents, fully local. Runs locally from the minirag-mcp Python package. Needs 13 environment variables to run.

not rated 66 +2 18d ago A Socket: warn tokens not measured original MIT

langflow-input-types

9631

Empreiteiro/langflow-factory

Cursor rule Cursor

This document provides a comprehensive guide to all input types available in Langflow. Each input type is designed for specific use cases and data formats.

not rated 66 +1 29d ago A 5,974 tokens

mckinsey-consultant

9633

Mann1988/awesome-claude-skills

Skill Claude CodeCodex

A consulting style method for breaking business questions into structured analyses and producing research reports or presentations.

not rated 66 +1 2d ago A SkillSpector: pass 82 tokens original MIT

git-history-recon

9634

Jamie-BitFlight/claude_skills

Skill Claude Code

Analyze git repository history to produce a codebase risk profile before code review. Probes repo size, runs 7 parallel git analysis pipelines (hotspots, bug magnets, bus factor, contributor momentum, firefighting frequency, newly added files), cross-references hotspots with bug magnets to identify high-risk files…

not rated 66 changed 20d ago A SkillSpector: pass 113 tokens original MIT

model curator

9635

amalik/convoke-agents

Agent Claude Code

Model Curator - Contextual capabilities model generation and curation.

not rated 66 changed 7d ago A 15 tokens original MIT

VapiAI/skills

Skill Claude CodeCodex

Opt-in recreation of the Bun + TypeScript framework used to build Vapi's landing-page voice agents from a ROUGHDRAFT.md spec, including a scenario registry, language stacks, prompt composer, assistant builder, and idempotent bootstrap script. Use only when the user explicitly invokes vapi-bootstrap-framework or…

not rated 66 14d ago A 123 tokens

cinematic-ui

9637

akseolabs-seo/cinematic-ui

Cursor rule Cursor

Apply when the user asks for a cinematic website, film-style landing page, director-inspired UI, or any design framed around a movie aesthetic. Do not apply for generic web design unless the user explicitly references a film, director, or cinematic style.

not rated 66 +1 5mo ago A 49 tokens original MIT

lighter-agent-kit

9638

elliottech/lighter-agent-kit

Skill Claude Code

Query Lighter DEX market data on Lighter and Robinhood Lighter (orderbooks, trades, candles, funding rates) and execute trades (limit and market orders, modify, cancel, leverage, margin, withdraw, spot and perp transfers) on perpetual and spot markets. Use when the user mentions Lighter, zkLighter, perps, perpetual…

not rated 66 +2 1mo ago C 94 tokens original MIT

remove-ai-marks

9639

anshaneja5/markscrub

Skill Claude CodeCodex needs its repo

Scrub AI provenance marks from text and files using the markscrub CLI: invisible Unicode (Layer A), optional statistical rewrite (Layer B), and C2PA/EXIF/XMP/container metadata on PNG/JPEG/SVG/PDF/DOCX/HTML/MD. Use when the user asks to strip watermarks, remove Content Credentials, clean AI metadata, remove invisible…

not rated 66 22d ago A SkillSpector: warn 91 tokens original MIT

packaging-workshop

9640

taxueseek/say-it-human

Skill Claude CodeCodex

A final presentation review for finished Chinese content. It works on the title, opening, layout, punctuation, images, and platform format without changing the main body.

not rated 66 +1 1mo ago A SkillSpector: pass 242 tokens original MIT

yongge-restaurant

9641

Astro-wen/yongge-restaurant-skill

Skill Claude CodeCodex

A Chinese-language decision assistant for restaurant entrepreneurship, covering choices such as opening a shop, joining a franchise, selecting a location, and checking profitability.

not rated 66 4mo ago A 196 tokens original MIT

md-to-docx

9642

pickle-an/md-to-docx-skill

Skill Claude CodeCodex

A document conversion tool that turns Markdown, a plain-text writing format, into a formatted DOCX Word document.

not rated 66 5mo ago A 47 tokens

luna-chat-coder

9643

Osteoporosis/luna-chat-coder

Skill Claude CodeCodex

Keep repository development reliable from chat by using the sandbox work container first, recovering exact GitHub state, and using bounded Actions missions when normal sandbox or GitHub paths are insufficient.

not rated 66 +2 changed 19d ago A SkillSpector: warn 41 tokens original MIT

development

9644

stbenjam/skillsaw

Cursor rule Cursor

You must follow these instructions when developing skillsaw.

not rated 66 changed 5d ago A 10 tokens original Apache-2.0

brand-toolkit

9645

jgerton/brand-toolkit

Plugin Claude Code

Bundles 10 skills, 1 command, 1 agent · 659 tokens together

Methodology-grounded brand building toolkit. Positioning, messaging, voice, visual identity, audit, and competitive analysis powered by Dunford, Miller, Neumeier, and NN/g frameworks.

not rated 66 +2 5mo ago A tokens not measured original MIT

voiceprint

9646

charlie947/voiceprint

Skill Claude CodeCodex

Use when writing an article, newsletter, blog post or long social post that must genuinely be the user's own writing. Triggers on "voiceprint", "write this in my voice", "turn my recording into an article", "cut my transcript down", "make this actually mine", "write from my video". Turns the user's own spoken words…

not rated 66 1mo ago A SkillSpector: warn 83 tokens original MIT

musicfree-plugin-dev

9647

maotoumao/musicfree-skills

Skill Claude CodeCodex

A guide for developing plugins for MusicFree, a music-player application, including plugins that connect it to a music website or API.

not rated 66 +2 6mo ago A 109 tokens AGPL-3.0

GitHub-Zero123/MCDevTool

Skill Claude CodeCodex

A workflow for testing Minecraft Bedrock Addons, Python 2 mods, interfaces, gameplay logic, and visual resources with MCDK-MCP. MCP is a way for an AI coding agent to call external testing tools.

not rated 66 changed 9d ago A SkillSpector: pass 0 tokens original BSD-3-Clause

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: