LLM skills

9,502 tagged LLM, measured the same way as everything else here.

Browse within: agent 493chatgpt 237agents 207cli 167ml 133bun 131agent-framework 124javascript 124agentic-ai 116openai 116deep-learning 107openclaw 99foundation-models 98open-source 93

gmail-email

145

open-gitagent/gitagent

Skill Claude CodeCodex

Send emails via Gmail SMTP using App Password authentication.

not rated 677 +9 19d ago A SkillSpector: pass 13 tokens original MIT

agent-style

146

yzhao062/agent-style

Skill Claude CodeCodex

Literature-backed English technical-prose writing rules. Use when writing or editing prose in .md, .tex, .rst, or .txt files, especially research papers, proposals, documentation, and release notes.

not rated 672 +10 5d ago A 46 tokens

content-angle-ranker

147

Affitor/affiliate-skills

Skill Claude CodeCodex

Rank content angles by engagement data, competition level, and platform fit. Data-driven angle selection instead of guesswork. Use this skill when the user has a keyword or product and needs to decide WHAT to create, which angle to take, which format to use, or which platform to target. Triggers on: "what angle should…

not rated 652 +12 3d ago A SkillSpector: pass 175 tokens original MIT

echo-custom-mcp

148

truffle-ai/dexto

Skill Claude CodeCodex

Use bundled skill files for quick skill bundle checks.

not rated 649 today A 10 tokens

node-tools

150

sno-ai/mda

Skill Claude CodeCodex

Run a TypeScript script via tsx to fetch an HTTP endpoint and stream the response. Use when you need a small Node.js helper for HTTP calls.

not rated 616 3mo ago A 34 tokens original Apache-2.0

actionbook

151

smallnest/goclaw

Skill Claude CodeCodex

This skill should be used when the user needs to automate multi-step website tasks. Activates for browser automation, web scraping, UI testing, or building AI agents. Provides complete action manuals with step-by-step instructions and verified selectors.

not rated 602 +1 5mo ago A 49 tokens original MIT

mcp-scripting

152

Zhou-Shilin/Aether

Skill Claude CodeCodex

Write mcpScript JavaScript for discovering, inspecting, and calling MCP tools.

not rated 598 +5 3d ago A SkillSpector: pass 21 tokens GPL-3.0

sou350121/VLA-Handbook

Skill Claude CodeCodex

Adversarial research analysis framework that uses structured Bull/Bear/Arbiter debates to help users make better research judgments. Maintains a belief graph as backend engine, applies statistical calibration discipline, tracks phase transitions, and detects biases. MANDATORY TRIGGERS: Use this skill whenever the user…

not rated 599 +8 today A SkillSpector: warn 179 tokens CC-BY-4.0

api-reference

154

matrixorigin/memoria

Skill Claude CodeCodex

Memoria REST API endpoints, request/response formats, auth, rate limits. Use when calling or implementing API endpoints.

not rated 595 +1 today A SkillSpector: warn 27 tokens original Apache-2.0

p5.js

155

agentic-in/elephant-agent

Skill Claude CodeCodex

Production pipeline for interactive and generative visual art using p5.js. Creates browser-based sketches, generative art, data visualizations, interactive experiences, 3D scenes, audio-reactive visuals, and motion graphics — exported as HTML, PNG, GIF, MP4, or SVG. Covers: 2D/3D rendering, noise and particle systems…

not rated 582 +1 12d ago A 152 tokens

video-clip-extractor

156

linzzzzzz/openclip

Skill Claude Code

Processes videos to identify engaging moments, generate transcripts, and create highlight clips with artistic titles and custom cover images. Use when user needs to: extract highlights from long videos or livestreams, clip or cut best moments from videos, cut video highlights, process Bilibili/YouTube URLs or local…

not rated 559 +4 15d ago B SkillSpector: warn 128 tokens original MIT

lynkr

157

Fast-Editor/Lynkr

Skill Claude CodeCodex

Universal LLM gateway with intelligent routing, Graphify code intelligence, Distill compression, routing telemetry, Code Mode, and 12+ provider support. 60-80% cost reduction for Claude Code, Cursor, and Codex.

not rated 547 +1 3d ago A SkillSpector: pass 50 tokens original Apache-2.0

openclaw-auto-dream

158

LeoYeAI/openclaw-auto-dream

Skill Claude CodeCodex

Cognitive memory architecture for OpenClaw agents — periodic dream cycles that consolidate daily logs into structured long-term memory with importance scoring, insights, and push notifications. Use when: user asks for 'auto memory', 'dream', 'auto-dream', 'memory consolidation', 'memory dashboard'. Powered by…

not rated 547 +2 5mo ago A 79 tokens original MIT

pptx

159

antgroup/agentic-ai-landscape

Skill Claude CodeCodex

Use this skill any time a .pptx or .potx file is involved in any way — as input, output, or both. This includes: creating slide decks, pitch decks, or presentations; reading, parsing, or extracting text from any .pptx or .potx file (even if the extracted content will be used elsewhere, like in an email or summary)…

not rated 543 2d ago A 171 tokens

wdoc-skill

160

thiswillbeyourgithub/wdoc

Skill Claude CodeCodex

Comprehensive reference for wdoc, a RAG CLI and Python library that summarizes, searches, and queries documents across 20+ filetypes (PDF, YouTube, audio, Anki, web, Zotero, Karakeep, and more) through LiteLLM (100+ LLM providers). Use when the user runs or asks about the wdoc command, imports from wdoc import wdoc…

not rated 541 +1 15d ago A 121 tokens AGPL-3.0

token-optimization

161

ooples/token-optimizer-mcp

Skill Claude CodeCodex

Use the token-optimizer MCP tools to reduce context/token usage when reading, searching, or editing files, or when the context window is filling up. Trigger when reading large files, re-reading files already seen, searching a big/unknown tree, making edits to large files, or when you need to store bulky output…

not rated 509 +1 today A SkillSpector: pass 71 tokens original MIT

Th0rgal/sandboxed.sh

Skill Claude CodeCodex

How Hermes monitors and steers long-running sandboxed.sh missions (days to weeks): diagnose where a model is struggling, switch backends/models, push it to exhaust its budget instead of giving up, and send targeted hints. Trigger terms: mission, sandboxed.sh, babysit, monitor, /goal, switch backend, stalled, resume…

not rated 507 +9 changed today A 94 tokens

background-watch-hook

163

avibe-bot/avibe

Skill Claude CodeCodex

Use vibe watch to run a managed Harness waiter that returns to the same conversation later. Best for reviews, CI, files, logs, and other wait-now-continue-later workflows.

not rated 499 +3 today A SkillSpector: warn 44 tokens original MIT

intelligencedev/manifold

Skill Claude CodeCodex

Author WARPP workflows for Manifold as typed-port dataflow JSON. Use when a user asks to build, create, design, generate, or edit a Flow / workflow / automation / pipeline / DAG in Manifold, or mentions WARPP, workflow nodes, or the /flow builder. Covers the document format, port types and coercions, the builtin node…

not rated 497 1mo ago A SkillSpector: pass 103 tokens original MIT

clawdotnet/openclaw.net

Skill Claude CodeCodex

Extract structured insight briefs from community research transcripts or notes. Produces pain points, stakeholder needs, opportunity maps, risks, and follow-up questions. Requires human review before publication.

not rated 497 +9 today A SkillSpector: pass 41 tokens original MIT

workflow-patterns

166

QuintinShaw/pi-dynamic-workflows

Skill Claude CodeCodex

Argument shapes for the 5 built-in workflow patterns — deep-research, adversarial-review, code-review, multi-perspective, codebase-audit — runnable via the workflow tool's name input, without slash-command syntax. Use for requests like "research X", "fact-check/adversarially review this", "review this diff/PR"…

not rated 498 +11 5d ago A SkillSpector: pass 108 tokens original MIT

kicad-library

167

mixelpixx/Konnect

Skill Claude Code needs its repo

Library management workflow for KiCAD — creating symbols, footprints, and managing libraries via MCP tools. Triggers on: "create a symbol", "make a footprint", "custom component", "register library", "find a part", "pin numbering", "new symbol", "new footprint", "add to library", "library path", "pad layout".

not rated 543 +102 yesterday A SkillSpector: pass 77 tokens AGPL-3.0

make-trace

168

AIScientists-Dev/Flowtrace

Skill Claude CodeCodex

Turn any source that describes how a kind of task gets done (a SKILL.md, a chat log, a runbook, plain prose) into a runnable Morph trace. Lift it into a DAG, write a contract per step, place inputs, and drive the full run lifecycle to verify it. Use whenever someone wants to make a trace from a source.

not rated 488 +2 3mo ago A SkillSpector: warn 76 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: