ai skills

25,660 tagged ai, measured the same way as everything else here.

Browse within: LLM 584agent 538cli 374chatgpt 282agents 206LangChain 145ml 144generative-ai 131cybersecurity 129hacking 125bun 118chatbot 118agentic 116mcp-server 83

skill-creator

289

qhkm/zeptoclaw

Skill Claude CodeCodex

Create or update ZeptoClaw skills. Use when designing, structuring, or authoring new agent skills.

not rated 651 +1 today A SkillSpector: warn 27 tokens original Apache-2.0

librechat-docs

290

LibreChat-AI/librechat.ai

Skill Claude CodeCodex

Use the official LibreChat documentation to install, configure, operate, and troubleshoot LibreChat.

not rated 643 +2 today A SkillSpector: warn 24 tokens original MIT

agent-builder

291

TesslateAI/OpenSail

Skill Claude CodeCodex

Draft new agents and attach scheduled automations to them. Depth-1 cap; drafts only — a human must publish via the UI.

not rated 642 +2 yesterday A SkillSpector: pass 30 tokens original Apache-2.0

debug-helper

292

JackyST0/awesome-agent-skills

Skill Claude CodeCodex

Help debug code by analyzing error messages, identifying root causes, and providing fix suggestions.

not rated 634 +2 2d ago A SkillSpector: pass 20 tokens original CC0-1.0

nubase

293

OtterMind/Nubase

Skill Codex

Use when the user mentions Nubase broadly, wants a backend for an AI-generated app, or needs to deploy/publish generated code online — across Database, Auth, Storage, Assets (static frontend CDN), Functions (edge/serverless), AI Gateway, Memory, cron/scheduled jobs, Supabase-style REST/RLS, servicerole keys, or MCP.…

not rated 627 +2 24d ago A SkillSpector: warn 92 tokens original Apache-2.0

vendo-setup

294

runvendo/vendo

Skill Claude CodeCodex

Install and configure Vendo (the embedded product agent) in a host repo. Use when asked to add Vendo to an app, run vendo init/doctor/sync, wire the Vendo handler or VendoProvider, or debug a Vendo install.

not rated 614 +9 9d ago A SkillSpector: warn 56 tokens original Apache-2.0

nw-distill

295

nWave-ai/nWave

Skill Claude Code

Acceptance test creation methodology for the DISTILL wave. Domain knowledge for the acceptance designer agent: port-to-port principle, prior wave reading, wave-decision reconciliation, graceful degradation, and document back-propagation.

not rated 610 +5 5d ago A SkillSpector: warn 46 tokens original MIT

tandem-browser

296

hydro13/tandem-browser

Skill Claude Code

Use Tandem Browser's MCP server (local and remote agents) or HTTP API (local and remote agents) to inspect, browse, and interact with the user's shared browser safely. Prefer targeted tabs and sessions, use snapshot refs before raw DOM or JS, verify action completion explicitly, and leave durable handoffs instead of…

not rated 606 +2 today D 72 tokens original MIT

java-coding-standards

297

Snailclimb/AIGuide

Skill Codex

A set of conventions for writing, reviewing, refactoring and explaining Java and Spring Boot code. It covers common application layers such as controllers, services and data-access code, while allowing repository-specific rules to take priority.

not rated 605 +7 2mo ago A 144 tokens

mcp-scripting

298

Zhou-Shilin/Aether

Skill Claude CodeCodex

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

not rated 599 +5 5d ago A SkillSpector: pass 21 tokens GPL-3.0

api-reference

299

matrixorigin/memoria

Skill Claude CodeCodex

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

not rated 594 +2 today A SkillSpector: warn 27 tokens original Apache-2.0

coolify

300

StuMason/coolify-mcp

Skill Claude CodeCodex

Operate a Coolify self-hosted PaaS through the @masonator/coolify-mcp server. Use this skill whenever the user asks Claude to inspect, deploy, restart, debug, or manage anything on Coolify — including applications, databases, services, servers, projects, environments, deployments, environment variables, private keys…

not rated 589 +10 changed 2d ago A SkillSpector: warn 156 tokens original MIT

data_analysis

301

ArtificialAnalysis/Stirrup

Skill Claude CodeCodex

High-performance data analysis using Polars - load, transform, aggregate, visualize and export tabular data. Use for CSV/JSON/Parquet processing, statistical analysis, time series, and creating charts.

not rated 599 +9 17d ago A 44 tokens copy · 100% MIT

video-clip-extractor

302

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 560 +3 17d ago B SkillSpector: warn 128 tokens original MIT

skilldeck

303

crossoverJie/SkillDeck

Skill Claude CodeCodex

Manage AI agent skills via natural language — install, update, delete, and assign skills to agents using SkillDeck's filesystem conventions.

not rated 558 +3 2mo ago A ✓ AI review SkillSpector: warn 29 tokens original MIT

chinese-writing

304

miantiao-me/aigc-weekly

Skill OpenCode

A Chinese-language writing skill for producing weekly issues, blog posts, and technology-news articles.

not rated 557 +1 10d ago A Socket: passSnyk: passSkillSpector: pass 25 tokens AGPL-3.0

hatayama/unity-cli-loop

Skill Claude CodeCodex

Get Unity project information via uloop CLI. Use when you need to check project settings, Unity version, platform, or other project metadata.

not rated 559 +10 changed 10d ago A SkillSpector: pass 34 tokens original MIT

story-long-write

306

uu201/character-arc

Skill Claude CodeCodex

A Chinese-language coaching workflow for creating a long online novel from the initial idea through the outline and chapter text. It starts by defining the intended emotion, then uses research and story-planning stages to guide writing.

not rated 559 +7 today A SkillSpector: pass 81 tokens original MIT

repo-auditor

307

oxbshw/LLM-Agents-Ecosystem-Handbook

Skill Claude CodeCodex

Use before opening a PR to audit the changes for stale comments, unused imports, missing tests, and inconsistencies with neighboring code.

not rated 546 +3 2mo ago A SkillSpector: pass 31 tokens original MIT

ralph-specum-design

308

tzachbon/smart-ralph

Skill Codex

This skill should be used only when the user explicitly asks to use $ralph-specum-design, or explicitly asks Ralph Specum in Codex to run the design phase.

not rated 536 +4 changed 7d ago A SkillSpector: warn 41 tokens original MIT

vet

309

imbue-ai/vet

Skill Claude CodeCodex

Run vet immediately after ANY logical unit of code changes. Do not batch your changes, do not wait to be asked to run vet, make sure you are proactive.

not rated 536 +3 3mo ago B Socket: passSnyk: warn 35 tokens AGPL-3.0

workflow-creator

310

deerwork-ai/deer-workflow

Skill Claude CodeCodex

Create or revise runnable Deer Workflow orchestration modules from a user's task description. Use this skill whenever the user asks to turn a repeatable multi-step task into a Workflow, generate a deer-workflow script, coordinate several Agent Loops with parallel or pipeline, or repair a Workflow that assumes APIs are…

not rated 533 +6 1mo ago A SkillSpector: pass 66 tokens original MIT

truecourse-hooks

311

truecourse-ai/truecourse

Skill Claude Code

Install, configure, or remove the TrueCourse pre-commit hook.

not rated 528 +1 today A SkillSpector: warn 17 tokens original MIT

nurb

312

Shpigford/nurb

Skill Claude CodeCodex

Design 3D-printable parts as Python functions with nurb. Use when the user wants a part designed, changed, or checked for 3D printing (a bracket, mount, holder, enclosure, shelf, or any STL/STEP to print), and in any directory with a parts/ folder. The user describes the part and judges it in a browser; you model it.

not rated 516 +13 changed 4d ago A Socket: warnSnyk: fail 81 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: