ai-agent skills

17,533 tagged ai-agent, measured the same way as everything else here.

Browse within: LLM 341agent 300cli 284openclaw 220ai-tools 197chatgpt 193agentic-ai 180cybersecurity 160Multi-Agent 132agentskills 123curated 122myclaw 122skill-collection 121coding-agent 113

gem-pw

1297

lesterppo/hermes-gem-pw

Skill Claude CodeCodex

Browser-automated Gemini Gem CLI (CDP-first) — chat, CRUD, image gen, deep research, --collab surgical-diff review. No API key.

not rated 1 1mo ago A 39 tokens original MIT

power-bi-master

1299

Jignesh-Gond/Power-BI-Master-Skill

Skill Claude CodeCodex

POWER BI MASTER SKILL by JG — The ultimate Power BI Automation and DAX Engineering standard. Master PBIX surgery, Lakh/Crore formatting, and high-performance DAX patterns. Compatible with Gemini CLI, OpenCode, and Agy CLI.

not rated 1 3mo ago A 55 tokens

krx-cli

1300

kyo504/krx-cli

Skill Claude CodeCodex

A command-line skill for querying data from the Korea Exchange (KRX), South Korea’s stock-market operator. It covers stocks, indices, funds, bonds, derivatives, commodities and ESG data.

not rated 1 5mo ago A 128 tokens original MIT

solana-mcp-skill

1301

visioneth/solana-mcp

Skill Claude CodeCodex

This skill teaches AI agents how to interact with the Solana blockchain using the Solana MCP Server.

not rated 1 1mo ago A 0 tokens original MIT

warrant-policy-author

1302

rmanish2000-del/warrant-mcp

Skill Claude Code

Write a warrant-mcp policy in plain English, shaped for the closed rule set so review has the best chance of accepting it first time — only warrant-mcp review can say whether it compiles. Use when the user wants to create or edit .warrant/policy.md, write rules for what an AI agent may do in a project, or asks what…

not rated 1 19d ago A 126 tokens original MIT

shoppingscraper

1303

ShoppingResult/shoppingscraper-cli

Skill Claude CodeCodex

Fetch product data, prices, offers, buy-box winners, variants, and reviews from Google Shopping, Amazon, Bol.com, and Coolblue via the ShoppingScraper API. Use whenever the user asks about marketplace pricing, competitor offers, product matching, or e-commerce SERP positions for a specific EAN/SKU.

not rated 1 1mo ago A 69 tokens original MIT

cold-outreach-sequence

1304

omarkhandji-commits/midas

Skill Claude CodeCodex

When to use. The operator has identified an ICP (ideal customer profile) and wants a deliverability-aware sequence to test it.

not rated 1 1mo ago A 0 tokens original MIT

stars-cash-flow

1307

govRosMedia/stars-cash-flow-mcp

Skill Claude CodeCodex

Order and manage Telegram Stars CPA / SMM services (channel subscribers, boosts, bot starts) via the Stars Cash Flow reseller API. Use when the user wants to buy, price, check or cancel Telegram promotion orders, or check their reseller balance.

not rated 1 3d ago A 55 tokens original MIT

Prove Before Act

1308

jasonxkensei/prove-before-act

Skill Claude CodeCodex

Prove Before Act proof and accountability integration for AI agents. REST API, MCP, and x402. Check live endpoints for availability, pricing, and proof status.

not rated 1 23d ago A 38 tokens

humanread-publisher

1309

humanread-content/humanread-agent-kit

Skill Codex

Design, upload, safely theme, preview, review, and publish Markdown, HTML, text, or isolated HTML+CSS novels through the Humanread MCP server. Use for any Humanread novel creation or publication task.

not rated 1 1mo ago A 48 tokens original MIT

seekbridge-browser

1310

Chang-Hai/seekbridge

Skill Codex

Operate the user's real Chrome through SeekBridge with task-owned tabs, semantic element refs, verified actions, and safe recovery. Use for navigating websites with DeepSeek-powered agents, working in signed-in web apps, collecting page information, filling ordinary forms, testing web interfaces, taking screenshots…

not rated 1 1mo ago A 73 tokens original MIT

spokes

1311

Dente22/Spokes

Skill Claude CodeCodex

Use Spokes MCP before inventing code. Triggers on: implement a feature, build an app, add auth/api/ui, reuse existing code, find how I did this before, check my GitHub repos, avoid reinventing the wheel, pull logic from my projects. Always consult Spokes memory of the user's owned GitHub repositories first.

not rated 1 25d ago A 72 tokens original MIT

screen-use

1312

tongriyaotxt/screen-use

Skill Claude CodeCodex

A Windows desktop automation skill for clicking controls, entering text, using keyboard shortcuts, scrolling, and taking screenshots. It can also carry out multi-step tasks through visual guidance.

not rated 1 18d ago A 58 tokens original MIT

design-mcp-server

1314

cyanheads/federal-reserve-mcp-server

Skill Claude CodeCodex

Design the tool surface, resources, and service layer for a new MCP server. Use when starting a new server, planning a major feature expansion, or when the user describes a domain/API they want to expose via MCP. Produces a design doc at docs/design.md that drives implementation.

not rated 1 23d ago A 62 tokens

bat-submit

1315

bataitools/bat-skills

Skill Claude CodeCodex needs its repo

Submit an AI tool to BAT AI Tools (bataitools.com) via bat-cli CLI. Use a continuous 3-step workflow — extract, translate, then pack and submit.

not rated 1 1mo ago A Socket: warnSnyk: warn 40 tokens original MIT

ck:cook

1316

huuanh20/awesome-ai-agent-skills

Skill Claude Code

Implement a feature phase by phase from a phased JSON master or Markdown plan. Before each phase, confirm whether to create/run unit tests and whether to run ck:quality, unless explicit flags supply those choices. Supports token-budgeted execution, resumable state, and TDD handoff to ck:test.

not rated 1 1mo ago A 64 tokens original MIT

active-recall

1317

AlirezaFakari/annuma-study-companion

Skill Claude CodeCodex

Quizzes the user on AnNuMa (Analysis und Numerische Mathematik) exam topics using active recall. Use this skill whenever the user wants to be tested, quizzed, or drilled on a math topic, or says things like "quiz me", "test me on", "active recall", "flashcard", "ask me questions about", or "let's practice ". The skill…

not rated 1 1mo ago A 132 tokens

amzscout-research

1318

amzscout-corp/amzscout-skill-mcp

Skill Claude CodeCodex

Amazon-seller research using AMZScout tools — analyze a product by ASIN, evaluate a niche / category, pull keyword & PPC data, and explore a brand's Amazon catalog. Use whenever the user asks whether an Amazon product is worth selling, to analyze a niche or its competition, find/discover products, check a listing's…

not rated 1 +1 1mo ago A 125 tokens original MIT

meta-analysis

1319

zamushwani/biomedical-ai-skills

Skill Claude CodeCodex

Systematic review and meta-analysis for clinical and preclinical evidence. Covers protocol registration, search strategy, screening, PRISMA 2020 flow diagrams, risk of bias, pooling with fixed and random effects models, small-study effects, sensitivity diagnostics, network meta-analysis, and GRADE/CINeMA certainty…

not rated 1 14d ago A 0 tokens original MIT

wbrowser

1320

matveikarpov64/Wbrowser

Skill Claude CodeCodex

Use when a task needs a browser that is already signed in — reading a dashboard, checking a web app, filling a form, taking a screenshot of a real page, or debugging a site's console. Drives a real Chrome window the user signed into by hand, so no re-login and no API keys. Do not guess selectors; run wb read first and…

not rated 1 +1 3d ago C 81 tokens copy · 100% 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: