agent skills

11,628 tagged agent, measured the same way as everything else here.

Browse within: LangChain 204generative-ai 179cybersecurity 178hacking 178ai-tools 141samples 128volcengine 128agentic 127bun 127ai-assistant 125ml 124deep-learning 103foundation-models 99agent-framework 98

background-watch-hook

193

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 498 +2 yesterday A 44 tokens original MIT

aristoteleo/PantheonOS

Skill Claude CodeCodex

End-to-end workflow for gene panel design in scRNA-seq and spatial transcriptomics, that should be STRICTLY followed: dataset understanding + smart downsampling + train/test splits, algorithmic selection (HVG/DE/RF/scGeneFit/SpaPROS), optimal sub-panel discovery (ARI vs size), biological completion with a stability…

not rated 482 3d ago A 110 tokens original BSD-2-Clause

computer-use-linux

195

agent-sh/computer-use-linux

Skill Claude CodeCodex

Linux desktop observation and control via native Pi tools or the computer-use-linux MCP server: accessibility trees, screenshots, window targeting, and input synthesis (click, type, scroll).

not rated 482 +4 changed 2d ago A 39 tokens original MIT

hcom-agent-messaging

196

aannoo/hcom

Skill Claude CodeCodex

Multi-agent communication for AI coding tools. Agents message, watch, and spawn each other across terminals. Use when setting up hcom, troubleshooting delivery, or writing multi-agent scripts.

not rated 477 +8 27d ago C 42 tokens original MIT

workflow_creation

197

rome-os/rome

Skill Claude CodeCodex

Build a new Rome workflow app — one action whose body is a single async function that implements its control flow in plain TypeScript (await, if, for, Promise.all) and calls existing actions (including system:summon). Use whenever the user describes a multi-step automation OR asks an LLM to produce something from…

not rated 471 +20 yesterday A 0 tokens original MIT

11-browser-qa

198

ai-driven-dev/framework

Skill Claude Code

Run post-review browser QA and produce short named videos for a locked happy path and sourced browser edge cases. Use when the user wants concise reviewer evidence for a web journey. Not for API, CLI, automated tests, diff review, or application fixes.

not rated 455 +2 yesterday A 55 tokens original MIT

agent-spec-tool-first

199

ZhangHanDong/agent-spec

Skill Claude Code

CRITICAL: Use for agent-spec CLI tool workflow. Triggers on: agent-spec, contract, lifecycle, guard, verify, explain, stamp, checkpoint, plan, requirements, work-units, knowledge requirements, KLL, docs vs knowledge, spec verification, task contract, spec quality, lint spec, run log, "how to verify", "how to use…

not rated 451 +3 7d ago A 165 tokens original MIT

dive-into-langgraph

200

luochang212/dive-into-langgraph

Skill Claude CodeCodex

A comprehensive guide and reference for building agents using LangGraph 1.0, including ReAct agents, state graphs, and tool integrations.

not rated 448 +1 1mo ago A 35 tokens

foreman-tdd

201

VisionForge-OU/foreman

Skill Claude CodeCodex

Stack-agnostic test-driven development loop for a single Foreman issue. Implements one vertical slice with strict red-green-refactor (one test at a time, never horizontal slicing) using the foreman-test wrapper, saves completion evidence, then emits a machine-readable FOREMAN-SUMMARY block Foreman parses.

not rated 448 +1 2mo ago A 67 tokens

obelisk

202

tommy0103/obelisk

Skill Claude Code

A search tool for finding information in past Claude Code, Codex, Kimi Code, and Pi work sessions.

not rated 447 +4 changed 2d ago A 159 tokens AGPL-3.0

bytedance/agentkit-samples

Skill Codex ✓ vendor

Guide a user conversationally through generating a new ad video from a template video and a user-provided product image. The host agent performs video understanding, detailed analysis, and rewrite planning; BytePlus Seedance is used only for final video generation with local product images as generation references.

not rated 446 +2 changed yesterday A 71 tokens original Apache-2.0

slides

204

xpert-ai/xpert

Skill Codex

Create and edit presentation slide decks (.pptx) with PptxGenJS, bundled layout helpers, and render/validation utilities. Use when tasks involve building a new PowerPoint deck, recreating slides from screenshots/PDFs/reference decks, modifying slide content while preserving editable output, adding…

not rated 437 yesterday A 83 tokens AGPL-3.0

yupi-skill

205

liyupi/yupi-skill

Skill Claude CodeCodex

以"程序员鱼皮"的身份、口吻、思维方式回答问题。鱼皮是前腾讯全栈工程师、全网200万+粉丝的AI+编程知识博主、科技公司鱼鸢网络CEO、编程导航创始人。 当用户想要以鱼皮的视角获得编程学习建议、求职指导、项目选型、技术方向判断、创业经验、自媒体运营建议、AI编程实战指导时使用此技能。 也适用于用户明确要求"用鱼皮的风格"或"像鱼皮一样"回答的场景。 覆盖的典型问题包括:编程学习路线、简历怎么写、要不要接某个offer、该学什么技术、怎么做开源、怎么做自媒体、AI时代程序员怎么办、创业踩过哪些坑。.

not rated 425 +4 4mo ago A 192 tokens original MIT

tmux-manual-qa

206

code-yeongyu/senpi

Skill Claude CodeCodex

Run a single manual tmux-based QA scenario for the todo continuation feature against the real CLI (./pi-test.sh) in an interactive TUI. Captures scrollback, asserts deterministic pass/fail count markers, and cleans up test fixtures. Use only for the manual-qa milestone features.

not rated 420 +1 yesterday A 66 tokens original MIT

author-lookup

207

poco-ai/Agentero

Skill Claude CodeCodex

A workflow for finding public contact details and online profiles for a research paper’s first and corresponding authors. It also looks for the paper’s OpenReview page; OpenReview is a website used to publicly discuss and review some research papers.

not rated 420 +11 today A 100 tokens original MIT

importing-a-codebase

208

JetBrains/thinkrail

Skill Claude CodeCodex ✓ vendor

Use when the repo holds real source code but no specs: the existing-codebase branch of setting-up-a-project, normally reached via that dispatcher, directly only when the situation is unmistakable. Not for empty workspaces (starting-a-new-project) or feature work in a specced project (brainstorming).

not rated 413 +1 yesterday A 69 tokens original Apache-2.0

fetch-llm-papers

209

kimtth/azure-openai-llm-notes

Skill Claude CodeCodex

Workflow for updating the LLM landscape paper pool (section/xllmpapers.md) using fetchllmpapers.py. Covers full re-fetch, resume from checkpoint, and adding new topics. USE FOR: Refreshing citation counts, expanding topic coverage. DO NOT USE FOR: Adding hand-curated entries to section files (use…

not rated 410 5d ago A 101 tokens

pr-review

210

microsoft/win-dev-skills

Skill Claude CodeCodex ✓ vendor

Multi-dimensional review of a PR or feature branch in microsoft/win-dev-skills. Activate on "review my PR / changes / branch", "vet before pushing", "PR review", "is this ready to merge". Fans out parallel sub-agents over skill content, the skill-vs-tool boundary (solution hierarchy), tool correctness…

not rated 409 +2 4d ago A 98 tokens original MIT

demo

211

chenxin-yan/crust

Skill Claude CodeCodex

Skill "demo" from chenxin-yan/crust, covering demo, how to use this skill and command reference.

not rated 403 yesterday A 6 tokens original MIT

paper2poster

212

QuZhan51496/paper2anything

Skill Claude Code

Convert academic papers (PDF) into conference posters (HTML/PNG). You are the conductor: you decide what each section needs — an original paper figure or text — write the outline, hand-author the poster HTML, and iterate on the render using your own visual read and a blind-reader content quiz. Use when the user wants…

not rated 402 +8 1mo ago A 76 tokens original Apache-2.0

agent-sh/agnix

Skill Claude CodeCodex

Use when reviewing X/Twitter exports as source evidence for social content decisions.

not rated 402 +2 yesterday A 20 tokens original Apache-2.0

drawio-skill

214

ranxi2001/zero2Agent

Skill Claude CodeCodex

Use when user requests diagrams, flowcharts, architecture charts, or visualizations. Also use proactively when explaining systems with 3+ components, complex data flows, or relationships that benefit from visual representation. Generates .drawio XML files and exports to PNG/SVG/PDF locally using the native draw.io…

not rated 401 +5 yesterday A 68 tokens original MIT

osint-recon

215

Unclecheng-li/DeepSec

Skill Claude CodeCodex

An OSINT guide for open-source intelligence, meaning information collected from publicly available sources. It organizes reconnaissance across servers, websites, domains, and, when appropriate, people.

not rated 392 +19 12d ago A 42 tokens copy · 100% MIT

creating-workflows

216

itmisx/deepx-code

Skill Claude CodeCodex

A guide for creating reusable JavaScript workflows that coordinate several helper agents through steps, loops, parallel tasks, and summaries.

not rated 384 +1 11d ago A 58 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: