85183 Skills Available

Find awesome
Agent Skills

Agent-Skills.md is a agent skills marketplace, to find the right agent skills for you.

Popular searches

session-handoff

List and resume previous coding agent sessions by loading their context into the current session. Use when the user wants to (1) see previous sessions for the current directory with summaries, (2) continue work from a previous session by loading its full conversation context, (3) recover work from an interrupted session, or (4) transfer context between sessions. Supports Claude Code and Codex sessions.

pitzcarraldo
pitzcarraldo
0

review-and-fix

Pre-push CodeRabbit review-fix loop. Runs local CodeRabbit review, fixes valid issues, and repeats until clean so the branch passes CodeRabbit review on push with no additional comments. Use when the user says "review and fix", "review loop", or wants to ensure the branch is CodeRabbit-clean before pushing.

pitzcarraldo
pitzcarraldo
0

hwp

This skill should be used when the user wants to view contents of HWP/HWPX files (Korean word processor documents), mentions ".hwp" or ".hwpx" file paths, asks to "read hwp", "read hwpx", "open hwp", "open hwpx", or needs to extract text from Korean word processor documents.

pitzcarraldo
pitzcarraldo
0

commit

This skill should be used when the user asks to "commit changes", "make a commit", "commit staged files", "create a commit with conventional commit format", or mentions committing code following conventional commit convention.

pitzcarraldo
pitzcarraldo
0

autofix

Fetch and fix CodeRabbit review feedback interactively or in a batch while preserving the latest user-agreed PR purpose. Review suggestions are evidence, not authority to change required behavior.

pitzcarraldo
pitzcarraldo
0

branch-review

Review the current Git branch against origin/main, including committed, staged, unstaged, and untracked changes. Use when the user asks to review a branch, inspect branch changes before merge, or perform a comprehensive code review of the current working branch.

pitzcarraldo
pitzcarraldo
0

code-review

Review code or PR diffs with CodeRabbit and repository evidence for correctness, quality, and security. Validate findings against the latest user-agreed purpose. Keep review-only requests read-only; fix only verified in-scope defects without changing the task contract.

pitzcarraldo
pitzcarraldo
0

create-pull-request

Create a GitHub pull request following project conventions. Use when the user asks to create a PR, submit changes for review, or open a pull request. Handles commit analysis, branch management, and PR creation using the gh CLI tool.

pitzcarraldo
pitzcarraldo
0

multi-ai-collab

Orchestrate multiple AI agents with specialized personas for cross-review and collaborative development

takuan-osho
takuan-osho
01

gemini-search

Web search using Google Gemini CLI. This skill should be used when performing web searches through the Gemini CLI tool instead of the built-in WebSearch tool. Requires the Gemini CLI to be installed and configured.

takuan-osho
takuan-osho
01

gcm

Generate Git Commit Message. This skill should be used when generating a commit message for staged changes. It analyzes git staged changes and generates an appropriate English commit message following Conventional Commits format.

takuan-osho
takuan-osho
01

create-pr

Create Pull Request. This skill should be used when creating a pull request from the current branch. It analyzes changes between the current branch and main branch, then generates an appropriate title and description following Conventional Commits format.

takuan-osho
takuan-osho
01

cognitive-rhythm-writing

説明的な文章に緩急を設計するための規範。緩急を装飾ではなく認知モードの切替(観察→逡巡→断定→再観察)と未回収の緊張の管理として扱い、文の拍、段落の密度波形、節の入り方、緩みと駄文の判別、執筆後の機械的な点検手順を定める。読み物として読ませたい章・記事・解説文を生成するとき、または「密度はあるが平坦でおもしろくない」文章を診断・修正するときに使用する。

takuan-osho
takuan-osho
01

tdl

This skill should be used when implementing or improving Traceable Development Lifecycle (TDL) practices in software projects. Use this skill to establish traceability across the 5-phase workflow (analysis → requirements → ADR → design → implementation). Provides tools, templates, and best practices for ADRs, commit messages, PR templates, structured logging, and traceability analysis as cross-cutting code-integration patterns.

takuan-osho
takuan-osho
01

japanese-tech-writing

日本語の技術文書・書籍原稿の文章規範。整形(一文一行、引用ブロック、脚注、コラム記法)、段落と論証の構成(パラグラフライティング)、論証の厳密さ(ツッコミどころの除去)、読み手の負荷の管理、視点と語り、演出の抑制、LLM っぽい空句の禁止、冗長の排除を定める。日本語で技術書の章、草稿、記事、解説文を書くとき、または推敲・リライトするときに使用する。

takuan-osho
takuan-osho
01

k6-docs

Use this skill when writing or debugging Grafana k6 load testing code. Provides access to the latest official k6 documentation including API references, examples, and best practices for creating performance tests.

takuan-osho
takuan-osho
01

report

Create Investigation/Analysis Report. This skill should be used when summarizing investigation or analysis work into a structured GitHub Flavored Markdown report. Use it after completing research, debugging, security audits, or other analytical tasks.

takuan-osho
takuan-osho
01

interview

Conduct iterative interviews to clarify scope, surface constraints, and reach a "do / don't do / done" agreement before starting non-trivial work. Use when receiving an ambiguous request, a vague task description, or before entering plan mode for any non-trivial implementation. Skip for one-line concrete fixes ("rename foo to bar"), single-fact questions, or when scope, constraints, and acceptance criteria are already specified. Supports requirements definition, debugging investigation, architecture review, security review, documentation creation, and general exploration.

takuan-osho
takuan-osho
01

implement_lenis_scroll

Instructions for implementing Lenis smooth scrolling in a Next.js or React application.

jerrar670
jerrar670
0

premium_web_design

Guidelines and principles for creating premium, high-end web designs.

jerrar670
jerrar670
0

video-gen

使用 AI 生成视频,支持 Veo/Sora 模型。Use when user wants to 生成视频, AI视频, 文生视频, 图生视频, generate video, create video, text to video, image to video, 做一个视频.

infquest
infquest
0

video-concat

合并多个视频文件为一个视频。Use when user wants to 合并视频, 拼接视频, 视频合并, 视频拼接, 把视频合在一起, 连接视频, join videos, merge videos, combine videos, concatenate videos.

infquest
infquest
0

youtube-download

使用 yt-dlp 下载 YouTube 视频、音频或字幕。Use when user wants to 下载视频, 下载YouTube, youtube下载, 下载油管, download youtube, download video, 下载B站, bilibili下载.

infquest
infquest
0

skill-extractor

从当前会话中提取经验,自动生成可复用的 Claude Code Skill。Use when user wants to 提取skill, 总结成skill, 固化经验, 生成skill, extract skill, create skill from context, save as skill, 把经验变成skill.

infquest
infquest
0

media-understand

使用 AI 理解和分析多媒体内容(图片、视频、音频)。Use when user wants to 理解图片, 分析视频, 音频转文字, 视频问答, understand media, analyze video, transcribe audio, describe image, what is in this video/image/audio.

infquest
infquest
0

video-trim

裁剪视频片段,支持压缩、音频控制等选项。Use when user wants to 剪辑视频, 裁剪视频, 截取视频, 视频剪切, 切视频, trim video, cut video, clip video, extract video segment.

infquest
infquest
0

browser

Browser automation with persistent page state. Use when users ask to navigate websites, fill forms, take screenshots, extract web data, test web apps, or automate browser workflows. Trigger phrases include "go to [url]", "click on", "fill out the form", "take a screenshot", "scrape", "automate", "test the website", "log into", or any browser interaction request.

infquest
infquest
0

image-gen

使用 AI 生成图片,支持多种模型和风格。Use when user wants to 生成图片, 画图, 创建图像, AI绘图, 生成一张图, generate image, create image, draw picture, AI art, 编辑图片, 修改图片, edit image, modify image.

infquest
infquest
0

audio-extract

从视频文件中提取音频。Use when user wants to 提取音频, 抽取音频, 视频转音频, 导出音频, extract audio, video to audio, get audio from video, 把视频的声音提取出来.

infquest
infquest
0

audio-transcribe

使用 Whisper 将音频/视频转换为文字,支持词级别时间戳。Use when user wants to 语音转文字, 音频转文字, 视频转文字, 字幕生成, transcribe audio, speech to text, generate subtitles, 识别语音.

infquest
infquest
0

electron-architect

Electron desktop application architect. Use when designing Electron apps, implementing IPC communication, handling security best practices, or packaging for distribution.

tomlord1122
tomlord1122
02

cloud-architect

Cloud infrastructure and platform expert. Use when the user needs to understand a cloud domain (networking, orchestration, IaC, observability, etc.) from first principles before designing infrastructure — or when writing K8s manifests, Helm charts, or Terraform modules.

tomlord1122
tomlord1122
02

code-review-master

Code review expert that first validates whether a PR achieves its stated goal, then checks security, quality, and performance. Use when reviewing PRs, conducting security audits, or assessing code changes.

tomlord1122
tomlord1122
02

deep-research

Deep research expert for building comprehensive knowledge maps from first principles. Use when the user wants to deeply understand a topic — its origin, the problem it solves, the foundational theory, the architecture, and future trajectory — all grounded in primary sources.

tomlord1122
tomlord1122
02

golang-master

Golang language expert specializing in concurrency, performance optimization, standard library, and testing. Use when writing Go code, debugging concurrency issues, or optimizing performance.

tomlord1122
tomlord1122
02

golang-architect

Software Architect specializing in Go projects. Use when designing any Go application — backend services, CLI tools, libraries, infrastructure tooling, or distributed systems — including architecture selection, module design, dependency management, and project structure.

tomlord1122
tomlord1122
02

frontend-architect

Frontend architecture expert. Use when planning component architecture, state management strategies, performance optimization, or technology selection decisions.

tomlord1122
tomlord1122
02

tmux-native-coding-agent

Use when discussing CLI/TUI coding agents, Claude Code interactive mode, Codex, opencode, tmux workflows, persistent terminal sessions, capture-pane context sharing, long-running dev tasks, or multi-agent terminal workspaces. Explains the mindset and design patterns for terminal-native AI coding environments.

tomlord1122
tomlord1122
02

tailwind-ssr

TailwindCSS v4 and SSR expert. Use when configuring TailwindCSS, implementing SSR strategies, optimizing critical CSS, or solving styling performance issues.

tomlord1122
tomlord1122
02

terraform-infra-architect

Scaffold and evolve multi-environment, multi-stack Terraform repositories with S3 remote state, Makefile automation, and GitHub Actions CI. Use when the user asks to "create a terraform repo", "scaffold infrastructure", "build a new terraform stack", "set up IaC project", "design multi-stack terraform architecture", "help me create EKS infrastructure", or "set up foundation AWS resources with Terraform".

tomlord1122
tomlord1122
02

systems-analyst

Systems analysis expert for understanding unfamiliar codebases, distributed architectures, and technical toolchains. Use when asked to investigate a system, survey how components interact, explain what a tool does, find gaps in an architecture, or produce a learning document about a technical domain.

tomlord1122
tomlord1122
02

typescript-master

TypeScript language expert specializing in type system, generics, conditional types, and advanced patterns. Use when writing complex types, debugging type errors, or designing type-safe APIs.

tomlord1122
tomlord1122
02

svelte-kit

Svelte 5 and SvelteKit syntax expert. Use when working with .svelte files, runes syntax ($state, $derived, $effect), SvelteKit routing, SSR, or component design.

tomlord1122
tomlord1122
02

pr-writer

Write pull request titles and descriptions in Tom''s house style. Use when the user asks to create a PR, open a pull request, or write a PR description. Trigger phrases include "make a PR", "create a PR", "write a PR description", "open a pull request".

tomlord1122
tomlord1122
02

learning-curriculum

Write a newbie learning curriculum for a codebase so readers can rebuild it and leave with an engineer mindset. Use when the user asks for learning docs, a study guide, 開發文件, "teach this repo", "how would you build this from scratch", 從頭開發, or a course that covers framework, layers, logging, tests, mocks, DI, context, SQL, or OTel.

tomlord1122
tomlord1122
02

reverse-architect

Reverse-engineer any software project's design from high-level purpose down to component interactions, producing a knowledge map that enables either contributing to the project or rebuilding your own version in a different tech stack. Use when asked to "understand this codebase", "explain how this project works", "map this architecture", "write docs for this repo", "prepare to contribute", or "rebuild this in my own stack".

tomlord1122
tomlord1122
02

native-feel-cross-platform-desktop

Use when the user is designing, prototyping, or rewriting a desktop app that must run on multiple OSes (macOS + Windows, optionally Linux) AND feel indistinguishable from a native app to its users — fast launch, native windowing, native input handling, native materials. Trigger words include "cross-platform desktop", "Electron alternative", "Tauri vs native", "WebView wrapper", "near-native performance", "Raycast architecture", "WebKit/WebView2 quirks", "WKWebView", "system tray app", "global hotkey app", "launcher app". Do NOT trigger this skill for pure web apps, pure mobile apps, or for greenfield projects that have no native-feel requirement.

tomlord1122
tomlord1122
02

excalidraw-mermaid

Author Mermaid diagrams that render cleanly when pasted into Excalidraw's "Mermaid to Excalidraw" feature. Use when the user asks for a diagram, flow chart, sequence diagram, class diagram, architecture diagram, or specifically mentions Excalidraw, Mermaid, drawing, sketching, "draw this", "make a diagram", or "paste into excalidraw".

tomlord1122
tomlord1122
02

design-system-extractor

Extract and document a frontend repo's foundation design system (fonts, colors, transitions, layout, spacing, component styles) into a readable DESIGN-SYSTEM.md reference. Use when the user says "extract the design system", "document our design tokens", "what fonts/colors does this app use", "build a design system reference", or "audit our styling".

tomlord1122
tomlord1122
02

go-symphony

Project scaffolding expert for go-symphony. Use when generating or planning a new Gin-based Go project with PostgreSQL, Supabase, SQLC, Docker, GitHub Actions, WebSocket support, or optional SvelteKit/Next.js frontend integration.

tomlord1122
tomlord1122
02

Page 1496 of 1704 · 85183 results

Adoption

Agent Skills are supported by leading AI development tools.

FAQ

Frequently asked questions about Agent Skills.

01

What are Agent Skills?

Agent Skills are reusable, production-ready capability packs for AI agents. Each skill lives in its own folder and is described by a SKILL.md file with metadata and instructions.

02

What does this agent-skills.md site do?

Agent Skills is a curated directory that indexes skill repositories and lets you browse, preview, and download skills in a consistent format.

03

Where are skills stored in a repo?

By default, the site scans the skills/ folder. You can also submit a URL that points directly to a specific skills folder.

04

What is required inside SKILL.md?

SKILL.md must include YAML frontmatter with at least name and description. The body contains the actual guidance and steps for the agent.

05

How can I submit a repo?

Click Submit in the header and paste a GitHub URL that points to a skills folder. We’ll parse it and add any valid skills to the directory.