Prompt-driven capabilities that teach an agent new workflows.
Ranked by GitHub stars. Search to find fast, or page through the full list.
Evidence before assertions, always
Turn specs into phased implementation plans
Red → green → refactor discipline for any feature or bugfix
Reproduce, isolate, diagnose — don't guess
🌐 Make websites accessible for AI agents. Automate tasks online with ease.
"CLI-Anything: Making ALL Software Agent-Native" -- CLI-Hub: https://clianything.cc/
Browser automation CLI for AI agents
An autonomous agent that conducts deep research on any data using any LLM providers
Create beautiful slides on the web using Claude's frontend skills
Claude Code skill implementing Manus-style persistent markdown planning — the workflow pattern behind the $2B acquisition.
Huashu Design · HTML-native design skill for Claude Code · Claude Code 里 HTML 原生的设计 skill · 高保真原型 / 幻灯片 / 动画 + 20 设计哲学 + 5 维评审 + MP4 导出 · Agent-agnostic
AI-agent Skill for generating polished HTML slide decks: editorial magazine and Swiss layouts, image prompts, social covers, and a WebGL/low-power presentation runtime.
Your agent writes bad React. This catches it
>
>
>
>
>
>
>
>
>
>
>
>
Generate bilingual (English + Traditional Chinese) commit message from git changes.
從最新的 git tag 到 HEAD 生成結構化變更日誌並推薦新版本。當使用者請求生成變更日誌、發行說明或版本升級文件時使用。
Search the curated Agenvoy public API list for an API that fits the current user need or skill context, then chain into the `api-tool-add` skill to register it under `~/.config/agenvoy/tools/api/`. Triggers when the agent lacks a tool for a data lookup (weather, currency, geocoding, dictionary, etc.), when the user says "找個 API"／"有沒有 XXX 的 API"／"我需要查 XXX 但你沒工具"／"add a public API for this", or when an upstream skill needs an external data source that is not yet wired.
從原始碼分析自動生成雙語 README。當使用者請求為專案建立 README、需要從程式碼庫生成 README.md（英文）和 README.zh.md（中文）、或希望為其函式庫/套件建立一致的多語言文件時使用。
>
Package a script tool under ~/.config/agenvoy/tools/script/ into a tar.gz and publish to pkg.agenvoy.com registry. Keyword picker, dep/key detection, config-stored email (ask + lowercase + persist), ask version, email verification gate, multipart upload with downgrade/unique guards.
Install an Agenvoy extension from pkg.agenvoy.com registry (browse/pick) or local tarball into ~/.config/agenvoy/tools/.extension/<type>/<name>@<version>/. Extracts tar.gz, validates manifest (email field, type api/script only), installs deps, stores keychain keys, atomically moves staged dir. Collisions handled by Overwrite/Rename/Cancel popup.
教学过程中自动捕获和记录学习者的概念疑难点（"为什么/是什么/怎么推/什么意思"类型的问题），保存到进度文件的"概念疑难点记录"区，形成考前回顾清单。
>
>
>
>
帮助学生在临考前进行结构化极速复习：解析课程资料/大纲/重点，按章节生成 wiki 知识库与标准题库，组织针对性刷题与判分，并记录复习进度和错题。当用户即将考试、需要快速复习计划、练习题、错题复盘或考前小抄时使用（关键词：期末/备考/复习/刷题/划重点/错题；exam, cram, study plan, quiz, review）。不适用于长期学习规划、与考试无关的写作或编程任务。
>
>
>
>
한국 정부·공공기관 지원사업(창업지원, 사업화 자금, 입주공간, R&D, 바우처, 경진대회) 전수조사 및 프로젝트 적합성 판정 스킬. K-Startup·기업마당(bizinfo)·NIPA·KOCCA·SMTECH 공고를 크롤링해 현재 작업 폴더의 프로젝트(아이템) 프로필에 맞는 사업을 "즉시 지원 가능 / 요건 충족 시 / 변형하면 가능" 3단계로 분류하고 마감일·자격요건을 원문 검증해 보고서를 만든다. 사용자가 "지원사업 찾아줘", "정부지원", "창업지원 사업", "입주공간/사업화 자금 알아봐", "공모전/경진대회 조사", "우리 아이템에 맞는 지원사업", "K-Startup/기업마당 조사" 등을 요청하면 반드시 이 스킬을 사용한다. 이전에 조사한 적이 있는 프로젝트에서 "재조사", "새로 나온 지원사업 있나", "지난번 이후 뭐 올라왔나"를 물으면 diff 모드(증분 재조사)로 이 스킬을 사용한다. 특정 사이트를 지목하지 않아도 지원사업·보조금·정부과제 탐색 의도가 보이면 트리거된다. 한국 지원사업 전용.
>
CLI-first serial port debugging and macro automation with serial-mcp-server for Codex and Claude Code. Use when working with UART or USB-serial devices, listing serial ports, probing STM32/Arduino/ESP32 boards, writing or reading serial data, running JSON serial macros, controlling RTS/DTR, or using serial-mcp-server through MCP tools.
Analyze Claude Code sessions to learn what went right/wrong and suggest high-confidence improvements to skills. Use when asked to analyze a session, learn from a session, or review workflow effectiveness.
Harden a manifest-dev task guidance file for one-shot quality — either /define's quality-gate/Default set or figure-out's probe set. Iterates: orthogonality gap analysis, user-approved additions, prompt review, fix, converge. Use when a task file needs comprehensive coverage or "harden task file".
Iteratively optimizes prompts for token efficiency by maximizing information density - reduces verbosity, removes redundancy, tightens phrasing while preserving semantic content. Use when asked to compress, shorten, reduce tokens, tighten, maximize density, increase information density, or make a prompt more concise.