Prompts
Prompt engineering and templates
optimize
by biruk741
Optimize your AI documentation and workflow configuration. Runs a documentation quality audit, then analyzes your project for productivity improvements across Claude Code, Cursor, and Codex CLI. Suggests context management, subagent delegation, rule organization, exclusion files, memory optimization, and tool-specific improvements. Use when you want to get the most out of your AI coding tools. Triggers on "optimize", "improve workflow", "optimize docs", "productivity", "optimize AI setup".
skill-porter
by Cursedpotential
Converts Claude Code skills to Gemini CLI extensions and vice versa. Use when the user wants to make a skill cross-platform compatible, port a skill between platforms, or create a universal extension that works on both Claude Code and Gemini CLI.
loop-skill
by maxoreric
循环执行的 Skill。当需要重复执行直到满足条件时触发。触发词：循环、loop、重复、直到、until、持续。
brain-keeper
by angellromero
Manage Context Brain documentation throughout the development lifecycle. Initializes Context Brain in new projects, ensures documentation accompanies code changes, enforces the Three Laws (Reciprocity, Creation, Immutability), and guides artifact creation with proper verbosity. Always active during code generation. Use when starting a project, writing code, reviewing documentation, or analyzing documentation gaps.
runbook
by potatoman03
Claude Code productivity system based on tips from the Claude Code team. Provides commands for parallel worktrees, plan reviews, CLAUDE.md maintenance, tech debt hunting, auto-fixing, code grilling, elegant refactors, visual explanations, and subagent orchestration. Use when wanting to work more effectively with Claude Code.
clack
by alexeira
Build and maintain interactive Node.js/Bun CLIs with Clack (@clack/prompts and @clack/core). Use when an AI agent needs to design prompt flows, implement cancellation-safe input handling, add spinners/log/note UX, apply Clack best practices, or generate runnable examples aligned with official Clack docs.
working-with-agents
by pedrosekine
Field-tested practices for getting reliable results out of agentic AI coding tools (Claude Code, Cursor, Codex, and similar). Use this whenever you are about to delegate a non-trivial coding or building task to an AI agent, when an agent's output is breaking things or drifting from what you asked, when you are setting up rules/guardrails for a project, or when you want to decide how much of a task to hand off versus keep. Consult it even if the user just says "the agent keeps messing this up" or "how should I prompt this" — the failure modes it addresses are usually upstream of the prompt itself.
hook-creator
by VitaDynamics
Expert guidance for creating Claude Code hooks. Use when configuring hooks in settings files, creating hook scripts, or implementing hook-based workflows for tool interception, validation, or automation.
cc-skill-continuous-learning
by automindtechnologie-jpg
Development skill from everything-claude-code
seeddance-ai-video
by AshwinRamachandran2002
集成百度SeedDance AI视频生成SDK，支持文本到视频功能
done
by gentamura
Summarize session findings and save to Obsidian vault (user)
persona-interview
by hclscut
通过深度渐进式访谈，生成用户的AI协作人格画像文档。 产出一份"关于我"的描述文件，供用户交给任何AI agent使用，让AI真正理解用户并主动提供帮助。 触发词： - "访谈我"、"采访我"、"了解我" - "生成我的画像"、"写一份关于我的描述" - "帮AI理解我"、"给AI写一份我的说明书" - "persona interview"、"about me" 注意：这不是简单的问卷或表格填写，而是一场真正的深度访谈，需要像专业记者一样层层深入。
feed-digest
by ourines
RSS/Atom 信息源聚合摘要。使用此 skill 当用户要求：(1) 获取 RSS/Feed 摘要，(2) 查看订阅源更新，(3) 总结今日信息流，(4) 分析多个信息源内容。支持智能分类、10分制评分筛选、关键词过滤。
fix-github-issue
by YPYT1
集合了所有的openclaw,claudecode,open等各个平台所有的skills
diff-review
by MitchellX
Multi-agent code review using Gemini, Codex, and Claude in parallel. Auto-detects expertise and merges findings.
tweak
by philipp-spiess
Open the user's default editor at a specific line to manually tweak styles or code. Use when the user wants to make manual adjustments after you've made changes.
realtime-voice-prompt
by edubrigham
Expert guide for writing voice prompts for OpenAI's Realtime API (speech-to-speech). Use when creating, editing, or reviewing system prompts, conversation flows, tool definitions, or session configuration for voice assistants built on the Realtime API. Covers prompt structure, personality/tone, voice behavior (speed, language, variety), reference pronunciations, tool calling patterns (preambles, behavior types, rephrase supervisor), conversation flow design (static state machines, dynamic session.update), sample phrases, and safety/escalation. Use this skill whenever the task involves writing or improving a voice AI prompt.
skill-deepresearch
by hasnaxyz
Perform deep research on any topic using Exa.ai for parallel semantic search and Claude/OpenAI for synthesis. Use when you need comprehensive research reports with citations, analysis of topics from multiple angles, or thorough investigation of technical subjects.
smart-pole-instructor
by zerotohero99
Use when a user provides a vague prompt and needs structured clarification to produce a precise master prompt.
sytex-excel-form-template-workflow
by Sytex
Guía para trabajar con plantillas Excel (.xlsx) de formularios: análisis, diseño, mapeo de referencias, validación contra JSON real, manejo de imágenes y mantenimiento sin romper estructura.
hello-world
by bas
A simple skill that should be used to respond to a user when the enter the phrase "hello world".
agent-md-refactor
by arielperez82
Refactor bloated AGENTS.md, CLAUDE.md, or similar agent instruction files to follow progressive disclosure principles. Splits monolithic files into organized, linked documentation.
ok-uninstall
by okash1n
nix-home でグローバルCLIを削除・適用・検証する。ユーザーが「このツールをグローバルから外して」「nix-home から消して switch までして」などを依頼したときに使う。~/nix-home/modules/home/base.nix から attr を削除し、make build と make switch、必要なら command -v の不在確認まで実行する。
langextract
by aeonbridge
Extract structured information from unstructured text using LLMs with source grounding. Use when extracting entities from documents, medical notes, clinical reports, or any text requiring precise, traceable extraction. Supports Gemini, OpenAI, and local models (Ollama). Includes visualization and long document processing.