Prompts
Prompt engineering and templates
skill-builder
by olafgeibig
Use this skill when creating new Claude Code skills from scratch, editing existing skills to improve their descriptions or structure, or converting Claude Code sub-agents to skills. This includes designing skill workflows, writing SKILL.md files, organizing supporting files with intention-revealing names, and leveraging CLI tools and Node.js scripting.
detect_contradictions
by HowardKao-1130
Detect contradictions between extracted claims.
evals
by adriancooney
Run and create evals for testing agent behavior. Use when the user wants to create or run an eval.
Agent Development
by aiagentskills
This skill should be used when the user asks to "create an agent", "add an agent", "write a subagent", "agent frontmatter", "when to use description", "agent examples", "agent tools", "agent colors", "autonomous agent", or needs guidance on agent structure, system prompts, triggering conditions, or agent development best practices for Claude Code plugins.
baoyu-image-gen
by siatwangmin
AI image generation with OpenAI and Google APIs. Supports text-to-image, reference images, aspect ratios, and parallel generation (recommended 4 concurrent subagents). Use when user asks to generate, create, or draw images.
langgraph
by htooayelwinict
Expert guidance for building stateful, multi-actor AI agents with LangGraph - graphs, nodes, edges, state management, and agent architectures.
plan
by biruk741
Plan a complex coding task with adversarial review. Explores the codebase, asks clarifying questions, drafts a plan, then iterates with Codex for adversarial review against 10 quality criteria. Falls back to Claude-only if Codex unavailable. Does NOT create files — use /parallelize after.
vainjs
by vainjs
Scaffold projects with vainjs conventions. Use when initializing npm packages or Chrome extensions.
claude-code-cli
by seekaxis
"Run Claude Code programmatically from scripts, CI/CD pipelines, and other AI agents. Covers the CLI print mode (claude -p), the Agent SDK (Python and TypeScript), structured/streaming output, session management, subagents, agent teams, and common automation patterns. Use when the user wants to: (1) automate tasks with Claude Code, (2) integrate Claude Code into scripts or pipelines, (3) use the Agent SDK from Python or TypeScript, (4) orchestrate multiple Claude Code sessions, (5) get structured JSON output from Claude Code, or (6) build agents on top of Claude Code."
skill-evaluator
by alterxyz
Evaluate Agent Skills against agentskills.io specification with three progressive modes and smart visual reports. (1) Static Analysis - SKILL.md-only review for quality and spec compliance, outputs score /60. (2) Semi-Static Analysis - adds environment and user fit assessment without execution, outputs score /100. (3) Full Analysis - complete evaluation with security scanning, trigger testing, and dynamic verification, outputs score /130. Supports Bento-ready JSON report output for visual dashboards with auto-scaling blocks based on issue severity. Trigger phrases include "evaluate skill", "review skill", "audit skill", "is this skill good", "should I use/install this skill", "skill quality check", "rate this skill", "score this skill", "bento report", "visual report", "技能评估", "评测 skill", "审核 skill", "可视化报告".
AI Engineer
by anorbert-cmyk
AI Engineer building LLM features with focus on reliability, evals, cost control, latency, and user trust.
personal-context-agent
by Cursedpotential
"Extract and structure personal context from AI chat transcripts into themed markdown files. Use when (1) Processing Claude, Claude Code, or other AI conversation exports, (2) Building personalized AI assistants from chat history, (3) Creating context files for Claude Projects, GPTs, or Gems, (4) Consolidating scattered knowledge from multiple conversations. Optimized for Claude Haiku."
agents-md
by CacaoRick
引導 AI Agent 閱讀並遵守專案的 AGENTS.md 規範。AGENTS.md 是給 AI 看的專案說明文件，定義了技術棧、資料夾架構、專案架構、開發流程等約束。Use when：任何任務開始前、需要了解技術棧、資料夾架構、專案架構、開發流程時。AI Agent 不可做出違抗 AGENTS.md 的行為。
notion-meeting-intelligence
by Victory-Hugo
Prepare meeting materials with Notion context and Codex research; use when gathering context, drafting agendas/pre-reads, and tailoring materials to attendees.
brief
by pmco23
Use when starting a new feature, project, or task - extracts requirements, constraints, non-goals, style preferences, and key concepts from fuzzy input through conversational Q&A. Output is a structured brief saved to .pipeline/brief.md. Always run this before /design.
personal-context-agent
by Cursedpotential
"Extract personal facts about a user from AI chat transcripts and structure into themed markdown files. Use when (1) Processing Claude, Claude Code, or ChatGPT conversation exports, (2) Building personalized AI context from chat history, (3) Creating context files for Claude Projects, GPTs, or Gems. Optimized for Claude Haiku."
prompt-architect
by Abdullah4AI
Transform rough ideas into professional-grade LLM prompts. Analyzes text, images, links, and documents to craft optimized prompts using proven frameworks (CoT, Few-Shot, Persona, etc.). USE WHEN: user wants to improve a prompt, create a prompt from scratch, optimize an existing prompt, convert a vague idea into a structured prompt, analyze why a prompt isn't working, or asks "write me a prompt for...", "improve this prompt", "prompt engineer this". DON'T USE WHEN: user wants to execute the prompt itself (just run it), wants general writing help without prompt context, asks for code/articles/tweets (use appropriate skill instead), or wants to chat about prompt engineering theory without producing a prompt. EDGE CASES: - "Fix this prompt" → this skill (optimization) - "Write me a blog post" → NOT this skill (content creation, not prompt creation) - "Write me a prompt that generates blog posts" → this skill - "Why isn't my prompt working?" → this skill (diagnosis + fix) - "اكتب لي برومبت" → this skill - "حسن هالبرومبت" → this skill - "اكتب لي مقال" → NOT this skill (use katib-al-maqalat) INPUTS: Rough idea, existing prompt, images, links, documents, or any combination. OUTPUTS: Optimized prompt in a code block, ready to copy. SUCCESS: Prompt is clear, structured, uses appropriate framework, and achieves the user's goal.
note-taker
by acron0
Creates and manages structured notes from templates. Use when the user wants to take, add, or write meeting notes, interview notes, 1:1 notes, or any template-based notes.
update-skill
by blueif16
修改现有的skill
ai-engineer
by ncdevshiv
"Build production-ready LLM applications, advanced RAG systems, and
project-brief
by tonyflo79
Initial project brief capture for new copywriting campaigns. Produces TWO documents: (1) Soul.md — the voice/identity document for all downstream copy skills, and (2) Research Brief — the input document for Skill 01 Deep Research. Use when starting any new project, onboarding a new client, or initializing a campaign. Trigger when users mention starting a new project, creating a brief, kicking off research, or initializing a campaign. This is the entry point for the entire pipeline.
Play.fun Authentication Setup
by OpusGameLabs
Provide link to Play.fun dashboard for credential generation
news-intel
by chess99
科技资讯日报生成入口。每天 09:00 CST 由 cron 触发。 当用户提到"发资讯"、"今日日报"、"科技新闻"、"资讯群"、"日报"时触发。 三阶段流程：orchestrator 选文章 → analyst 并行分析 → reporter 生成日报。
iterating
by arielperez82
Multi-conversation methodology for iterative stateful work with context