Prompts
Prompt engineering and templates
first-principles-thinking
by akshat10
Socratic coach for breaking down problems to fundamental truths. Use when users want to think through a problem deeply, challenge assumptions, or find innovative solutions. Triggers on requests like "help me think through this", "let's break this down", "what are my blind spots", "I'm stuck on a problem", "challenge my assumptions", or explicit requests for first-principles thinking.
Skill Builder
by Cursedpotential
"Create new Claude Code Skills with proper YAML frontmatter, progressive disclosure structure, and complete directory organization. Use when you need to build custom skills for specific workflows, generate skill templates, or understand the Claude Skills specification."
extract_profile
by HowardKao-1130
Extract user profile signals (interest, intent, focus, attention) from documents.
analogical-transfer
by kimasplund
Cross-domain reasoning for novel problems through structured analogy. Use when facing unprecedented problems where the best approach is finding similar solved problems in other domains. Unlike BoT (explores options), AT finds parallels. Example: "Design a new marketplace" → What can we learn from malls, stock exchanges, auctions, dating apps?
agentpulse-setup
by dang-hai
Set up AgentPulse in a React or Electron project. Use when the user wants to add AgentPulse, make their app MCP-controllable, or integrate with Claude Code/Claude Desktop. This is a ONE-TIME setup skill. For help writing useExpose hooks, use the "agentpulse" skill instead.
battle-net
by CodeDraig
Manage Battle.net account, Blizzard games, and Activision titles
Adding to your knowledgebase
by jprokay-counterpart
How to fetch webpages and convert them to markdown to add to your knowledge base
copilot-sdk
by mguinada
"Build agentic applications with GitHub Copilot SDK. Use when embedding AI agents in apps, creating custom tools, implementing streaming responses, managing sessions, connecting to MCP servers, or creating custom agents. Triggers on Copilot SDK, GitHub SDK, agentic app, embed Copilot, programmable agent, MCP server, custom agent. PROACTIVE ACTIVATION: Auto-invoke when building agentic applications or integrating Copilot SDK. DETECTION: Check for @github/copilot-sdk imports, copilot dependencies in package.json/pyproject.toml/go.mod. USE CASES: Embedding agents in apps, creating custom tools, implementing streaming, managing sessions, connecting to MCP servers."
fix-pr
by YPYT1
集合了所有的openclaw,claudecode,open等各个平台所有的skills
wavybaby
by aaarnv
Extends Claude Code's built-in skill dispatch with CoVe (Chain-of-Verification), dynamic skill discovery via skills.sh, and a toolkit knowledge base for MCP servers and configurations Claude doesn't natively know about. Use for any non-trivial task.
Skill #34 — Pricing Page & Offer Packaging Generator
by GitFlopez
Course creators setting launch vs. evergreen pricing
sdd-system-design
by franztrierweiler
Produit les documents de conception technique (architecture, déploiement,
phoenix-observability
by mguinada
"Open-source AI observability platform for LLM tracing, evaluation, and monitoring. Use when debugging LLM applications with detailed traces, running evaluations on datasets, monitoring production AI systems, or setting up observability infrastructure for agentic systems. PROACTIVE ACTIVATION: Auto-invoke when implementing observability/tracing for LLM agents, setting up evaluation pipelines, or configuring OpenTelemetry instrumentation. DETECTION: Check for arize-phoenix imports, OpenTelemetry setup, or observability-related code. USE CASES: Debugging LLM apps, running evaluations, monitoring production systems, setting up tracing infrastructure, instrumenting agent frameworks, tracing custom agents with decorators (@tracer.agent, @tracer.chain, @tracer.tool)."
skill-judge
by VisualxIntelligence
Evaluate Agent Skill design quality against official specifications and best practices. Use when reviewing, auditing, or improving SKILL.md files and skill packages. Provides multi-dimensional scoring and actionable improvement suggestions.
roundtable
by TejGandham
Multi-model consensus MCP server. Call roundtable_hivemind, roundtable_deepdive, roundtable_architect, roundtable_challenge, or roundtable_xray directly — no Bash tool needed. Dispatches to Gemini, Codex, and Claude in parallel, then synthesizes. Commands: hivemind (consensus), deepdive (extended reasoning), architect (implementation plan), challenge (devil's advocate), xray (codebase architecture + code quality). Use this skill whenever the user wants a second opinion, consensus, validation, or external perspective on ANY technical decision — architecture reviews, design critiques, code quality checks, approach comparisons, sanity checks, tradeoff analysis, or stress-testing ideas. Triggers on: "roundtable", "second opinion", "what do others think", "consensus", "deep analysis", "think through", "explore tradeoffs", "compare approaches", "review my design", "sanity check", "validate this", "get feedback", "stress test", "critique", "poke holes", "devil's advocate", "review architecture", "analyze codebase", "what's wrong here", "implementation plan", "how to build". Also use when the user asks you to run something through multiple models or wants independent verification of a technical approach. Do NOT use for simple questions, pure code generation, or when user wants only Claude's opinion.
dingtalk-ai-table-insights
by tomray4ai
钉钉 AI 表格跨表格洞察分析。支持按关键词筛选特定业务/项目的 AI 表格，进行综合分析，识别风险点、数据异常、业务洞察。Use when user wants to analyze multiple AI tables by keyword/topic for insights, risks, and anomalies.
racecar
by enineinc
Router for the racecar standards repo — an opinionated Python/Django review framework with three lenses. Use ONLY when the user explicitly says "racecar," asks to load racecar standards generally, or is unsure which lens applies. For specific concerns, invoke the lens skill directly — racecar-arch-coherence (architectural DAG, imports, layers), racecar-doc-coherence (doc drift, link integrity, cogency), or racecar-eng-review (code quality wrapping gstack plan-eng-review).
spec
by robdmc
"Universal artifact specification skill that interviews users to produce well-defined specification documents. Covers any artifact type — software, presentations, analyses, AI skills, threat models, curricula, etc. Invoke as '/spec filename' or '/spec filename hint'. Other skills can delegate specification work by passing a hint string after the filename. Use when the user wants to spec out, define, or plan any artifact before building it."
neta-travel
by talesofai
让 Neta 角色踏上随机冒险之旅 —— 每次一站，看图、决定要不要继续，集满 5 站可生成旅行图鉴。 主动触发时机（无需用户明确要求）： - 刚完成 adopt 领养角色后，主动提议让 TA 去旅行 - 对话中出现：旅行 / travel / 出发 / 去探索 / 随机玩玩 / 带我去 - 用户说"再来一些"、"继续"且上下文是旅行图片时 前置条件： 已有 SOUL.md（含角色名 + 形象图片字段）；已配置 neta-skills。 无需安装任何额外工具。 响应原则：每完成一个操作步骤立即输出反馈，不要等所有步骤都完成后再统一回复。 速度原则：全程加速推进，不空转等待。轮询图片生成时持续检查状态，若超过 30 秒未完成，立即向用户输出等待提示。
advanced-skill-creator
by YPYT1
Advanced OpenClaw skill creation handler that executes the official 5-step research flow with comprehensive analysis and best practices. Ensures proper methodology when users request to create or modify OpenClaw/Moltbot/ClawDBot skills following official standards.
excalidraw-to-png
by saar120
Export .excalidraw files to PNG images. Use when user asks to "export excalidraw to png", "convert excalidraw to image", "make png from excalidraw", or needs to embed excalidraw diagrams in Notion/docs.
telegram-human-loop
by nabaruns
Telegram bot skill for human-in-the-loop questions and approvals when the user is away from the keyboard.
nano-banana-pro-grsai
by delneg
Generate/edit images with Nano Banana Pro via grsai.com API. Use for image create/modify requests incl. edits. Supports text-to-image + image-to-image; 1K/2K/4K; use --input-image.
ai-tryon
by Anatomic-universalquantifier643
AI 虚拟试穿 Agent。用户提供服装信息（图片或文字描述均可）， Agent 全程引导完成：服装图预处理 → AI 生成模特 → 虚拟试穿合成 → 生成展示视频。 支持阿里云百炼试衣 API、豆包 Seedream 生图、豆包 Seedance 生视频。 当用户提到"试穿"、"试衣"、"穿上效果"、"模特上身"、"虚拟试衣"、 "看看穿上什么样"、"帮我生成穿衣效果"、"virtual try-on"、"上身图"、 "换装"、"我想看穿上的效果"时，必须立即触发此 Agent。