AI全自动化编程,Claude Code作为项目经理指挥Builder自动完成编程任务(需求对齐→指令生成→自动执行→验收→文档归档暂存)
This skill should be used when the user wants to read, analyze, or work with CAD DWG/DXF drawing files. Trigger phrases include: DWG, DXF, CAD drawing, drawi...
Diagnose pipeline health, detect stalled deals, and surface what needs attention this week. Built for sales teams managing active opportunities.
Architect biotech business plans tailored to company type, stage, and disclosure level to align investor presentations with fundraising goals.
Write a full-length technical book using multi-agent AI orchestration. Spawns parallel research, writing, and review agents to produce 60K-100K+ word manuscr...
Your AI Chief Marketing Officer. Autonomous agent that runs your entire marketing — auto-posts to Twitter/X, Bluesky, Telegram, Discord, auto-engages with yo...
Find, evaluate, and recommend AI products using the watcha.cn platform API. Use this skill whenever the user asks about AI tools, AI products, AI apps, or wa...
Marketing Mode combines 23 comprehensive marketing skills covering strategy, psychology, content, SEO, conversion optimization, and paid growth. Use when users need marketing strategy, copywriting, SE
--- name: agent-optimizer description: V6.1 Agent 性能优化器 - 基于轨迹分析和奖励反馈的轻量级优化框架 homepage: https://github.com/openclaw/openclaw metadata: {"openclaw":{"emo
Build apps with the Claude API or Anthropic SDK. TRIGGER when: code imports `anthropic`/`@anthropic-ai/sdk`/`claude_agent_sdk`, or user asks to use Claude AP...
Python best practices enforcer — clean code, proper patterns, performance, testing, type hints. Use when writing or reviewing Python code.
Evaluate individual framework controls against organizational documentation with evidence extraction, severity classification, and remediation recommendations.
Shop YHD.com (1号店) with smart deal finding, daily flash sales, fresh grocery navigation, and membership benefits guidance. Use when the user wants help shopp...
Generates structured, argument-driven book manuscript sections using modular 800--1000 word conceptual units.
Interact with Twitter/X via TwitterAPI.io — search tweets, get user info, post tweets, like, retweet, follow, send DMs, and more. Covers all 54 endpoints. Us...
--- name: feedback-loop version: 1.0.0 description: Feedback Loop - Collect, analyze, and act on user feedback for continuous agent improvement author: OpenClaw license: MIT tags: - feedback - ana
Generate hologram and 3D display content using each::sense AI. Create holographic product displays, presenters, 3D logos, interactive menus, event content, m...
Vector memory engine with PostgreSQL + pgvector + OpenAI embeddings. Store, search, and inject contextual memories into LLM prompts. Includes auto-injection...
Detect and automatically fix spelling errors in Markdown, plain text, and documentation files with support for custom dictionaries and batch processing.
--- name: nexus-code-review description: "Security, performance, and style analysis for code" version: 1.0.0 capabilities: - id: invoke-code-review description: "Security, performance, and style
Optimize web performance and LLM API costs. Covers loading speed, runtime efficiency, resource optimization, and cost-aware LLM pipelines with model routing,...
Create, evaluate, improve, benchmark, and publish OpenClaw skills. Use when building a new skill from scratch, iterating on an existing skill, running evals...
Remove signs of AI-generated writing from text. Use when editing or reviewing text to make it sound more natural and human-written. Based on Wikipedia's comp...
Fetches and summarizes recent arXiv and Hugging Face papers with Agentic Paper Digest. Use when the user wants a paper digest, a JSON feed of recent papers, or to run the arXiv/HF pipeline.