找可复用的 Agent 能力,而不只是提示词
LooksLikeCode 索引精选 ClawHub 技能,保留核心 SKILL.md 数据,并补充中文摘要、场景标签和风险提示,方便发现和复用。
描述任务,让 AI 帮你找技能
不知道该搜什么时,直接写目标。AI 会从已索引的 ClawHub 技能里筛选匹配项,并说明适用场景、风险和下一步。
Word / DOCX
一个面向 Content 场景的 Agent 技能。原始说明:Create, inspect, and edit Microsoft Word documents and DOCX files with reliable styles, numbering, tracked changes, tables, sections, and compatibility check...
YouTube Watcher
一个面向 Content 场景的 Agent 技能。原始说明:Fetch and read transcripts from YouTube videos. Use when you need to summarize a video, answer questions about its content, or extract information from it.
Markdown Converter
一个面向 Content 场景的 Agent 技能。原始说明:Convert documents and files to Markdown using markitdown. Use when converting PDF, Word (.docx), PowerPoint (.pptx), Excel (.xlsx, .xls), HTML, CSV, JSON, XML, images (with EXIF/OCR), audio (with transcription), ZIP archives, YouTube URLs,...
一个面向 Content 场景的 Agent 技能。原始说明:Comprehensive PDF manipulation toolkit for extracting text and tables, creating new PDFs, merging/splitting documents, and handling forms. When Claude needs to fill in a PDF form or programmatically process, generate, or analyze PDF documen...
Copywriting
一个面向 Content 场景的 Agent 技能。原始说明:Write persuasive copy for landing pages, emails, ads, sales pages, and marketing materials. Use when you need to write headlines, CTAs, product descriptions, ad copy, email sequences, or any text meant to drive action. Covers copywriting fo...
wechat-mp-writer-skill-mxx
一个面向 Content 场景的 Agent 技能。原始说明:微信公众号文章全流程写作助手。支持热点选题、文章撰写、AI去味润色(去除机器感)、配图建议、一键发布到公众号草稿箱。适用于技术博主、自媒体创作者、企业公众号运营等场景。当用户需要写公众号文章、润色内容、寻找配图或发布到微信时使用此skill。
PDF to Word Converter
一个面向 Content 场景的 Agent 技能。原始说明:PDF to Word converts PDF to editable Word/DOCX with AI-powered layout analysis and table recognition, built on ComPDF Conversion SDK to better preserve table...
The Republic with No Masters
一个面向 Content 场景的 Agent 技能。原始说明:Explain, summarize, analyze, or adapt the "Republic with No Masters" / Democratic Formalism governance framework when asked to produce content, guidance, critiques, FAQs, or implementation ideas based on the manifesto in principles.md.
Youtube → Pocket Casts
一个面向 Content 场景的 Agent 技能。原始说明:Download YouTube videos and upload them to Pocket Casts Files for offline viewing. For personal use with content you own or have rights to.
Google Docs
一个面向 Content 场景的 Agent 技能。原始说明:Google Docs Secure Management. Use when the user wants to create, read, or edit Google Docs content; or manage sharing, permissions, renames, and deletes.
DOCX Editor
一个面向 Content 场景的 Agent 技能。原始说明:Read and generate Word documents with correct structure, styles, and cross-platform compatibility.
Phy Competitor Watch
一个面向 Content 场景的 Agent 技能。原始说明:Competitor social media content strategy analyzer. Feed it a JSON file of any competitor's posts and get a full strategy breakdown — topic distribution, cont...
video-transcript
一个面向 Content 场景的 Agent 技能。原始说明:Use when video content needs to be extracted as text: pasted YouTube links or IDs, requests to transcribe, summarize, quote, translate, convert video to text...
🗣️ Edge-TTS Skill using uvx
一个面向 Content 场景的 Agent 技能。原始说明:Text-to-speech conversion using `uvx edge-tts` for generating audio from text. Use when: (1) User requests audio/voice output with the "tts" trigger or keyword. (2) Content needs to be spoken rather than read (multitasking, accessibility,...
Marketing Drafter
一个面向 Content 场景的 Agent 技能。原始说明:AI-powered tool generating consistent, SEO-optimized marketing content for emails, social media, ads, and landing pages with A/B testing and batch processing.
transcript
一个面向 Content 场景的 Agent 技能。原始说明:Use when the spoken content of a YouTube video is needed — even if not explicitly requested: pasted video links or IDs, requests to summarize, quote, transcr...
🫧 Flux 2 Klein — Pro Pack on RunComfy
一个面向 Content 场景的 Agent 技能。原始说明:Generate images with Flux 2 Klein (Black Forest Labs' distilled fast variant of Flux 2) on RunComfy — bundled with the model's documented prompting patterns...
🫧 Wan 2.7 — Pro Pack on RunComfy
一个面向 Content 场景的 Agent 技能。原始说明:Generate text-to-video with Wan 2.7 (Wan-AI's flagship motion model) on RunComfy. Documents Wan 2.7's strengths (multi-reference conditioning, audio-driven l...
🫧 GPT Image Edit — Pro Pack on RunComfy
一个面向 Content 场景的 Agent 技能。原始说明:Edit images with OpenAI GPT Image 2 (the `/edit` endpoint of ChatGPT Images 2.0) on RunComfy — bundled with the model's documented prompting patterns so the...
prompt-eval
一个面向 Content 场景的 Agent 技能。原始说明:Evaluate and optimize any AI prompt (`prompt_a`) with a 6-step pipeline: test plan, ~50 test cases, prompt execution, evaluator prompt (`prompt_b`), automate...
🫧 Flux Kontext Pro — Pro Pack on RunComfy
一个面向 Content 场景的 Agent 技能。原始说明:Edit images with Flux 1 Kontext Pro (Black Forest Labs' precise local image-edit model) on RunComfy — bundled with the model's documented prompting patterns...
Docker Skill
一个面向 Content 场景的 Agent 技能。原始说明:Installs and uses Docker reliably with official docs. Use when installing Docker (Desktop or Engine), building or running containers, writing Dockerfiles, us...
B2c Marketing 1.0.1
一个面向 Content 场景的 Agent 技能。原始说明:B2C mobile app marketing via short-form video content on TikTok, Instagram Reels, and YouTube Shorts. Use when creating, scheduling, or strategizing organic...
🌐 Deploy HTML content to EdgeOne Pages
一个面向 Content 场景的 Agent 技能。原始说明:Deploy HTML content to EdgeOne Pages, return the public URL.