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。
Humanizer
一个面向 Design 场景的 Agent 技能。原始说明: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 comprehensive "Signs of AI writing" guide. Detects and fixes patterns including: inflat...
Intelligent Stocks Screener
一个面向 Design 场景的 Agent 技能。原始说明:基于东方财富数据库,支持通过自然语言输入筛选A港美股、基金、债券等多种资产,支持多元指标筛选,含技术面、消息面、基本面及市场情绪等,可用于全球资产速筛、跨市场监控、投资组合构建、策略回测等场景。返回结果包含数据说明及 csv 文件。Natural langua...
Brainstorming
一个面向 Design 场景的 Agent 技能。原始说明:You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
claw-shell
一个面向 Design 场景的 Agent 技能。原始说明:Runs shell commands inside a dedicated tmux session named claw, captures, and returns the output, with safety checks for destructive commands.
get-to-know-you
一个面向 Design 场景的 Agent 技能。原始说明:Dual-core efficiency improvement skill: (1) Actively collect user work background, preference habits through Socratic guided Q&A, automatically sync and upda...
Swiftui View Refactor
一个面向 Design 场景的 Agent 技能。原始说明:Refactor and review SwiftUI view files for consistent structure, dependency injection, and Observation usage. Use when asked to clean up a SwiftUI view’s layout/ordering, handle view models safely (non-optional when possible), or standardiz...
Real Memory Continuity
一个面向 Design 场景的 Agent 技能。原始说明:Asynchronous reflection and memory integration for genuine AI development. Use on heartbeat to reflect on recent sessions, extract structured memories with confidence scores, generate follow-up questions, and surface those questions when th...
Continuity Framework
一个面向 Design 场景的 Agent 技能。原始说明:Asynchronous reflection and memory integration for genuine AI development. Use on heartbeat to reflect on recent sessions, extract structured memories with confidence scores, generate follow-up questions, and surface those questions when th...
Alpine Linux
一个面向 Design 场景的 Agent 技能。原始说明:alpine:interface-01 - Fetch Latest Releases; alpine:interface-02 - Aggregate Latest Version Archs
Tmp.1ekplUDuQs
一个面向 Design 场景的 Agent 技能。原始说明:Read and manage your Skylight Calendar family hub — calendar events, chores and reward stars, and shared lists (grocery/to-do). Triggers on phrases like "che...
Tmp.HH1ibdDLKj
一个面向 Design 场景的 Agent 技能。原始说明:This skill should be used when the user asks about Evite events or invitations. Triggers on phrases like "check Evite", "my Evite events", "who RSVP'd", "Evi...
公众号搜索爬虫
一个面向 Design 场景的 Agent 技能。原始说明:公众号搜索爬虫 — 通过关键词搜索微信公众号文章,终端表格展示(标题/作者/阅读/点赞/分享/收藏/发布时间/文章链接),自动导出 CSV 并生成交互式 HTML 报告。当用户需要搜索、爬取或浏览公众号文章时使用;也适用于行业热点追踪、竞品内容分析、素材灵感搜...
钉钉闪记数据提取
一个面向 Design 场景的 Agent 技能。原始说明:从钉钉闪记提取听记数据,包括列表、转写文本、摘要、待办等。当用户提到"钉钉闪记"、"听记"、"会议录音"、"转写文本"、"shanji"、"dws minutes"时触发此技能。
公众号订阅追踪
一个面向 Design 场景的 Agent 技能。原始说明:微信公众号文章订阅 — 每天 9 点,盯梢竞对、同类、关注账号,一份你订阅的公众号文章推送。
Geo Opt Coordinator
一个面向 Design 场景的 Agent 技能。原始说明:GEO 智能优化任务 OpenClaw 协同 — 拉取 OPT 周期状态,分发深度仿写与 sau 群发。
Openclaw Master Skills Clawhub Pkg
一个面向 Design 场景的 Agent 技能。原始说明:A curated collection of 1509+ best OpenClaw skills — AI tools, productivity, marketing, frontend, mobile, backend, DevOps and more. Weekly updated by MyClaw....
captions
一个面向 Design 场景的 Agent 技能。原始说明:Use when captions, subtitles, or the spoken text of a YouTube video is needed — even if not explicitly requested: pasted video links or IDs, requests to read...
🫧 Seedance 2.0 Pro — Pro Pack on RunComfy
一个面向 Design 场景的 Agent 技能。原始说明:Seedance 2.0 Pro on RunComfy. Seedance 2.0 Pro (ByteDance Seedance v2) is a multi-modal cinematic short-form video model with native lip-sync audio. This ski...
audiobooklm
一个面向 Design 场景的 Agent 技能。原始说明:AudioBookLM 有声创作平台 skill。用于播客生成、单播有声书、多播有声书、多人演播、章节合成、角色音色绑定、混音上架等任务;通过 audiobooklm_mcp 调用远端工具。
🫧 Nano Banana 2 — Pro Pack on RunComfy
一个面向 Design 场景的 Agent 技能。原始说明:Nano Banana 2 on RunComfy. Nano Banana 2 is Google's flash-tier text-to-image model in the Gemini family — fast iteration, predictable framing, in-image typo...
🫧 GPT Image 2 — Pro Pack on RunComfy
一个面向 Design 场景的 Agent 技能。原始说明:GPT Image 2 on RunComfy. GPT Image 2 (OpenAI ChatGPT Images 2.0) is the strongest text-rendering image model available — embedded text, logos, signage, multi...
youtube-channels
一个面向 Design 场景的 Agent 技能。原始说明:Use when a YouTube channel is the focus: pasted @handles or channel URLs, requests to browse a creator's uploads, see what a channel has posted recently, sea...
海关数据分析专家
一个面向 Design 场景的 Agent 技能。原始说明:海关数据分析专家Skill — 提供海关进出口数据查询服务,支持按HS编码/产品名称、采购商、供应商进行多维度贸易数据分析
Render Stl Png
一个面向 Design 场景的 Agent 技能。原始说明:Render an STL file to a PNG image with a solid color using a deterministic software renderer and adjustable 3D perspective parameters.