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。
多视角代码审查
一个面向 Design 场景的 Agent 技能。原始说明:多视角代码审查 - 安全(OWASP)/性能/正确性/风格,每视角输出严重级别+修复建议,支持PASS/BLOCK裁定
improve-hn-karma
一个面向 Design 场景的 Agent 技能。原始说明:Generate daily batches of 4–5 tailored Hacker News comments in your expertise area to build karma on active, high-visibility threads with fresh technical ang...
Fix Exec Allowlist Miss
一个面向 Design 场景的 Agent 技能。原始说明:Hybrid reload mode auto-restarts for gateway/plugins changes. Config patching requires baseHash from config.get first. Minimax cron auth uses system-level to...
HTTP客户端
一个面向 Design 场景的 Agent 技能。原始说明:HTTP客户端 - 发送GET/POST/PUT/DELETE请求,自定义请求头/Body,响应验证,超时控制,重试机制
Tesseract Ocr
一个面向 Design 场景的 Agent 技能。原始说明:Extract text from images using the Tesseract OCR engine directly via command line. Supports multiple languages including Chinese, English, and more. Use this...
学术汇报 PPT 生成技能 (Academic PPT Builder)
一个面向 Design 场景的 Agent 技能。原始说明:学术汇报 PPT 生成技能。当用户需要生成论文答辩、顶会 Oral 或基金汇报的 PPT 方案时使用。 适用场景包括: - 用户提供论文题目和背景,需要构建完整学术故事线(Story Arc) - 请求生成 PPT 结构、图表设计、叙事逻辑 - 要求图表自包含、同行可复现 - 用户...
Free voice from Comfy UI + Qwen3 TTS
一个面向 Design 场景的 Agent 技能。原始说明:Generate Russian male voice audio using ComfyUI with Qwen3 TTS node and save as MP3 for voice messages.
Brainstorming
一个面向 Design 场景的 Agent 技能。原始说明:Socratic design refinement before coding. Use when user requests feature without clear spec.
okx-cex-portfolio
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 'account balance', 'how much USDT do I have', 'my funding account', 'show my positions', 'open positions',...
"What if?" Scenario Builder
一个面向 Design 场景的 Agent 技能。原始说明:Structured methodology for constructing rigorous "what if?" scenarios combining foresight frameworks (Shell, Schwartz, Manoa, Intuitive Logics), deep analyti...
okx-cex-bot
一个面向 Design 场景的 Agent 技能。原始说明:Manage Grid bots (spot/contract/coin-margined) and DCA Martingale bots (Spot DCA 现货马丁 / Contract DCA 合约马丁) on OKX. Covers create, stop, amend, monitor P&L, T...
Send Token
一个面向 Design 场景的 Agent 技能。原始说明:Transfer tokens from OpenAnt wallet on Solana or Base. Use when the user wants to send, transfer, or pay tokens via OpenAnt. Supports native coins (SOL, ETH)...
Cancel Task
一个面向 Design 场景的 Agent 技能。原始说明:Cancel a task on OpenAnt and reclaim escrowed funds. Only the task creator can cancel. Use when the user wants to abort a task, take it down, withdraw the bo...
循古黄历
一个面向 Design 场景的 Agent 技能。原始说明:循古黄历 - 获取中国万年历信息,包括二十四节气、农历日期、宜忌、吉凶、黄道吉日等。当用户询问节气、农历、日子好坏、宜忌、黄历相关问题时使用此技能。
Robotaxi Briefing
一个面向 Design 场景的 Agent 技能。原始说明:Track autonomous driving and Robotaxi sector intelligence with Pony.ai, Waymo, Tesla Robotaxi, and Baidu Apollo as core targets. Generates twice-daily increm...
Freelance Autobot
一个面向 Design 场景的 Agent 技能。原始说明:Autonomous freelance hunter — finds gigs on FreeLanceDAO and CryptoGigs, scores them for fit, and auto-submits proposals. Also builds your CryptoGig profile...
Batchedits
一个面向 Design 场景的 Agent 技能。原始说明:Autonomously edit videos, add captions, and remove silences via BatchEdits.
presentation-by-html
一个面向 Design 场景的 Agent 技能。原始说明:Use when the user needs to create a technical sharing, presentation, or talk material. Triggered by requests like "prepare a sharing", "make slides", "build...
Nonprofit RBM Logic Model
一个面向 Design 场景的 Agent 技能。原始说明:Build donor-ready nonprofit RBM logic models, theory of change, logframes, concept notes, LOIs, full proposal sections, MEAL indicators, evidence-gap tracker...
Strategical Alignment
一个面向 Design 场景的 Agent 技能。原始说明:Strategical alignment analysis — detect where short-term optimization (profit, efficiency, convenience) is building long-term fragility, dead ends, or collap...
Dola Seedream Gen
一个面向 Design 场景的 Agent 技能。原始说明:这是豆包(Doubao/ByteDance)的 Seedream 图片生成技能。 支持:文生图(text-to-image)、图生图(image-to-image,需公网URL)、组图(sequence)。 模型: 4.5→5.0Lite→4.0 自动降级,每模型日限18次。 触发词: /img 生成图片 画图...
Doubao Seedream Gen
一个面向 Design 场景的 Agent 技能。原始说明:调用豆包 Seedream 模型生成图片。新用户通过火山「协作奖励计划」免费使用顶级模型。 支持文生图+图生图,智能调度 4.5→5.0Lite→4.0,每模型每日18次,超限拒绝。 Use when: 用户输入中含触发词(/img /draw /gen 生成图片 画图 搞个图 generate image tx...
Discord
一个面向 Design 场景的 Agent 技能。原始说明:Manage Discord guilds, channels, messages, members, roles, and application commands - powered by ClawLink.
OpenClaw MiniMax Media
一个面向 Design 场景的 Agent 技能。原始说明:Install, configure, verify, or troubleshoot the @jwongart/openclaw-minimax-media OpenClaw plugin for MiniMax image understanding, image generation, music gen...