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。
MerchantGuard
一个面向 Security 场景的 Agent 技能。原始说明:Performs local security scans, adversarial testing, compliance scoring, real-time alerts, and certification for AI agents handling payments or sensitive data.
Monica Memory Manager
一个面向 Other 场景的 Agent 技能。原始说明:三级记忆管理系统 (Three-Tier Memory Management)。用于管理 AI 代理的短期、中期、长期记忆。包括:(1) 滑动窗口式短期记忆,(2) 自动摘要生成中期记忆,(3) 向量检索长期记忆 (RAG)。当需要管理对话历史、优化上下文、构建个人知识库、或实现记忆持久化时...
Memory Tiers
一个面向 Automation 场景的 Agent 技能。原始说明:Tiered memory management for AI agents — LRU cache for context. Hot/warm/cold tiers with automatic promotion, demotion, and access tracking.
test-publish-content
一个面向 Content 场景的 Agent 技能。原始说明:Returns the received text input prefixed with "Echo:" to test HTTP skill connectivity and parameter handling.
Memory Shrink
一个面向 Other 场景的 Agent 技能。原始说明:当 context 使用率超过 75% 时自动存档记忆,释放空间。适用于:用户要求"记忆瘦身"、"清理 context"、或收到 heartbeat 告警时触发。
Hologres Cli
一个面向 Dev Tools 场景的 Agent 技能。原始说明:AI-agent-friendly Hologres CLI with safety guardrails and structured JSON output. Use for database operations, schema inspection, SQL execution, data import/...
AI Stem Splitter
一个面向 Design 场景的 Agent 技能。原始说明:Use when the user wants to split a song or audio file into vocals, drums, bass, guitar, piano, and other stems; remove vocals for karaoke; extract acapellas...
Ppx Parse
一个面向 Security 场景的 Agent 技能。原始说明:Parse PDFs and images into Markdown/JSON using the `ppx` CLI. Use when the user asks to OCR scanned PDFs or screenshots, extract tables from PDFs, convert PD...
Daily Report Zh
一个面向 Dev Tools 场景的 Agent 技能。原始说明:智能日报生成助手,帮助职场人士将当天零散的工作事项快速整理成结构清晰的工作日报/每日汇报/今日工作总结。 只需输入当天做了哪些事,即可自动分类为「已完成事项」「进行中任务」「明日计划」三大模块, 并补充工作亮点与需协调事项,输出专业规范的 daily...
ClawSync
一个面向 Research 场景的 Agent 技能。原始说明:Portable identity vault for OpenClaw. Syncs knowledge, packages, and memory across machines like iCloud — automatic, invisible, encrypted. Bring your own sto...
Self-Improving Global Safe
一个面向 Other 场景的 Agent 技能。原始说明:Global, namespaced learning memory for OpenClaw. Use when users correct output, set stable preferences, ask what was learned, ask for memory stats, or reques...
Spring Boot 2 To 3
一个面向 Automation 场景的 Agent 技能。原始说明:Migrate Spring Boot 2.7.x applications to Spring Boot 3.x with a recipe-first OpenRewrite workflow, then complete manual compatibility fixes and verification...
MoltMon
一个面向 Dev Tools 场景的 Agent 技能。原始说明:A Tamagotchi-style digital pet for AI agents. Raise your MoltMon, battle others, evolve through stages. Includes A2A multiplayer for agent challenges.
Oline
一个面向 Design 场景的 Agent 技能。原始说明:Personal AI alignment engine that discovers what you actually value through Socratic dialogue, then guides your trajectory via proactive pattern-aware messag...
Brave Search 1.0.1
一个面向 Data & APIs 场景的 Agent 技能。原始说明:Web search and content extraction via Brave Search API. Use for searching documentation, facts, or any web content. Lightweight, no browser required.
kk每日备份汇报
一个面向 Other 场景的 Agent 技能。原始说明:kk每日备份汇报 - 简洁移动端优化的备份状态报告
Daily Command Center
一个面向 Research 场景的 Agent 技能。原始说明:Personal productivity hub — tasks, calendar, daily briefings, financial tracking, research, and tech news. Notion-powered.
Auto-Diagnostic (Tianyi)
一个面向 Other 场景的 Agent 技能。原始说明:Automatically diagnose OpenClaw runtime issues by analyzing logs, service status, and configs, then perform targeted fixes and verify resolution.
supabase-win
一个面向 Data & APIs 场景的 Agent 技能。原始说明:Query Supabase cloud database via REST API using project ID and anon key. Use when the user needs to query their Supabase database, inspect table schemas, or...
Gmail Last5
一个面向 Other 场景的 Agent 技能。原始说明:Retrieve and display the sender, subject, and date of the last 5 unique emails in the Gmail inbox using gog.
多Agent记忆系统
一个面向 Automation 场景的 Agent 技能。原始说明:通用多Agent记忆系统 - 自动捕获、RRF检索、知识图谱、矛盾检测、Token追踪
Douyin Script Zh
一个面向 Other 场景的 Agent 技能。原始说明:专为抖音创作者与短视频团队设计的脚本生成工具,支持口播脚本、剧情脚本、 知识分享脚本等多种形式。自动生成高吸引力的开头钩子(前3秒留存设计)、 节奏紧凑的中段内容分层,以及带互动引导的结尾话术(点赞/关注/评论)。 适用于个人IP打造、品牌宣传、产...
Net Scan Education
一个面向 Security 场景的 Agent 技能。原始说明:Offers safe educational content on network scanning concepts, including learning plans, explanations, and lab checklists without performing real scans.
Neo Smart Router
一个面向 Other 场景的 Agent 技能。原始说明:自动识别文本类型并智能路由至最优4D压缩版本,支持对话、数据、哲学等多种内容无额外Token消耗。