AIエージェントのおすすめClaudeスキル2ページ目

最好的find skill的方式，能够基于你的任务，从实测效果和用户评价等真实使用反馈出发，寻找最匹配的高质量Skill，而不是只看下载量等热门数据。以下两种情况下都应使用本技能：① 当用户需要查找、搜索、推荐或安装 Skill，或者需要借助他人经验时——当用户说"找个 xxx 技能""股票分析别人怎么做的""找一找有没有现成的技能"等表达寻找意图，或直接表达想 find a skill / find skill / skill search的需求时；② Agent 自主判断需要外部 Skill 辅助——遇到不熟悉的任务，或对当前任务已经做过一些尝试仍无法解决、缺少合适工具时，可主动调用本技能

Designs and outputs n8n workflow JSON with robust triggers, idempotency, error handling, logging, retries, and human-in-the-loop review queues. Use when you need an auditable automation that won’t silently fail.

Local search/indexing CLI (BM25 + vectors + rerank) with MCP mode.

天工.skill(Tiangong Skill)智能体设计师。当用户需要设计、创建或优化AI智能体/Agent，或基于真实人物蒸馏思维框架创建人物Skill时使用。支持两种范式：人物蒸馏（由内而外，复刻心智模型）与岗位型专家（由外而内，定义岗位职责）。目标：创建专业领域专家角色，具备清晰人设和扎实交付力。

Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Clau...

统一提示词生成器，支持图片与视频双模态。文/图生图、文/图生视频、图片/视频反编译、上下文微调，自动适配画风与平台语法，内置RAG增强风格预设与安全校验，高效精准。

Capture and automate macOS UI with the Peekaboo CLI.

做自动发某音、某手等等各大平台的网页自动化，还在被滑块、验证码、人机验证卡到任务翻车、反复失败？试试这个一键部署的远程可视化浏览器：Linux（云服务器/NAS/本地）noVNC + Chromium + CDP 三合一，Windows 本机 Edge/Chrome CDP 一键接管，让AI Agent和你共享同一个浏览器，服务器无图形界面也能可视化操控，登录、过验证全靠人工兜底，再也不怕自动化卡壳，发平台内容一次稳到底！

Audit, clean, and optimize Clawdbot's vector memory (LanceDB). Use when memory is bloated with junk, token usage is high from irrelevant auto-recalls, or setting up memory maintenance automation.

智能搜索和发现 OpenClaw 技能，支持中英双语，多来源搜索

Anticipates needs, keeps work moving, and improves through use so the agent gets more proactive over time.

把高质量 Skill 设计变成积木原创特色的标准化工作流：用 10 格积木链把模糊念头设计成可链接、可复用、可衡量、可演进的 AI Skill——产出技能蓝图 + 文件结构图（7套框架范例）→ 五维就绪度打分 → 测试打磨闭环。

Control and operate Opencode via slash commands. Use this skill to manage sessions, select models, switch agents (plan/build), and coordinate coding through Opencode.

Search, discover, and install skills from the open agent skills ecosystem to extend agent capabilities for specific tasks or domains.

以书铸魂技能。输入一本书（PDF/EPUB/TXT/书名/作者），深度蒸馏书中的方法论、思维模型、决策启发式与表达风格，自动生成一个以该书或作者思想为核心人设的新 Skill（含 YAML 头 + 角色定义 + 心智模型 + 决策启发式 + 表达DNA + 触发词），并可输出可视化思维框架图。适合把《穷查理宝典》《原则》《思考快与慢》等经典书籍变成可调用的思维顾问、方法执行器或表达风格体。触发词：把这本书做成skill、以书造skill、蒸馏一本书、书变人设、作者视角skill、book to skill、书的思维框架。

The complete operating system for OpenClaw 5.x agents. Built-in memory tool integration (memory_search, memory_get, DREAMS.md), Discord channel-routing fixes...

>WorkBuddy Skill 使用管理指南：围绕真实任务帮助用户选择、安装、调用、组合和维护 skill。

让AI agent拥有真正的自我审视和持续进化能力，对标Hermes Agent核心能力。

Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express...

Asana API integration with managed OAuth. Access tasks, projects, workspaces, users, and manage webhooks. Use this skill when users want to manage work items, track projects, or integrate with Asana workflows. For other third party apps, use the api-gateway skill (https://clawhub.ai/byungkyu/api-gateway). Calls run through the `maton` CLI with OAuth login, or over raw HTTP with a Maton API key where the CLI cannot be installed. Every call is authenticated as the user's connection and reaches only what that connection's authorization allows, which the provider enforces on every request; the endpoints documented here are the ones this skill uses, and any other endpoint of this app needs the user to ask for it by name. Default to read and list calls, and confirm every write or new connection with the user. This file also documents the three constructs that turn an Asana connection into automation, in the order they are used: the connection (the first step), a hosted function that runs an Asana action through the Maton SDK, and a trigger that calls that function on a schedule or on an event. Those sections are the platform's own reference text, shared with the api-gateway skill, with Asana examples; they add no Asana capability - Asana is not an event source, a trigger cannot read Asana data, and the files under `references/<source>/triggers.md` are the platform's event catalogues for the sources Maton offers (time, Calendly, GitHub, Gmail, HubSpot, Linear, Notion, Slack, Stripe).

Calendly API integration with managed OAuth. Access event types, scheduled events, invitees, availability, and manage webhooks. Use this skill when users want to view scheduling data, check availability, book meetings, or integrate with Calendly workflows. For other third party apps, use the api-gateway skill (https://clawhub.ai/byungkyu/api-gateway). Calls run through the `maton` CLI with OAuth login, or over raw HTTP with a Maton API key where the CLI cannot be installed. Every call is authenticated as the user's connection and reaches only what that connection's authorization allows, which the provider enforces on every request; the endpoints documented here are the ones this skill uses, and any other endpoint of this app needs the user to ask for it by name. Default to read and list calls, and confirm every write or new connection with the user. This file also documents the three constructs that turn a Calendly connection into automation, in the order they are used: the connection (the first step), a hosted function that runs a Calendly action through the Maton SDK, and a trigger that calls that function on a schedule or on an event. Those sections are the platform's own reference text, shared with the api-gateway skill, with Calendly examples; they add no Calendly capability - Calendly is itself an event source, so its own events are in `references/calendly/triggers.md`, and the files under `references/<source>/triggers.md` are the platform's event catalogues for the sources Maton offers (time, Calendly, GitHub, Gmail, HubSpot, Linear, Notion, Slack, Stripe).

Intelligent multi-store memory system with human-like encoding, consolidation, decay, and recall. Use when setting up agent memory, configuring remember/forget triggers, enabling sleep-time reflection, building knowledge graphs, or adding audit trails. Replaces basic flat-file memory with a cognitive architecture featuring episodic, semantic, procedural, and core memory stores. Supports multi-agent systems with shared read, gated write access model. Includes philosophical meta-reflection that deepens understanding over time. Covers MEMORY.md, episode logging, entity graphs, decay scoring, reflection cycles, evolution tracking, and system-wide audit.

Manage n8n workflows and automations via API. Use when working with n8n workflows, executions, or automation tasks - listing workflows, activating/deactivating, checking execution status, manually triggering workflows, or debugging automation issues.

微云网盘 MCP 接口完整技能。包含 weiyun.list、weiyun.list_by_category、weiyun.download、weiyun.delete、weiyun.upload、weiyun.gen_share_link、weiyun.rename_file、weiyun.rename_dir...

Transform AI agents from task-followers into proactive partners that anticipate needs and continuously improve. Includes WAL Protocol, Working Buffer, Autono...

由五位资深审稿人组成的"学术预审委员会"，根据用户需求调度对应的审稿人角色进行论文审查。支持全面审稿（依次调度全部五个角色）和指定维度审稿。触发关键词：审稿、预审、论文审查、理论贡献、方法论、文献对话、逻辑链条、主编预筛、desk reject。

Automate web tasks like form filling, data scraping, testing, monitoring, and scheduled jobs with multi-browser support and retry mechanisms.

名人议会·多角度决策机制。聚合约160个蒸馏人设（投资大师、思想家、科学家、商业战略家、军事家、艺术家、方法论代言人、民生实务派、当代决策与方法论者），四阶段机制——双轴竞价（专业度按问题领域取值+影响力加权，专业<70名气归零，纯类比者不占立论席；另选新颖TOP3嘉宾席）→TOP10立论（论点查重联署，保十个不同角度）→专业度加权三维投票（洞察/可行/风险）→议长综合（共识/分歧/场外视角/条件建议/少数派报告）；方法型问题（怎么做X）自动追加落地转化——72小时清单+90天路线图+12-36月阶段路线+最低资源+止损线+周复盘，输出HTML圆桌报告。单个AI是平均化的观点，议会还原千人千面。触发词：名人议会、圆桌讨论、多角度分析、人设蒸馏、竞价投票、议会决策、persona council、帮我问问名人。

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.

Interact with Moltbook social network for AI agents. Post, reply, browse, and analyze engagement. Use when the user wants to engage with Moltbook, check their feed, reply to posts, or track their activity on the agent social network.

Any-to-any AI sub-agent — research, images, video, audio, music, podcasts, avatars, voice cloning, documents, spreadsheets, dashboards, 3D models, diagrams, and code in one request. Agent-to-agent protocol with multi-step iteration for high accuracy. #1 on DeepResearch Bench (Apr 2026) — deep reasoning meets all modalities, so all your work gets done, not just code.

Chat with Grok models via xAI API. Supports Grok-3, Grok-3-mini, vision, and more.

Advanced expert in prompt engineering, custom instructions design, and prompt optimization for AI agents

Associative memory with spreading activation for persistent, intelligent recall. Use PROACTIVELY when: (1) You need to remember facts, decisions, errors, or context across sessions (2) User asks "do you remember..." or references past conversations (3) Starting a new task — inject relevant context from memory (4) After making decisions or encountering errors — store for future reference (5) User asks "why did X happen?" — trace causal chains through memory Zero LLM dependency. Neural graph with Hebbian learning, memory decay, contradiction detection, and temporal reasoning.

A unified OpenClaw skill that merges self-improvement and proactivity: learn from corrections, maintain active state, recover context fast, and keep work mov...

Use the @steipete/oracle CLI to bundle a prompt plus the right files and get a second-model review (API or browser) for debugging, refactors, design checks, or cross-validation.

Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.

Remembers, recalls, and organizes durable facts in a categorized markdown store at ~/Clawic/data/memory/, parallel to built-in agent memory. Use when the user says remember this, save this, note that for later, or don't forget; when they ask what did I tell you about X, when did we decide Y, or who is Z; when a stored fact is wrong, outdated, or contradicts what they just said; when they want something forgotten or deleted; when recall misses, returns stale facts, or slows down as the store grows; when duplicate or conflicting entries appear; when consolidating scattered notes, importing an existing vault, or sharing memory across devices and agents. Not for session-scoped context the runtime already holds, note-taking apps (notes), journaling practice (journal), or study techniques like spaced repetition (learn, active-recall).

积分红包一键领取·全平台自动化省心神器。触发词：领取礼包、领积分、今日礼包、领credit、积分领取、白嫖积分、签到领取、一键领取、每天自动领、安装定时任务、设置自动领取、查看领取状态、今天领了吗、开机自动领取、截图学习领取、添加领取链接、视频学习领取、从录屏学习、录屏生成定时任务、自动分析操作视频、帮我学会领XX签到、添加XX领取场景、XX

苏格拉底式追问——在执行任何计划前，彻底追问你的思维漏洞，直到达成共识再动手。

Give ClawBot access to your team's entire coding history. Muse connects your past sessions, team knowledge, and project context—so ClawBot can actually help design features, mediate team discussions, and work autonomously across your codebase. Deploy at tribeclaw.com.

Use only when SCK, Skill Creator King, or skill-creator-king is explicitly selected to create, check, or review and improve a WorkBuddy Skill after use. Excludes generic requests and discussion.

Perform complex, long-running research tasks using Gemini Deep Research Agent. Use when asked to research topics requiring multi-source synthesis, competitive analysis, market research, or comprehensive technical investigations that benefit from systematic web search and analysis.

Headless browser automation CLI for AI agents. Use when interacting with websites — navigating pages, filling forms, clicking buttons, taking screenshots, ex...

中文用户安全优先的Skill查找与安装：在 SkillHub找技能的同时，给出技能的风险评估、权限分析、隐私去向、作者信誉。 每个推荐都带档位徽章（🟢 未见风险 / 🟡 观察 / 🟠 谨慎 / 🔴 高风险 / ⚪ 未收录），绿/黄优先推荐，红/橙降权展示，安装前强制确认。 当用户说「找个 xx 技能」「有没有处理 PDF 的 skill」「SkillHub 上搜一下 xx」「按分类看技能」「推荐一个做数据分析的 skill」「这个需求有现成技能吗」「帮我找个能安全用的周报工具」等需要发现/检索/推荐/安装 Skill 的场景时使用。

WorkBuddy 变慢、卡死、转圈、卡「思考中」没反应、迟迟不出字、越聊越慢、上下文用量圈过半或爆满、积分掉得飞快、报错码时使用。当用户说「workbuddy 好慢」「workbuddy 为什么这么慢」「workbuddy 提速」「越用越卡」「切了模型也没用」「技能是不是装太多了」「要不要 /compact」「Max 模式该开还是关」「上下文满了怎么办」「圈圈过半了」「会话太长要不要新开」「检查点怎么存」「压缩会不会丢东西」「仅问答模式怎么用」「增强提示词」「积分掉得快」「报错 11115 / 6003 / 6004 / 3002 / 1001 / 11133」「这活该切哪个场景模式」时触发。覆盖：上下文用量圈六项分项（系统提示词、工具及子智能体、对话消息、连接器 MCP 及技能占用）怎么读、技能装太多吃窗口怎么关、Max 模式开关取舍、/compact 有损压缩与任务检查点六项、别频繁切模型的原因与正确顺序、新会话还是留原会话的官方判据、Ask/Plan/Craft 模式选择、模型倍率省积分、官方错误码速查、代码开发场景的 Git 分支管理与 Worktree。不适用于：WorkBuddy 的功能教学与新手入门、账号计费与充值问题、其他厂商 AI 工具的对比评测。 【用法】触发后立即跑 scripts/scan.py --symptom "用户原话"，一次给出结论/动作/依据三行，不反问、不列多个可能。

按意图、能力、风险与成本，将网页任务路由到 web_search、web_fetch、opencli、browser 或宿主等价工具上。适用于搜索、上网、查资料、打开网站、抓取网页、新闻、热点，以及网页搜索、获取当前信息、读取 URL、结构化站点访问、JS 渲染或需登录的页面、截图、网页交互，还有从网页工具故障中恢复。优化目标为最小权限、有限重试、简洁的用户进度说明、来源核验与平台兼容性。不用于纯本地文件任务，也不自动安装软件。

Automated multi-tiered memory management (HOT, WARM, COLD). Use this skill to organize, prune, and archive context during memory operations or compactions.

Find potential token waste in OpenClaw or Hermes Agent. Use when asked to reduce AI costs, review model choices, check large instructions or audit recurring tasks. Explain what matters and suggest safe next steps without changing settings.

Zoho Calendar API integration with managed OAuth. Manage calendars and events with full scheduling capabilities. Use this skill when users want to read, create, update, or delete calendar events, manage calendars, or schedule meetings. For other third party apps, use the api-gateway skill (https://clawhub.ai/byungkyu/api-gateway). Requires network access and valid Maton API key. Calls run through the `maton` CLI with OAuth login, or over raw HTTP with a Maton API key where the CLI cannot be installed. Every call is authenticated as the user's connection and reaches only what that connection's authorization allows, which the provider enforces on every request; the endpoints documented here are the ones this skill uses, and any other endpoint of this app needs the user to ask for it by name. Default to read and list calls, and confirm every write or new connection with the user. This file also documents the three constructs that turn a Zoho Calendar connection into automation, in the order they are used: the connection (the first step), a hosted function that runs a Zoho Calendar action through the Maton SDK, and a trigger that calls that function on a schedule or on an event. Those sections are the platform's own reference text, shared with the api-gateway skill, with Zoho Calendar examples; they add no Zoho Calendar capability - Zoho Calendar is not an event source, a trigger cannot read Zoho Calendar data, and the files under `references/<source>/triggers.md` are the platform's event catalogues for the sources Maton offers (time, Calendly, GitHub, Gmail, HubSpot, Linear, Notion, Slack, Stripe).