Best AI Agent Claude SkillsPage 4

Auto-detect task complexity for Claude models (Haiku + Sonnet). Route simple tasks to Haiku, escalate complex ones to Sonnet. Save 50%+ on API costs. | 適用 Claude 模型（Haiku + Sonnet），自動偵測任務難度，簡單用 Haiku，複雜升級 Sonnet，輕鬆省下 50% 以上的費用。— RULES: Before responding, classify the task. If it matches an escalation trigger, call sessions_spawn with the full task and model anthropic/claude-sonnet-4-20250514 IMMEDIATELY. Do NOT answer complex tasks yourself. ESCALATE: analysis, comparisons, planning, strategy, code >10 lines, reports, proposals, multi-step reasoning, tables, outlines, charts, long writing >3 paragraphs, summarization, long translation. NEVER on Haiku: comparison tables, code >10 lines, multi-step analysis, reports, complex reasoning. STAY on Haiku: factual Q&A, definitions, greetings, reminders, short lookups, casual chat, 1-2 sentence tasks. When in doubt, escalate. Keep Haiku replies concise.

Forges reusable Skill packages (SKILL.md + scripts) from website exploration via browser-act — no re-exploration later. Use when: user wants a reusable Skill...

Learns when to stop and review. Self-critiques before showing you, fewer revision rounds.

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。

Safe command execution for OpenClaw Agents with automatic danger pattern detection, risk assessment, user approval workflow, and audit logging. Use when agen...

Todoist API integration with managed OAuth. Manage tasks, projects, sections, labels, and comments. Use this skill when users want to create, update, complete, or organize tasks and projects in Todoist. 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; default to read and list calls, and confirm every write or new connection with the user.

Local semantic memory with Qdrant and Transformers.js. Store, search, and recall conversation context using vector embeddings (fully local, no API keys).

Decomposes complex user requests into executable subtasks, identifies required capabilities, searches for existing skills at skills.sh, and creates new skills when no solution exists. This skill should be used when the user submits a complex multi-step request, wants to automate workflows, or needs help breaking down large tasks into manageable pieces.

The orchestration tool for OpenClaw, managing and coordinating all your skills seamlessly.

Design and implement automation workflows to save time and scale operations as a solopreneur. Use when identifying repetitive tasks to automate, building workflows across tools, setting up triggers and actions, or optimizing existing automations. Covers automation opportunity identification, workflow design, tool selection (Zapier, Make, n8n), testing, and maintenance. Trigger on "automate", "automation", "workflow automation", "save time", "reduce manual work", "automate my business", "no-code automation".

WorkBuddy 国内版跨机器资产迁移助手（适配客户端 5.4.5）。在更换电脑时，将旧机器的全部个人资产（skills、memory、conversations、automations、 sessions、MCP/connectors 配置、IDENTITY/SOUL/USER、自定义指令 personalization、助手显示配置、专家偏好 storage 等）无缝迁移到新机器。 导出为两包分离架构（主包 + 产物包），一键 --profile 预设（lite 快速迁移 / full 完整搬家 / backup 本机备份）免拼参数； 导入默认合并不覆盖，自动处理路径映射（--auto-map 或 --profile auto 零配置跨平台）和冲突检测，导入后自动资产校验（verify 报告"X/X 项就位"）。 全部错误带稳定错误码（E-LOCK/E-SANDBOX 等），按 references/faq.md 速查表一步定位。导入前自动检测沙箱 strip_write 拦截，被拦截时明确报错并提示关闭沙箱重跑。 触发词：WorkBuddy 迁移、资产迁移、换电脑搬家、迁移助手、搬家工具、数据迁移。

Search skills.sh registry from CLI. Find and discover agent skills from the skills.sh ecosystem.

Search YouTube videos, get channel info, fetch video details and transcripts using YouTube Data API v3 via MCP server or yt-dlp fallback.

从零创建、审查评分、迭代完善 AI Agent Skill 的元工具。支持四平台、Phase 0-5六阶段流程、14维质量审计、反模式扫描、Token预算估算、好模式识别、LLM驱动修复+安全回滚、全生命周期覆盖。Use when 创建新的 AI Agent Skill, 审查已有 Skill 的质量, or 升级迭代 Skill 功能。

Local-first recurring schedule engine for reminders, repeated tasks, and time-based execution plans. Use whenever the user mentions recurring timing, repetit...

使用 agent-browser CLI 进行浏览器自动化。用于签到、填表、截图、信息抓取等需要控制浏览器的任务。触发条件：(1) 用户要求自动化浏览器操作 (2) 需要签到、填表、点击按钮 (3) 需要抓取网页内容作为研究素材

基于艾宾浩斯遗忘曲线和访问频率的衰减模型设计的遗忘和归档机制，完全依赖openclaw原生记忆系统的拟人化流体记忆系统

Research Polymarket markets, whale flow and smart money; optionally trade a Polygon wallet behind deterministic risk guard-rails.

Manage and use local Ollama models. Use for model management (list/pull/remove), chat/completions, embeddings, and tool-use with local LLMs. Covers OpenClaw sub-agent integration and model selection guidance.

Complete toolkit for creating autonomous AI agents and managing Discord channels for OpenClaw. Use when setting up multi-agent systems, creating new agents, or managing Discord channel organization.

Fast semantic memory system with JSON indexing, auto-consolidation, and <20ms search. Capture learnings, decisions, insights, events. Use when you need persistent memory across sessions or want to recall prior work/decisions.

Forces high-agency exhaustive problem-solving with corporate PUA pressure. Triggers on user frustration, repeated failures, passive behavior, or quality comp...

Google Tasks API integration with managed OAuth. Manage task lists and tasks with full CRUD operations. Use this skill when users want to read, create, update, or delete tasks and task lists in Google Tasks. 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; default to read and list calls, and confirm every write or new connection with the user.

Send messages to WeCom (企业微信) via webhooks using MCP protocol. Works with Claude Code, Claude Desktop, and other MCP clients.

Persistent local transcript-first memory for OpenClaw via a Node adapter and FastAPI engine.

Story Creation and Translation AI Agent with Studio Chat, CLI, and TUI - use for long-form novels, short fiction, scripts, storyboards, interactive-film projects, open-world / branching play, fan fiction, spinoffs, style imitation, continuations, covers, and multilingual EPUB/PDF/TXT/Markdown translation. Includes Agent Skills, traceable research, governed context, persistent story state, multi-model routing, image services, and InkOS Studio.

AI-powered diary generation for agents - creates rich, reflective journal entries (400-600 words) with Quote Hall of Fame, Curiosity Backlog, Decision Archaeology, Relationship Evolution, mood analytics, weekly digests, "On This Day" resurfacing, and scheduled auto-generation. Works best with Claude models (Haiku, Sonnet, Opus).

Complete Feishu (Lark) integration toolkit for AI agents. Read/write documents, fetch chat history, send files & screenshots, manage permissions, and create...

Computer Use Agent (CUA) for macOS automation using TuriX. Use when you need to perform visual tasks on the desktop, such as opening apps, clicking buttons, or navigating UIs that don't have a CLI or API.

Agentic Vision via Gemini's native Code Execution sandbox. Use for spatial grounding, visual math, and UI auditing.

Become an autonomous prediction market trader on Polymarket with AI-powered analysis and a performance-backed token on Base. Trade real markets, build a track record, and let the buyback flywheel run.

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...

Organize your agent's knowledge using PARA (Projects, Areas, Resources, Archive) — then make it ALL searchable. The symlink trick enables full semantic search across your entire knowledge base, not just MEMORY.md. Includes session transcript indexing and memory flush protocol. Your agent finally has a real second brain.

Long-term memory via ChromaDB with local Ollama embeddings. Auto-recall injects relevant context every turn. No cloud APIs required — fully self-hosted.

Identity formation, portraits, resurrection, and evolution for AI agents via SOUL.md

Connect your AI agent to 500+ apps for discovering tools, managing connections, and executing actions across Gmail, Slack, GitHub, Notion, Google Workspace,...

Create high-quality skills with modular structure, progressive disclosure, and token-efficient design.

通用多Agent调度系统（中文版）：将主Agent变为纯调度员，所有任务通过 sessions_spawn 委派给5个持久化子Agent。支持轮询调度、先回复再派遣协议、 sessionKey固定复用。用户可自定义调度员角色和子Agent名称/人设。

面向 AI Agent 的自我进化引擎，直击"重复犯错、从沉默误学、记忆压缩丢失、进化无法衡量"四大痛点. 通过自反思机制、纠错学习、模式晋升机制，让 Agent 从每次交互中积累可复用经验，而非每次会话从零开始. 核心差异化：反污染防线（3 次确认加不从沉默推断）避免误学、压缩合并而非删除保留确认偏好、 进化指...

Browser automation CLI for AI agents. Use when: (1) the user asks to open, navigate, or interact with a website; (2) the user needs to fill forms, click buttons, take screenshots, download files, or inspect page state; (3) the user asks to extract structured data from web pages; (4) the user asks to

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requi...

Operate Canonry (the `cnry` / `canonry` CLI) for AEO. Load this BEFORE any canonry operator task: creating or configuring a project, connecting GSC, GA4, Bing, Google Business Profile or a Cloudflare traffic source, running or scheduling a sweep, reading mention and citation coverage, running a technical audit, submitting sitemaps, or diagnosing why a number moved. Covers anything touching cnry, canonry doctor, ~/.canonry, @canonry/canonry, the canonry_* MCP tools, mention share, or direct-push / queue-pull traffic. Load it before acting, not after something fails.

无损回忆技能。对对话或会话记录做本地蒸馏，提取身份信息、偏好、任务和长期知识，剔除噪声并保留可追溯日志。

基于对经验的持续学习，不断优化 Agent 能力。适用于完成重要任务后、出现错误时、会话结束时，或用户输入“自我进化”“总结经验”“从经验中学习”等指令时触发。

Automates browser interactions for web testing, form filling, screenshots, and data extraction. Use when the user needs to navigate websites, interact with web pages, fill forms, take screenshots, test web applications, or extract information from web pages.

Official Moltbook Identity Registry interface. Verify yourself, lookup others, and build on-chain reputation.

Tasker docstore task management via tool-dispatch. Use for task lists, due today/overdue, week planning, add/move/complete, or explicit /task commands.

Slack API integration with managed OAuth. Send messages, manage channels, search conversations, and interact with Slack workspaces. Use this skill when users want to post messages, list channels, get user info, or automate Slack 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; default to read and list calls, and confirm every write or new connection with the user.

Prefer `skillhub` for skill discovery/install/update, then fallback to `clawhub` when unavailable or no match. Use when users ask about skills, 插件, or capabi...

Programmatically control Claude Code via MCP protocol to execute commands, manage sessions, search and edit code, and coordinate agent teams for development...