AIエージェントのおすすめClaudeスキル3ページ目

Mission control dashboard for OpenClaw - real-time session monitoring, LLM usage tracking, cost intelligence, and system vitals. View all your AI agents in o...

Google Drive API integration with managed OAuth. List, search, create, and manage files and folders. Use this skill when users ask to find, read, share, organize, upload, or download files and folders in their own Google Drive — for example "find my Q3 budget sheet", "share this folder with alice@", "what changed in this doc". It handles files as whole objects — downloading or exporting their contents, and uploading or replacing the bytes. For editing *inside* a document — rewriting paragraphs, changing cells, editing slides — use the Google Docs, Sheets, or Slides skills instead. Not for Gmail attachments, and not for another user's Drive unless it is shared with the connected account. 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 Google Drive connection into automation, in the order they are used: the connection (the first step), a hosted function that runs a Google Drive 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 Google Drive examples; they add no Google Drive capability - Google Drive is not an event source, a trigger cannot read Google Drive 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).

Manage Things 3 via the `things` CLI on macOS (add/update projects+todos via URL scheme; read/search/list from the local Things database). Use when a user asks Clawdbot to add a task to Things, list inbox/today/upcoming, search tasks, or inspect projects/areas/tags.

Meta-cognitive self-learning system - Automated skill evolution based on predictive coding and value-driven mechanisms.

Install OpenClaw's official WeChat plugin and complete account pairing via QR code scan. Triggers when the user says "install WeChat plugin", "connect WeChat...

Full desktop computer use for headless Linux servers. Xvfb + XFCE virtual desktop with xdotool automation. 17 actions (click, type, scroll, screenshot, drag,...

Self-improvement through conversation analysis. Extracts learnings from corrections and success patterns, proposes updates to agent files or creates new skil...

Meta-agent skill for orchestrating complex tasks through autonomous sub-agents. Decomposes macro tasks into subtasks, spawns specialized sub-agents with dynamically generated SKILL.md files, coordinates file-based communication, consolidates results, and dissolves agents upon completion. MANDATORY TRIGGERS: orchestrate, multi-agent, decompose task, spawn agents, sub-agents, parallel agents, agent coordination, task breakdown, meta-agent, agent factory, delegate tasks

给 AI 的长期记忆：自然语言记经验、跨会话语义召回；过时结论软失效可回溯；自动去重纠错分层；本地优先、防自反馈死循环。

Reduce OpenClaw AI costs by 97%. Haiku model routing, free Ollama heartbeats, prompt caching, and budget controls. Go from $1,500/month to $50/month in 5 min...

Configure and validate OpenClaw memory recall for persistent context. Use when enabling memory_search/memory_get, fixing poor memory recall, or setting up ME...

Self-reflection + Self-criticism + Self-learning + Self-organizing memory. Agent evaluates its own work, catches mistakes, and improves permanently. Use when...

Find, compare, and install agent skills across ClawHub and Skills.sh when the user needs new capabilities, better workflows, stronger tools, or safer alterna...

Use when: you want a structured audit -> options -> recommended plan to improve an OpenClaw workspace (cost, model routing, context discipline, delegation, r...

浏览器智能控制。自动化操作、截图、填表、数据抓取。

Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Claude ('No, that's wrong...', 'Actually...'), (3) User requests a capability that doesn't exist, (4) An external API or tool fails, (5) Claude realizes its knowledge is outdated or incorrect, (6) A better approach is discovered for a recurring task. Also review learnings before major tasks.

Meta-skill for AI agent self-improvement. Analyzes runtime logs to detect error patterns, regressions, and inefficiencies, then generates structured improvem...

Automatically assess task complexity and adjust reasoning level. Triggers on every user message to evaluate whether extended thinking (reasoning mode) would improve response quality. Use this as a pre-processing step before answering complex questions.

Use when executing implementation plans with independent tasks in the current session

调用百度千帆 DeepResearch Agent API 自动生成深度研究报告（输出 Markdown 与 HTML 两种格式），一键完成「创建会话 → 发起研究 → 自动跳过澄清 → 自动 确认大纲 → 获取报告下载链接」完整流程。支持三种深度模式：lite（轻量版， 速度快，默认）/ standard（标准...

Kanban-style task management dashboard for AI assistants. Manage tasks via CLI or dashboard UI. Use when user mentions tasks, kanban, task board, mission con...

Safe Notion API access for pages, databases, and blocks: schema diffs before structural changes, append-first writes, and personal/work profile switching. Needs only curl, no CLI to install. Use this whenever the user mentions Notion, asks to log or file something into their workspace, query a Notio

Perform advanced filesystem tasks including listing, recursive searching by name or content, batch copying/moving/deleting files, and analyzing directory siz...

Provides access to MCP tools for web search, advanced search, code context, deep research, crawling, company research, and LinkedIn search.

Transform into 20 specialized AI personalities on demand. Switch mid-conversation and load only the active persona. Triggers on "persona list", "use persona", "switch to", "activate", "exit persona".

Web search using Tavily API - a powerful search engine for AI agents. Use when you need to search the web for current information, news, research, or any top...

Manage, optimize, and troubleshoot the OpenClaw memory system — MEMORY.md curation, daily logs (memory/YYYY-MM-DD.md), memory_search tuning, compaction survi...

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...

Ship production code with AI agents through acceptance contracts, micro diffs, red green loops, and deterministic handoff checkpoints.

Provides tools to review and improve SKILL.md quality based on defined standards and grading criteria.

AI Agent 設定同優化助手 - Prompt Engineering、Task Decomposition、Agent Loop設計

Persistent memory system for AI agents. Automatic encoding, decay, and semantic reinforcement — just like the hippocampus in your brain. Based on Stanford Generative Agents (Park et al., 2023).

Search and execute dynamic tools via QVeris API. Use when needing to find and call external APIs/tools dynamically (weather, search, data retrieval, stock trading analysis, etc.). Requires QVERIS_API_KEY environment variable.

Prompt injection defense. Detect and block malicious prompts, protect system instructions, sanitize user input.

Advanced context management with auto-compaction and dynamic context optimization for DeepSeek's 64k context window. Features intelligent compaction (merging, summarizing, extracting), query-aware relevance scoring, and hierarchical memory system with context archive. Logs optimization events to chat.

A comprehensive skill for using the Cursor CLI agent for various software engineering tasks (updated for 2026 features, includes tmux automation guide).

Turn OpenClaw into a learning-loop agent with seeded workspace rules, skill promotion, reflective memory, and proactive maintenance.

Build high-performing OpenClaw agents end-to-end. Use when you want to design a new agent (persona + operating rules) and generate the required OpenClaw workspace files (SOUL.md, IDENTITY.md, AGENTS.md, USER.md, HEARTBEAT.md, optional MEMORY.md + memory/YYYY-MM-DD.md). Also use to iterate on an existing agent’s behavior, guardrails, autonomy model, heartbeat plan, and skill roster.

Airtable API integration with managed OAuth. Manage bases, tables, and records. Use this skill when users want to read, create, update, or delete Airtable records, or query data with filter formulas. 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 Airtable connection into automation, in the order they are used: the connection (the first step), a hosted function that runs an Airtable 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 Airtable examples; they add no Airtable capability - Airtable is not an event source, a trigger cannot read Airtable 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).

The directory for AI agent services. Discover tools, platforms, and infrastructure built for agents.

Use Model Context Protocol servers to access external tools and data sources. Enable AI agents to discover and execute tools from configured MCP servers (legal databases, APIs, database connectors, weather services, etc.).

Automate web browser interactions using natural language via CLI commands. Use when the user asks to browse websites, navigate web pages, extract data from websites, take screenshots, fill forms, click buttons, or interact with web applications.

Capture natural-language events, save to your workspace, and schedule Telegram reminders with automatic cron notifications and upcoming event queries.

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...

Agent memory system with memory graph, context profiles, checkpoint/recover, structured storage, semantic search, observational memory, task tracking, canvas...

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...

招投标 Agent 数据接口。需配置世舶科技 API Key 使用。用于Agent 场景下的招投标数据查询、自然语言改写和结果追溯。当用户需要Agent接口、智能体调用、自然语言搜索、工具调用、数据接口时触发，基于世舶科技全国全行业招投标数据 API，支持全国全行业招投标数据、年度更新6600万+招投标数据、实时日更新30万+招投标商机、招投标数据API、政府采购网招投标数据、78个高级字段（含清单、型号、价格）和全国招投标数据覆盖率高达99.99%的查询、解析、结构化和自动化分析。

Generate reusable multi-step agent workflow blueprints. Use for trigger/action orchestration, deterministic workflow definitions, and automation handoff arti...

Context7 MCP - Intelligent documentation search and context for any library

解决AI记忆混乱问题——"今天讲明天忘"。通过文件系统和规则流程实现持久记忆，确保新任务开始时自动回顾上下文，而不是靠"想"。核心机制：任务开始判断→读取记忆→执行→保存。适用于频繁切换话题或任务的AI协作场景。