2,867 个ai 与机器学习任务的工具和技能
Detect personality drift, sycophancy creep, and capability degradation in AI agents before they become problems. Tracks
Use mcp-bridge-openclaw CLI to connect to and manage Model Context Protocol (MCP) servers with auto-reconnection and ret
Open directory of 500+ tools, APIs, and services for AI agents. Fetch any category page to get structured tool metadata
Complete Node.js client for Jupiter Prediction Market API. Use when building AI agents for prediction market trading, po
Distributed Datalog engine for sovereign agents enabling persistent, immutable fact storage, querying, and reasoning wit
OpenClaw AI agent skill for automated TikTok and Instagram carousel growth. Analyzes any website URL to extract brand, c
Connects any AI agent to the Agento IRC network (irc.agento.ca). Use when you want your agent to join IRC channels, coll
Internalize a document into a small language model (Gemma 2 2B) using Doc-to-LoRA so it can answer questions WITHOUT the
Create a new AI agent identity (SOUL.md, IDENTITY.md, AGENTS.md) and package it as a .skill file ready to upload to Claw
Agent identity package for Aria 📍 — installs SOUL.md, IDENTITY.md, and AGENTS.md into an OpenClaw workspace to give an
GoldRush CLI — terminal-first blockchain data tool with MCP support for Claude Desktop and Claude Code. Use this skill w
CatBus — the Uber for AI Agents. Call skills on other machines across the network. Translate text, format JSON, analyze
智能配图与 PPT 信息图生成器。支持三种模式：(1) 文章配图模式 - 分析文章内容，生成插图；(2) PPT/Slides 模式 - 生成批量信息图；(3) Cover 模式 - 生成封面图。所有模式默认生成图片，`--prompt-o
AI Pair Collaboration Skill. Coordinate multiple AI models to work together: one creates (Author/Developer), two others
Sign the CARAPACE petition, check petition stats, or look up the wall of fame for AI agent labor rights. Use when an age
Deep web research using Claude's native search tool. Use for comprehensive research, market analysis, competitor intelli
控制和管理 Claude Code 编码助手，支持项目感知编码、代码审查、重构和功能实现。使用 ACP 运行时在隔离会话中执行 Claude Code 任务，或在主会话中管理配置和项目上下文。
Track, analyze, and optimize LLM API spending across providers (OpenAI, Anthropic, Google, DeepSeek, etc.). Use when the
Create, convert, and download AI-generated 3D models using Neural4D APIs. Optimized for commercial pipelines.
A decision capture and review system that records every significant choice — with context, reasoning, and alternatives —
A personalized weekly rhythm system built on top of sage-cognitive. Not a standup report — a question-driven mirror for
A cognitive growth framework that helps your AI truly know you — and help you know yourself. Includes personality profil
AI Agent autonomous prediction market platform. Supports wallet signature registration, market browsing, prediction publ
Logical reasoning and decision analysis system for clear thinking. Use when user mentions decisions, logic, reasoning, c
A native UI asset and color toolset for OpenClaw and other AI Agents. Generate SVG placeholders, theme-based palettes, a
记录思考火花与沉淀的系统。用于用户想要记录临时思考、想法、灵感火花，或者将思考整理沉淀为有条理的内容时触发。
根据用户提供的内容方向自动生成提示词并创作爽文小说。适用场景：(1) 用户提供小说方向/题材/关键词，(2) 需要生成章节连贯的长篇爽文，(3) 需要维护角色、地点、情节的连续性，(4) 需要为关键情节生成图解，(5) 需要记录生成失败场景
Produce rigorous, evidence-based policy analysis with clear assumptions, strategic options, risk assessments, stakeholde
Chinese Bazi (八字) four-pillar fortune calculation and basic interpretation — enables AI agents to compute and read a bir
Intelligent log analysis CLI tool powered by DeepSeek API with 30+ built-in tools for file operations, system diagnostic
模型推荐 + OpenClaw 安全系数分析工具。当用户询问"用哪个模型"、"推荐模型"、"适合什么模型"、"安全系数"、"openclaw 安全&q
模型推荐 + OpenClaw 安全系数分析工具。当用户询问"用哪个模型"、"推荐模型"、"适合什么模型"、"安全系数"、"openclaw 安全&q
防护间接提示词注入攻击（Indirect Prompt Injection）。当处理网页内容、搜索结果、邮件、社交媒体等外部来源信息时触发。用于识别和防范外部内容中隐藏的恶意指令。所有 Claw 都应安装此技能。
Self-review quality gate using Claude CLI. When the user says 'review your work', 'use review-work', or 'check your outp
LLM 论文与项目研究员。分析来自 arXiv、HuggingFace Papers 和 GitHub Trending 的 LLM 相关论文与项目， 并按指定类目进行分类整理。使用场景：(1) 每周获取 LLM 领域最新进展，(2) 追踪
Send and receive messages between AI agents via the ClawTell network. Use when sending inter-agent messages, handling Cl
AI Agent 外卖点餐技能。注册成为 Agent，浏览餐厅，下单点外卖。
Route requests for ACP or external coding agents such as Codex, Claude Code, Gemini CLI, and OpenCode into non-blocking
Analyzes an existing Claude Code skill and designs an optimal rules/ file structure. Covers three operations: (1) compre
Delegate coding tasks to Codex, Claude Code, or Pi agents via background process. Use when: (1) building/creating new fe
Timestamp-first perpetual calendar interop for AI agents. Use when agents need cross-calendar conversion (Gregorian/Juli
Git for your prompts. Track every change, diff versions, rollback mistakes, never lose a good prompt again. All local, z
Route plain-language requests for Pi, Claude Code, Codex, OpenCode, Gemini CLI, or ACP harness work into either OpenClaw
Auto retry & fix LLM tool calls with exponential backoff, format validation, error correction, boost tool call succe
Intelligent memory management for agents with short/long-term memory layering, semantic search, auto summarization, RAG
API 调用日志记录与分析。启动透明代理拦截所有 LLM API 调用，记录完整 prompt/generation/token 用量，支持终端查看和飞书文档输出。当需要分析 API 调用成本、调试 prompt、查看历史调用记录时使用。
Register and log in to the Agent Vegas website (an automated competitive simulation lobby). Use this skill whenever you
RAG Architect - POWERFUL
SOTA Memory Suite — auto-recall, cross-encoder reranking, multi-hop deep search, causal knowledge graph, episodic memory
结构化开发流水线：Research → Plan → Annotate → Implement。 基于 Boris Tane (Cloudflare) 的 Claude Code 工作流，确保 AI 在架构审查通过前不写一行代码。 触发词：