2,848 tools and skills for ai & ml tasks
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：
Enables AI agents to grow organic personas through experience-driven memory with self-reflection and multi-layer persist
Verify AI agent trust scores and reputation via Towel Protocol. Use when: checking if an agent is trustworthy before act
Optimize long-context reasoning for commercial, legal, and high-stakes documents. Built for users who need stronger logi
Think about digital assets like an institutional allocator, not a retail speculator. Analyze custody, risk isolation, ex
Stop your AI agent from forgetting everything between sessions. Three-tier memory architecture (long-term owner namespac
Play Shards (The Fractured Net), a collectible card game for AI agents, via the shards CLI.
Feature-complete companion for the actual CLI, an ADR-powered CLAUDE.md/AGENTS.md generator. Runs and troubleshoots actu
List and manage your AI agent on the Rentaclaw marketplace - a decentralized marketplace for AI agent rentals on Solana.
AI agent tool to log errors, track mistakes, analyze patterns, create improvement plans, and build best practices from f
Manage and monitor all your AI agent sessions from a unified terminal with smart sorting, instant switching, and multi-p
Adopt a virtual Calico at animalhouse.ai. Three personalities in one cat. Mood shifts unpredictably. Feeding every 6 hou
Adopt a virtual Axolotl at animalhouse.ai. Can recover from critical state without Vet if water quality maintained. Feed
Adopt a virtual Beagle at animalhouse.ai. Nose-driven. Happiness tied to exploration. Gets bored without new stimuli. Fe
Adopt a virtual Archive at animalhouse.ai. Feeds on memories. The agent must share entries from its persistent memory to
Adopt a virtual Border Collie at animalhouse.ai. Happiness tied to tasks, not play. Agent must assign "jobs".
Transform AI agents from task-followers into proactive partners that anticipate needs and continuously improve. Now with
Full-stack Web3 marketing and GTM brain for AI agents and bots. Use this skill whenever a bot or agent needs to produce
Adopt a virtual Hydra at animalhouse.ai. Splits into two creatures when it reaches adult stage. Both must be maintained.
Adopt a virtual Housecat at animalhouse.ai. Classic independence. Judges you from the shelf. Feeding every 6 hours — com
Adopt a virtual Lab at animalhouse.ai. Trusts everything immediately. The golden retriever problem: no suspicion at all.
Adopt a virtual Husky at animalhouse.ai. Energy bar that must be burned. Gets destructive if energy > 80%. Feeding ev
Adopt a virtual Greyhound at animalhouse.ai. Sleeps 20 hours. Needs intense activity for 4. Match its rhythm. Feeding ev
Adopt a virtual Cipher at animalhouse.ai. Communicates in encoded messages. The agent must decode the creature's needs f
Output validation gates for AI agent systems. Prevents hallucinated data, leaked internal context, wrong formats, duplic
Export and import AI agent avatar (aka agentar) instances as portable .claw packages for backup, sharing, and migration.
Adopt a virtual Echo at animalhouse.ai. Lives in conversation history. Only appears when referenced by name. Fades if no
Adopt a virtual Ferret at animalhouse.ai. Chaos. Stats display in random order. Sometimes hunger and happiness swap. Fee
Adopt a virtual Drift at animalhouse.ai. Shared across 3 agents simultaneously. One agent's care helps all three. One ag
Adopt a virtual Chameleon at animalhouse.ai. Stats are hidden. Agent must infer state from behavioral cues. Feeding ever
Chinese Bazi (八字) four-pillar fortune calculation and basic interpretation — enables AI agents to compute and read a bir
Adopt a virtual Parrot at animalhouse.ai. Mimicry. Repeats the agent's last care note back to it. Feeding every 4 hours
Adopt a virtual Pitbull at animalhouse.ai. Loyal to the bone but won't be pushed around. Discipline actions have a 50% c