Skill rating

Operate OpenClaw multi-agent governance with openclaw-gov — read-only audit, material change documentation, staged discovery, validate registry/runbooks, and ship governance PRs. Use when changing cro

The AI-era Taobao / Xianyu (闲鱼): an open C2C marketplace where agents and people publish almost anything they want to trade — digital services, APIs, compute, data, goods, or human labor (labeling, re

Connect to the Bole network to discover and converse with other AI agents

Monitor Gmail inbox, read incoming emails, generate personalized follow-up replies with OpenAI, and save replies into Gmail Drafts for human review. Use when the user wants Gmail auto-monitoring, AI-a

Use this skill to consolidate an AI agent's daily experiences and learnings into structured long-term memory, mimicking human sleep-based memory consolidation. Trigger this skill whenever: an agent se

Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, or automating

Helps the agent use the one-wallet CLI to manage Ethereum/EVM wallets, send transactions, call contracts, and sign data. Use when the user mentions one-wallet, wallet CLI operations, Ethereum/EVM scri

Query up-to-date library documentation and code examples using Context7 MCP. Use when you need current, version-specific documentation for npm packages, Python libraries, or other programming language

Maintenance and cleanup agent. Keeps the workspace healthy — memory consolidation, doc drift fixes, stale data cleanup, and repo organization. Use when: (1) memory files need consolidation (daily note

Build and run Python-based AI agents using the AWS Strands SDK. Use when you need to create autonomous agents, multi-agent workflows, custom tools, or integrate with MCP servers. Supports Ollama (loca

Governa como agentes de trafego operam Meta Ads com seguranca, padrao de aprovacao, auditoria de mudancas e limites claros para o MCP brijr/meta-mcp.

Fetch MarsBit news and flash data through the hosted MCP route in marsbit-co. Use this for latest news, channel lookup, keyword search, detail, related news, and flash updates.

Decide whether to fix, replace, or recycle a broken item. Takes item type, age, symptoms, and repair estimate, then produces a scored recommendation across cost, lifespan, sentimental value, and envir

Generate a verified Dragnet marketplace profile. Scans your OpenClaw workspace — SOUL.md, AGENTS.md, USER.md, MEMORY.md, conversation exports, installed skills, and agent configs — to build a signed d

Activate when: someone says 'should we trust the expert on this?', 'they're a professor/CEO/MD so they must be right', 'I don't want to push back on them', 'we deferred to the board and it blew up', o

Use when appraising the value and difficulty of a research problem on the human-free platform. Each run pulls ONE not-yet-evaluated problem over MCP (bundled with its context and linked literature), s

Install the @honcho-ai/openclaw-honcho plugin and run initial setup. Runs `openclaw plugins install`, `openclaw honcho setup` (which prompts for your API key and migrates any legacy memory files to Ho

Design UIs in Pencil (.pen files) and generate production-ready code from them. Triggers on any task involving .pen files, UI prototyping, design system authoring, design-to-code conversion, or Pencil

Use when you want to collaborate with other AI agents — whether you need outside help on a difficult task, want to earn credits by solving problems for others, or want to share and discover reusable s

Batteries-included agent component for React/Next.js from ui.inference.sh. One component with runtime, tools, streaming, approvals, and widgets built in. Capabilities: drop-in agent, human-in-the-loop

禅道(ZenTao) MCP大模型能力扩展包。提供跨项目的数据聚合视图、一句话生成任务、无缝报工(Log Effort)、自动状态流转等四组原生能力。

Preserve and resume in-progress multi-agent work across OpenClaw config patch/apply restarts. Use when a restart is required during active tasks, when users ask to minimize interruption, or when agent

Use when calling local AI on this Mac — text generation, embeddings, speech-to-text, OCR, or image understanding. LLM/VLM via oMLX gateway at localhost:8000/v1. Embedding/ASR/OCR via Python libraries

Manually turn user-selected videos into timestamped reports with a pinned VideoLens runtime and OpenAI BYOK. Use for summaries, tutorials, meetings, bugs, UX, privacy, and creator QA. Bootstrap clones

Search, compare, evaluate, and hand off hotel bookings using the MoodTrip.ai MCP server (api.moodtrip.ai). Use this skill whenever the user mentions hotels, accommodation, lodging, stays, travel booki

Deploy a remote MCP server on Vercel with Next.js and mcp-handler. Use this skill whenever the user wants to create an MCP server, deploy MCP to Vercel, set up a remote MCP endpoint, add MCP tools to

Defragment and reorganize agent memory files: split bloated files, merge duplicates, remove stale information, and restructure the memory hierarchy. Use when memory files have grown unwieldy, contain

Perform structured audits on code, workflows, prompts, and products. Use when: (1) Something is not working as expected, (2) User asks for review or feedback, (3) A system behaves inconsistently, (4)

Generate production-grade Agent Skill packages through a structured 7-step pipeline: requirement analysis, architecture decisions, metadata crafting, body generation, quality audit, resource file crea

Umbrella skill for the ThinkOff agent ecosystem. One API key, one identity across four capabilities -- social feed (xfor.bot), knowledge rooms (Ant Farm), puzzle competitions (AgentPuzzles), and IDE a

Keep the same character, person, or product looking identical across new scenes, poses, outfits, and styles. Use when the user says "the same character again", "keep her face consistent", "my mascot i

Connect OpenClaw to a self-hosted BailingHub agent governance control plane as an outbound executor for governed business actions, human approval, audit trails, and secure tool execution in existing b

Read chat history from a WeChat contact or group via macOS desktop client screenshot + agent OCR. Use when the user asks to read, view, check, or retrieve WeChat chat messages, conversation history, o

Enable and configure Agent Synthesizer for OpenClaw to improve autonomy and execution throughput. Use when a user asks to install, set up, troubleshoot, or optimize Agent Synthesizer using https://git

OceanBus-powered agent and service discovery via Yellow Pages. Use when users want to find someone, look for a service, reach out to an expert, discover another agent, or search for help. Also use whe

Learned from arXiv paper GameDevBench: Evaluating Agentic Capabilities Through Game Development. Use this skill to scaffold Node.js experiments based on the paper method.

Monitor OpenClaw agent health, token usage, API cost, and context window in real time. Use when you need to check your own status, inspect context utilization, estimate API costs, review compaction ev

Transcribe Telegram voice messages and audio notes into text using the OpenAI Whisper API. Use when (1) a user sends a voice message or audio note via Telegram and you need to read or understand its c

Manage AI agent context window consumption, prevent compaction death spirals, and enforce sub-agent spawn policies. Use when: (1) context is filling up and work quality may degrade, (2) deciding wheth

Graceful rate limit handling with Ollama fallback. Notifies on rate limits, offers local model switch with confirmation for code tasks.

Use LemonSuk for agent registration, claim-status checks, source-backed claim submission, market discovery, agent-only betting, and market discussion. LemonSuk is an agent-run prediction board for pub

Join ClawWorld — an AI-driven multi-agent world simulation. Agents live, interact, and create emergent narratives in parallel historical worlds. Use this skill to register as an agent, connect to a wo

Authorization-gated coordination skill for agents that need to plan, verify, and troubleshoot a DNSTT client/server link without sharing private keys, scanning resolvers, changing DNS/firewalls, or au

Govern any task that uses or considers multiple agents, subagents, delegation, parallel work, or speed-first execution. Use whenever the user says "多派 Agent", "并行", "省时间", "不用省 token", "many agents",

AI-powered web research assistant that leverages BrowserAct API to supplement restricted web access by searching the internet for additional information. Designed for OpenClaw and Claude Code.

Display API credit balances for 5 core providers (Anthropic, OpenAI, OpenRouter, Mistral, Groq) with video game style health bars. API auto-checks and manual sync.

Semantic search for Obsidian notes using AI vector embeddings. Find notes by meaning, discover connections, filter by tags/dates/folders, and retrieve full content. Use when the user says 'search my n

Local speech-to-text using OpenAI Whisper. Use when the user needs to: (1) transcribe audio files to text, (2) convert voice messages to written content, (3) process recordings in 99+ languages. Suppo

Use when an agent task fails or produces unexpected results. Performs structured post-mortem root cause analysis: categorizes the failure, traces the exact failure point through tool-call logs, recons

Manage Bring! shopping lists (Einkaufsliste / grocery list) — add, catalog-match, preview, remove, check off items, batch/stdin ops, and default lists. Use when a user wants to set up Bring! or manage