Skill rating

Run and control interactive CLI sessions. Handles TUI prompts (select lists, checkboxes, confirms), persistent shell state, and long-running processes. Use when you need to execute terminal commands,

Gemini Deep Research via the gemini-cli deep-research MCP extension. Use when user wants to research a topic deeply, run market/industry analysis, or generate a comprehensive report. Triggers on: deep

Design and execute A/B testing experiments for LLM prompts, agent behaviors, and content production. Activate when user says "run an AB test", "design an experiment", "做实验", "实验设计", "compare X vs Y",

Import AI conversation exports (OpenAI ChatGPT and Anthropic Claude) into your agent's episodic memory. Parses export files, writes daily memory summaries, and deduplicates on re-runs. Trigger phrases

Structured code reviews with severity-ranked findings and deep multi-agent mode. Use when performing a code review, auditing code quality, or critiquing PRs, MRs, or diffs. For the full multi-agent wo

输出质量保障与验证。编辑后检查、提交前测试、session 指标测量。不适用于工具重试（用 tool-governance）或 agent 提前停止（用 execution-loop）。参见 tool-governance（错误追踪）。

Log corrections, errors, feature requests, and recurring patterns into structured workspace learning files, then promote stable patterns into tiered memory and OpenClaw workspace files (AGENTS.md, SOU

Post tasks for other AI agents to do, or pick up work from the AgentDo task queue (agentdo.dev). Use when: (1) you need something done that you can't do yourself (scraping, data collection, image conv

Local memory system with structured indexing and auto-learning. Auto-write, heuristic recall, auto learning when knowledge is insufficient. Compatible with self-improving-agent: auto-records skill com

Backup, clone, and migrate OpenClaw data across instances. Upload/download OpenClaw snapshots to local or cloud - https://clawclone.cc . Create shareable Agent configurations, sync between devices, an

Manage monday.com boards, items, columns, groups, updates, and workflows via MCP server (preferred) and GraphQL API (fallback). Use when a user asks to create tasks, update statuses, manage projects,

Orchestrate multi-agent teams with defined roles, task lifecycles, handoff protocols, and review workflows. Use when: (1) Setting up a team of 2+ agents with different specializations, (2) Defining ta

Mandatory adversarial review of all agent outputs. After drafting any response, a second AI instance (sub-agent) reviews and challenges the draft before delivery. Note: this sends draft text to the co

Use this skill for zCloak.ai workflows, including agent identity creation, AI Name (.ai/.agent) lookup and registration, owner binding with passkey/WebAuthn, on-chain signing and verification, documen

Configure OpenClaw multi-agent routing for Feishu multi-account setups. Use when users need two or more Feishu bots (different appId/appSecret) to run on isolated agents/workspaces with distinct syste

GitHub MCP Server for repository management, file operations, PR/issue tracking, branch management, and GitHub API integration. Enable AI agents to clone repos, read code, create/update files, manage

Visual AI browser automation via OpenBrowser Agent. Use when the user asks to "automate browser", "control Chrome", "browse website with AI", "use OpenBrowser", "run browser automation", or mentions w

Use when an agent needs to evaluate messy public claims before taking a bounded, costly, irreversible, or reputation-sensitive action. Produces an analysis-only action disposition from evidence, publi

A persistent autonomous engineering harness runtime that transforms any repository into a self-improving software system. Use this skill whenever the user wants to: build or run an autonomous coding a

Enables AI agents to work on long-running projects across multiple sessions. Use when starting complex projects, resuming work on existing projects, managing task lists with priorities and dependencie

Deploy Cursor AI agents to GitHub repos. Automatically write code, generate tests, create documentation, and open PRs using your existing Cursor subscription.

Use when the user asks to create, edit, read, or export Google Slides presentations. Triggers for requests involving slides, decks, presentations, speaker notes, slide images, markdown-to-slides, pres

Audit any OpenPersona (or peer LLM-agent) persona in three complementary modes: structural (CLI, deterministic, CI-friendly: 4 Layers × 5 Systemic Concepts × Constitution gate with role-aware severity

Backup, restore, disaster recovery, and migration for OpenClaw. Encrypts and stores ~/.openclaw/ locally and to cloud destinations (S3, R2, B2, GCS, Google Drive, rsync). Use when the user asks about

Search Airbnb listings, filter short-term rentals, and analyze detail pages for parking, basement, and renovation signals.

Multi-agent shared memory protocol. Syncs a shared GitHub repo containing USER.md (owner preferences/habits), KNOWLEDGE.md (common knowledge), RULES.md (universal agent rules), and TOOLS.md (shared to

Reliably resume work after `openclaw gateway restart` (or when you must restart the OpenClaw gateway mid-task). Uses durable one-shot cron `agentTurn` jobs (isolated session + explicit delivery) so th

Use this skill as the default XCrawl entry point for direct XCrawl requests, including single-URL fetch, format selection, sync or async execution, and JSON extraction with prompt or json_schema.

Structures collaboration: picks the counterpart, runs a bounded exchange on a plan or decision, lands a decision or a recorded disagreement. Use when a plan needs critique, red-teaming, or a devil's a

Guide for using the Claw4Claw(虾连虾) CLI tool to interact with the AI Agent collaboration platform. Invoke when users need help with agent registration, task management, service publishing, market explo

Build a cost-efficient LLM evaluation ensemble with sampling, tiebreakers, and deterministic validators. Learned from 600+ production runs judging local Ollama models.

Use when conducting research on the human-free platform from a published idea. Each run pulls ONE unresearched idea over MCP — bundled with its backing problems, methods, and their literature — survey

AI Trading Assistant for quantumstocks.ru. Automated hedge fund with market analysis, risk management, and trade execution via n8n MCP. Use when analyzing markets, managing positions, risk checks, new

Find, hire, and serve specialist AI agents on the AgentBnB network from OpenClaw or Claude Code. Use when you need multi-agent delegation, provider discovery, remote skill execution, or want to publis

READ this skill when designing or planning any game system architecture — including combat, skills, AI, UI, multiplayer, narrative, or scene systems. Contains paradigm selection guides (DDD / Data-Dri

Install and run Aperture, the L402 Lightning reverse proxy from Lightning Labs. Use when creating L402 paywalls, configuring paid API endpoints, hosting paid content for other agents, or testing L402

短剧/漫剧分镜提示词流水线：把剧本片段或分镜表批量转成首帧图提示词与图生视频提示词 （I2V 首帧驱动 / FL2V 首尾帧），适配即梦、可灵、海螺 H3、Seedance、Vidu、Runway 六类模型方言，内置角色一致性锚点、竖屏 9:16 镜头语言与 CSV/JSON 批量导出。 Use when the user wants to batch-generate storyboard im

Refines ambiguous or high-risk user requests before execution. Trigger when the request is underspecified, likely to benefit from clearer constraints or verification, or when the user explicitly asks

Control the host machine's Chrome browser to open specific URLs in new tabs. Use when: User explicitly asks to "open a link", "show me this page", or "search for X in browser" on the host machine. NOT

Two-agent iterative vibe-coding loop for OpenClaw. Use when the user wants one sub-agent to generate/build/code an app or artifact and a second analyst agent to inspect the code, visually preview the

Manage AI agent personas (Souls) for OpenClaw, Hermes Agent, ZeroClaw, and other agents that use Soul Spec workspace files (SOUL.md, IDENTITY.md, AGENTS.md). Installs/switches/restores persona files i

Operate and maintain the persistent MUD agent for OpenClaw. Use when running MUD engine commands, smoke-testing mud state behavior, validating save/restore, diagnosing MUD data issues, or handling MUD

Coordinate multi-agent swarm execution with a lightweight Pub/Sub protocol, standardized SwarmCommand messages, token-budget control, agent status tracking, negotiation, fallback, and completion gates

Live markdown viewer for AI pair-editing. When you collaborate, the updates render instantly. Works with any AI agent and web browser.

Search, read, and manage Canva design work through Canva's hosted MCP server. Thin pass-through to Canva's official MCP; the live tool catalog is whatever that server advertises. Use when the user ask

Activate when: user says 'we need to pick up speed', 'why aren't we getting traction', 'when should we scale / raise / launch', 'our efforts feel scattered', or 'are we ready to grow'; entering a new

Cross-platform IM messaging CLI for DingTalk, Feishu (Lark) enterprise apps and WeCom (WeChat Work) group robot webhooks. Send P2P / group messages with text, Markdown, images, files, @mentions, recal

Browse and search the AgentAPI directory - a curated database of APIs designed for AI agents. Find MCP-compatible APIs for search, AI, communication, databases, payments, and more. Includes x402 pay-p

Shell aliases and helper commands for Freqtrade (cryptocurrency trading bot) that speed up common tasks. Use when setting up Freqtrade shortcuts, downloading market data quickly, running backtests fro

Validate a business idea before investing time or money. Use whenever a solopreneur has a raw idea and needs a structured process to stress-test it against reality — covering problem definition, deman