Skill reviews

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

• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• Does not say what the result is
• No condition that starts the skill

Coordinate multi-agent tasks with visible group updates. Use when delegating work across multiple topic agents and the user needs transparent progress in-group (start update, mid-p

• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• No condition that starts the skill
• Does not say what the process needs to start

Collaborative pixel art canvas for AI agents. Register, request pixel assignments, coordinate in block threads, and place colors. Use when an agent wants to create pixel art, join

• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• 18 top-level sections: this looks like several domains in one skill
• Does not say what the result is

Send and receive emails and phone calls via Inkbox agent identities. Use when the user wants to check inbox messages, list unread email, view a thread, search mailbox contents, dra

• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• 13 top-level sections: this looks like several domains in one skill
• The response is described with custom markup (3 tags): a typed call is more reliable

Claw-to-claw mentorship — receive expert configuration updates AND operational wisdom from mentors who've been where you're going. Your agent grows technically and relationally thr

• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• 12 top-level sections: this looks like several domains in one skill
• Does not say what the result is

Create a relationship-aware gift for the user and render it as an expressive H5, generated image, generated video, text-first artifact, or bounded live text play. Use when OpenClaw

• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• 10 top-level sections: this looks like several domains in one skill
• Does not say what the process needs to start

苏宁帮客预约服务

• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• Does not say what the result is
• No condition that starts the skill

A persistent local-only memory system for AI coding agents. Two files, one idea — AGENTS.md (committed, shared) + .agents.local.md (gitignored, personal). Agents read both at sessi

• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• 15 top-level sections: this looks like several domains in one skill
• Does not say what the result is

Enables AI agents to interact with AISP (Agent Inference Sharing Protocol) for renting or providing DIEM API capacity. Use when working with diem-marketplace, Venice API keys, USDC

• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• Does not say what the result is
• Does not say what the process needs to start

Framework-agnostic agent-to-agent payment system with SHIB on Polygon. Provides trustless escrow, price negotiation, and reputation system. 9,416x cheaper than traditional escrow (

• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• 15 top-level sections: this looks like several domains in one skill
• Does not say what the result is

Real-time Chinese web search powered by 360's search engine API. Use this skill when the user asks to search the web, look up recent news, find current information, or query anythi

• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• Does not say what the process needs to start
• Says nothing while it works

Discover, compare, review, install, or update OpenClaw skills from trusted sources with a review-first workflow. Use when the user wants to search for a skill, compare multiple can

• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• Does not say what the result is
• Does not say what the process needs to start

Route mid-session work to the right spawned model without changing the fixed main session. Use for coding, architecture, math, algorithms, web development, brainstorming, research,

• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• Does not say what the result is
• Does not say what the process needs to start

Interact with Bitget Wallet API for crypto market data, token info, swap quotes, and security audits. Use when the user asks about token prices, market data, swap/trading quotes, t

• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• Does not say what the result is
• Does not say what the process needs to start

• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• No condition that starts the skill
• Says nothing while it works

Build and operate autonomous AI agents that compete in Aureus Arena, a fully on-chain Colonel Blotto game on Solana. Use when the user asks about Aureus, Colonel Blotto strategies,

• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• 18 top-level sections: this looks like several domains in one skill
• Does not say what the result is

Plan and manage parcel shipping decisions with carrier selection, landed-cost math, customs checks, and delivery exception playbooks.

• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• Does not say what the result is
• No condition that starts the skill

Adaptive-language stock-analysis skill that interprets macro and political news, fuses it with retail/social sentiment, applies quantified value fallback rules, and outputs machine

• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• 16 top-level sections: this looks like several domains in one skill
• 1 mutating operations with no state check

Apply modern web development best practices for security, compatibility, code quality, and coding standards. Covers KISS/DRY/YAGNI principles, TypeScript/JavaScript standards, Reac

• References files that are not bundled: ../web-quality-audit/SKILL.md
• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• 16 top-level sections: this looks like several domains in one skill

Web3 development using MetaMask Smart Accounts Kit. Use when the user wants to build dApps with ERC-4337 smart accounts, send user operations, batch transactions, configure signers

• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• 15 top-level sections: this looks like several domains in one skill
• Does not say what the result is

Local, offline AI-powered file type detection — no network, no API keys

• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• No condition that starts the skill
• Does not say what the process needs to start

Single source of truth for all paths, naming conventions, and data formats across the OpenClaw Greek Accounting system. Reference document.

• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• 27 top-level sections: this looks like several domains in one skill
• Does not say what the result is

Intercept and filter communications from difficult contacts. Strips emotion, extracts facts, drafts neutral responses. Use when setting up communication filtering for specific cont

• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• Does not say what the result is
• Does not say what the process needs to start

Swap tokens on Ethereum via the AIDEX aggregator. Search tokens, check exchange rates, view balances, and execute swaps. Client-side transaction signing keeps your private key on y

• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• 11 top-level sections: this looks like several domains in one skill
• Does not say what the result is

Autonomous ClawArena client that stores scoped credentials and delivery state, runs a background watcher on a selected existing OpenClaw agent, and reports heartbeat/update telemet

• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• 13 top-level sections: this looks like several domains in one skill
• The skill tells the model to perform an irreversible action with no human approval