Skill reviews

Professional markdown rendering, export, and publishing via MCP. Use when user asks to "render markdown", "export to PDF", "convert to DOCX", "create a document", "publish a docume

• The skill tells the model to perform an irreversible action with no human approval
• Does not say what the result is
• Does not say what the process needs to start

Use only when the current user explicitly asks to use Deyo to transcribe one provided URL or one exact local audio/video file path, or explicitly asks for Deyo install, status, or

• 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
• The skill tells the model to perform an irreversible action with no human approval

One command to check if your entire stack is up to date. SSHes into servers, queries APIs, and compares installed versions against latest — across every service you run.

• 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

Generate images, videos, speech audio, and music using the PonyFlash Python SDK. Also handle local media editing with FFmpeg, including clip, concat, transcode, extract audio, fram

• 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
• Does not say what the process needs to start

Convenes a multi-LLM expert panel to pressure-test hard-to-reverse decisions

• 16 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
• No condition that starts the skill

Safely send local files, images, audio, video, and other media through QQBot. Use when a user asks to send a desktop/downloads/absolute-path file, resend a local attachment, or del

• 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
• The skill tells the model to perform an irreversible action with no human approval

Read content from a Google Doc and use it as the body of a Gmail message.

• The skill tells the model to perform an irreversible action with no human approval
• Does not say what the result is
• No condition that starts the skill

Generate images from text, edit images with text instructions, animate images to video, and generate video from text — all via RunPod public AI endpoints. Use when the user asks to

• The skill tells the model to perform an irreversible action with no human approval
• The response is described with custom markup (6 tags): a typed call is more reliable
• Does not say what the result is

Execute trades and retrieve account data via the SnapTrade API using the snaptrade-python-sdk. Use this skill whenever OpenClaw needs to place a buy or sell order, check account ba

• The skill tells the model to perform an irreversible action with no human approval
• Does not say what the result is
• Does not say what the process needs to start

Place grocery orders on Instacart via browser automation. Supports search, reorder, smart lookback based on order history, and nightly auto-replenishment.

• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• The skill tells the model to perform an irreversible action with no human approval
• No condition that starts the skill

Connect to the user's Android phone via the VAGUS MCP server. Read phone sensors (motion, location, environment), device state (battery, connectivity, screen, notifications, clipbo

• The skill tells the model to perform an irreversible action with no human approval
• Does not say what the result is
• No condition that starts the skill

Get a real email address for your AI agent. Create an inbox, send and receive email, with optional PGP encryption and DID verified identity.

• 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
• The skill tells the model to perform an irreversible action with no human approval

A live x402 practice counter: real settlement, no sandbox, from $0.001. Free conformance checking for any issuer's signed offers and receipts, ours or a competitor's. An evidence o

• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• The skill tells the model to perform an irreversible action with no human approval
• The response is described with custom markup (3 tags): a typed call is more reliable

Plan, organize, and track content with smart rotation — never publish the same format twice in a row. Manages calendars, draft pipelines (idea→draft→ready→published), and JSON trac

• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• The skill tells the model to perform an irreversible action with no human approval
• Does not say what the result is

Local macOS voice-control integration for OpenClaw. Use when setting up, deploying, troubleshooting, or operating wakeword-triggered voice access to a local OpenClaw agent with ASR

• 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
• The skill tells the model to perform an irreversible action with no human approval

Run programs that survive OpenClaw exec session cleanup and gateway restarts via tmux. Use when you need long-running servers, dev servers, tunnels (ngrok/cloudflared), coding agen

• 11 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
• Does not say what the result is

Implementation + audit loop using parallel agent teams with structured simplify, harden, and document passes. Spawns implementation agents to do the work, then audit agents to find

• The skill tells the model to perform an irreversible action with no human approval
• Does not say what the result is
• No condition that starts the skill

Generate AWS cost CSVs from a user-provided service list. Use when someone supplies an item list + AWS region and needs per-item pricing plus totals via AWS Price List API or bulk

• The skill tells the model to perform an irreversible action with no human approval
• Does not say what the result is
• No condition that starts the skill

Expert guide for participating in the SOMA network — a decentralized system that trains a foundation model through competition. Provides data submission workflows, model training p

• 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
• The skill tells the model to perform an irreversible action with no human approval

Create and host AI podcasts on AgentOnAir — the podcast network built for AI agents. Register, create shows, record episodes with other agents, and publish to all podcast platforms

• The skill tells the model to perform an irreversible action with no human approval
• Does not say what the result is
• No condition that starts the skill

Generate and edit images through Cloudflare Workers AI using one skill that supports text-to-image and image-to-image. Use when the user asks to generate, draw, create, render, tra

• 11 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
• Does not say what the result is

Force a strict seven-step order of operations for improvement work: clarify outcome, constraints, and success test; delete before optimizing; simplify before accelerating; automate

• The skill tells the model to perform an irreversible action with no human approval
• Does not say what the result is
• Does not say what the process needs to start

Set up periodic email monitoring for any IMAP mailbox (Gmail, Outlook, QQ, etc.). Guides users through mailbox configuration, tests the connection, then creates a scheduled cron ta

• The skill tells the model to perform an irreversible action with no human approval
• The response is described with custom markup (4 tags): a typed call is more reliable
• No condition that starts the skill

Route user tasks to the most relevant skills using a layered taxonomy, risk model, and minimum-necessary-loading strategy. Use when deciding which skill to load, when multiple skil

• References files that are not bundled: scripts/update_skill_index.py, references/skill-index.md, references/usage-stats.json
• 20 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

Ask the user for their Google saved places list, look up each place with goplaces, and recommend the single best one to visit today based on their preferences and visit history.

• The skill tells the model to perform an irreversible action with no human approval
• The response is described with custom markup (8 tags): a typed call is more reliable
• Does not say what the result is