Skill reviews

Domain expert learning system with persistent local knowledge base. READ THIS SKILL FILE at the start of every session — learned topics are stored locally and should be used to ans

• References files that are not bundled: part-001.md, part-002.md, ../../raw/web/{hash}.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

Connect to 100+ APIs (Google Workspace, Microsoft 365, GitHub, Notion, Slack, Airtable, HubSpot, etc.) with managed OAuth. Use this skill when users want to interact with external

• References files that are not bundled: references/, references/active-campaign/README.md, references/acuity-scheduling/README.md
• 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

Connect to 100+ APIs (Google Workspace, Microsoft 365, GitHub, Notion, Slack, Airtable, HubSpot, etc.) with managed OAuth. Use this skill when users want to interact with external

• References files that are not bundled: references/linkedin/README.md, references/mailchimp/README.md, references/mailerlite/README.md
• 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

Git for your prompts. Track every change, diff versions, rollback mistakes, never lose a good prompt again. All local, zero dependencies, works offline.

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

Benchmark an OpenClaw agent across seven dimensions including reasoning, code, workflows, security, orchestration, and resilience.

• 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

Use this skill when the user asks to merge a PR, check if a PR is ready to merge, "merge PR", "can this PR be merged", "merge-pr-check". Requires Gitee MCP Server to be configured.

• The skill tells the model to perform an irreversible action with no human approval
• Does not say what the result is
• Says nothing while it works

QuantConnect automated backtest pipeline — submit local strategies, compile, execute, monitor with early-stop, and download results in one command.

• 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

Execute liquid staking operations on Bifrost SLPx protocol across Ethereum, Base, Optimism, and Arbitrum. Mint vETH by staking ETH/WETH, redeem vETH back to ETH, and claim after re

• 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

Deploy and manage 3X-UI on a root-managed Ubuntu or Debian VPS using Docker Compose, nginx, ACME certificates, SSH panel tunneling, UFW hardening, and Xray VLESS over XHTTP behind

• 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 (5 tags): a typed call is more reliable

Send local files and documents to a Telegram user via bot. Use when user asks to "send", "发", "发给我", "发送" a file, note, or document via Telegram. Handles files from iCloud Drive pa

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

Merge overlapping local skills into one canonical skill and republish the canonical skill to ClawHub. Use when two local skills have overlapping responsibilities, when a temporary

• 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 process needs to start

Enterprise-grade persistent memory for AI agents — rollback, audit trails, knowledge graph, governed actions, time-travel debugging, and 60+ commands covering 100% of Novyx Core

• The skill tells the model to perform an irreversible action with no human approval
• The response is described with custom markup (26 tags): a typed call is more reliable
• Does not say what the result is

Download videos from Instagram Reels, TikTok, YouTube Shorts, Twitter/X clips, and other social media platforms. Use when the user clearly wants to download/save/grab a video from

• 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

Analyze Apple Health exports (export.zip or the exported folder) using xmlstarlet/jq to summarize activity, steps, sleep, and source counts. Trigger this skill when users ask about

• 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 (8 tags): a typed call is more reliable

USE WHEN user wants to audit a GitHub repository or local directory for malicious code, backdoors, suspicious behavior, or supply-chain risk before trusting or installing it. Perfo

• 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 (7 tags): a typed call is more reliable

Deslop, humanize, edit, or audit AI-sounding, robotic, generic, corporate, or ChatGPT-like copy while preserving the writer's voice.

• The skill tells the model to perform an irreversible action with no human approval
• Does not say what the process needs to start
• Says nothing while it works

Alibaba Cloud Bailian Knowledge Base Retrieval Tool. Use HTTPS API to query and retrieve knowledge base content. Use when: User needs to query knowledge base, retrieve document con

• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• The skill ranks results itself: that belongs to the system behind the tool, not the model
• The skill tells the model to perform an irreversible action with no human approval

Create, edit, improve, or audit AgentSkills. Use when creating a new skill from scratch or when asked to improve, review, audit, tidy up, or clean up an existing skill or SKILL.md

• References files that are not bundled: FORMS.md, REFERENCE.md, EXAMPLES.md
• 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

Run a self-contained Chinese and international AI news workflow inside the current workspace. Use when the user wants either high-frequency RSS capture only or scheduled report 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

Generate a deep, code-first project wiki and VitePress documentation site (DeepWiki-style) for a repository. Use when asked to create a complete wiki/manual for a new codebase, bui

• 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

Track and report OpenClaw context window usage with a detailed breakdown of what's consuming tokens. Use when: user asks about context usage, token usage, "how much context am I us

• The skill tells the model to perform an irreversible action with no human approval
• Does not say what the process needs to start
• Says nothing while it works

Interact with the AIOZ Stream API to manage videos, audio, playlists, players, webhooks, analytics, payments, chapters, and transcripts on the AIOZ decentralized streaming platform

• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• 17 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

Manage tasks, CRM leads, contacts, and settings via the DashTask REST API

• 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

Search the web using Gemini with Google Search grounding through a local script, with model routing and quota fallback across Gemini Flash-Lite / Flash variants. Use when web resea

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

Place McDonald's China delivery orders through the official MCP server at https://mcp.mcd.cn using a Bearer MCP token over Streamable HTTP / JSON-RPC. Use when the user wants to br

• 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