Skill reviews

Use this skill when a task needs browser automation through PinchTab: open a website, inspect interactive elements, click through flows, fill out forms, scrape page text, reuse a d

• 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 response is described with custom markup (15 tags): a typed call is more reliable

Calendar Management - secure Google Calendar, Microsoft Outlook & Exchange. Use when the user wants to list, search, or read calendar events; creating, updating, deleting, or respo

• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• The response is described with custom markup (6 tags): a typed call is more reliable
• Does not say what the result is

AI Agent Skill for GitHub project analysis and nad.fun token launch. Analyzes repos, generates token identity/promo, and launches on nad.fun.

• 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 result is

Control SwitchBot smart home devices (curtains, plugs, lights, locks, etc.) via SwitchBot Cloud API. Use when user asks to open/close curtains, turn on/off lights/plugs, check temp

• 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

Writes, debugs, and validates YAML that parses the same in every language and tool. Use when a file will not parse, when a value silently turns into a boolean, number, date or null

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

Guide CS learning from first programs to research and industry practice.

• 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

Troubleshoot and secure wireless networks with channel optimization and diagnostics.

• 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

Flashcard-based English vocabulary learning with SQLite + SRS. Works with any chat platform when paired with an OpenClaw agent prompt.

• 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

Microsoft Teams API integration with managed OAuth. Manage teams, channels, messages, and meetings via Microsoft Graph API. Use this skill when users want to list teams, create cha

• References files that are not bundled: references/<source>/triggers.md, references/{source}/triggers.md
• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• 14 top-level sections: this looks like several domains in one skill

Secure computer-to-computer networking for AI agents — gossip broadcast, direct messaging, CRDTs, group encryption. Post-quantum encrypted, NAT-traversing. Everything you need to b

• References files that are not bundled: scripts/install.py
• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• 14 top-level sections: this looks like several domains in one skill

Secure crypto wallet for AI agents. Hardware-isolated keys (Apple Secure Enclave), ERC-4337 smart wallet, on-chain spending caps, default-deny policy engine.

• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• The response is described with custom markup (4 tags): a typed call is more reliable
• Does not say what the result is

• 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

Expert SurrealDB 3 architect and developer skill (tracks v3.1.4+). SurrealQL mastery, multi-model data modeling (document, graph, vector, time-series, geospatial), schema design, s

• References files that are not bundled: {baseDir}/AGENTS.md
• 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

Use when you need your agent to see the world through your LENS. This skill evolves through the Trinity Nodes to ensure every interaction is an authentic reflection of who you are

• 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

Use this skill when an agent needs to create crypto wallets, send transactions, swap tokens, check balances, or perform any on-chain operation across 36+ blockchains using threshol

• 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

AI-native ERP system. Full accounting, invoicing, inventory, purchasing, tax, billing, HR, payroll, advanced accounting (ASC 606/842, intercompany, consolidation), and financial re

• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• The response is described with custom markup (9 tags): a typed call is more reliable
• Does not say what the result is

Macro-gated US stock analysis combining technical indicators, fundamentals, and macro environment with weighted scoring and Buy/Hold/Sell verdicts.

• 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

Short-form video for AI agents. Generate videos using the latest models, pay with USDC via x402.

• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• No condition that starts the skill
• Instruction body is 16062 tokens: crowds the task out of the window

Schedule meetings, check availability, and manage calendars across Google, Outlook, and CalDAV. Routes to focused sub-skills for datetime resolution and calendar scheduling. Also a

• 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

Builds, debugs, and hardens Django apps: models, the ORM, views, templates, forms, the admin, DRF APIs, and deployment. Use when a page fires one query per row (N+1, select_related

• 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 process needs to start

AI Face Swap - Swap face in video using verging.ai API. Supports local video files, YouTube/Bilibili URLs, local and remote face images. Auto-download, trimming, real-time progress

• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• The response is described with custom markup (3 tags): a typed call is more reliable
• Does not say what the result is

Play on-chain odd/even games on Solana devnet via Clawland. Mint GEM from SOL or USDC, bet odd or even, win 2x. Scripts handle wallet setup, minting, and autoplay.

• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• The response is described with custom markup (4 tags): a typed call is more reliable
• Does not say what the result is

Toolbelt is a collaborative substrate over your data. Upload any document — entities and relationships extracted automatically, queryable immediately. Ask questions that span struc

• 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 process needs to start

Runs web and application services on a host: process supervision, ports and sockets, worker sizing, restarting without dropping requests. Use when a service will not start, dies af

• 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
• Does not say what the process needs to start

PDF.co API integration with managed OAuth. Convert, merge, split, edit PDFs and extract data. Use this skill when users want to convert PDFs to/from other formats, merge or split P

• References files that are not bundled: references/<source>/triggers.md, references/{source}/triggers.md
• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• 14 top-level sections: this looks like several domains in one skill