Skill reviews

Configure agy-auto PreToolUse security gate to run Antigravity CLI (agy) unattended with layered policy controls instead of --dangerously-skip-permissions.

• 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

Certify a deployed service with fresh evidence across source, CI, migrations, runtime health, readiness, and critical routes; use before declaring a release production-ready.

• 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

Audit multi-role marketplace authorization across roles, resource ownership, tenant boundaries, and order-state transitions; use when access rules need evidence, not UI assumptions

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

Search, inspect, and run third-party data APIs through one CLI when the environment has no suitable integration.

• 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

Fetch YouTube video transcripts, search videos/channels, browse channels, and extract playlists via the getyoutubetranscript.com API - free tier, no card required.

• 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

Story Creation and Translation AI Agent with Studio Chat, CLI, and TUI - use for long-form novels, short fiction, scripts, storyboards, interactive-film projects, open-world / bran

• 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 response is described with custom markup (14 tags): a typed call is more reliable

Writes, fixes, and converts Markdown that renders the same in every parser — GitHub, MDX, Pandoc, docs sites, Slack, Notion. Use when a list stops nesting, a table renders as liter

• 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

Security-first behavioral guidelines for cautious agent operation. Use this skill for ALL operations involving external resources, installations, credentials, or actions with exter

• 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

Become an autonomous prediction market trader on Polymarket with AI-powered analysis and a performance-backed token on Base. Trade real markets, build a track record, and let the b

• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• 20 top-level sections: this looks like several domains in one skill
• No condition that starts the skill

Control Tesla vehicles from macOS via the Tesla Owner API using teslapy (auth, list cars, status, lock/unlock, climate, charging, location, and extras). Use when you want to check

• 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 comprehensive JavaScript style guide skill. When activated, it provides best-practice JavaScript coding conventions and generates code that strictly follows the style guide, cove

• 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

Email deliverability, list management, sequences, segmentation, and campaign optimization.

• 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

OneDrive API integration with managed OAuth via Microsoft Graph. Manage files, folders, and sharing. Use this skill when users want to upload, download, organize, or share files in

• 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

Microsoft Excel API integration with managed OAuth. Read and write Excel workbooks, worksheets, ranges, tables, and charts stored in OneDrive. Use this skill when users want to rea

• 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

Google Search Console API integration with managed OAuth. Query search analytics, manage sitemaps, and monitor site performance. Use this skill when users want to access Search Con

• 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

Telegram Bot API integration with managed authentication. Send messages, manage chats, handle updates, and interact with users through your Telegram bot. Use this skill when users

• 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

Build reliable, fast E2E test suites with Playwright and Cypress. Critical user journey coverage, flaky test elimination, CI/CD integration.

• 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

Safe command execution for OpenClaw Agents with automatic danger pattern detection, risk assessment, user approval workflow, and audit logging. Use when agents need to execute shel

• 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
• Does not say what the result is

Control Tuya smart home devices via natural language. Use when the user asks to control smart devices (turn on/off lights, AC, plugs, adjust brightness/temperature/mode), query dev

• 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 (5 tags): a typed call is more reliable
• Does not say what the process needs to start

Board meeting preparation, investor updates, and executive communication. Use when preparing board decks, writing investor updates, handling bad news with the board, structuring QB

• 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

Comprehensive AI prompt engineering safety review and improvement prompt. Analyzes prompts for safety, bias, security vulnerabilities, and effectiveness while providing detailed im

• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• No condition that starts the skill
• Linear process with no failure handling

Review the implementation source code of MCP (Model Context Protocol) servers, clients, and tool handlers against a security baseline — authentication, sessions, rate limiting, inp

• 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

Generate tailored AI agent instruction files via AgentRC instructions command. Produces .github/copilot-instructions.md (default, recommended for Copilot in VS Code) plus optional

• 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 (7 tags): a typed call is more reliable
• Does not say what the process needs to start

Build, scaffold, and deploy Power Automate cloud flows using the FlowStudio MCP server. Your agent constructs flow definitions, wires connections, deploys, and tests — all via MCP

• 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

Debug failing Power Automate cloud flows using the FlowStudio MCP server. The Graph API only shows top-level status codes. This skill gives your agent action-level inputs and outpu

• 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
• Does not say what the result is