Skill reviews

Use when an object has two or more parts, or when a connectivity or joint_sweep finding fired: how parts must touch without penetrating. For static_object and articulated_object in

• 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

Build or publish nemo-switchyard Python distributions through the repository's GitHub Actions workflow. Use when asked to build a development wheel, cut a Python release, publish t

• 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

Review Switchyard Rust changes for correctness and maintainability. Use for pull requests or diffs touching crates, PyO3 bindings, async runtime behavior, streaming, protocol types

• 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

Publish images, videos, Reels or carousels to your Instagram professional account via the Instagram Content Publishing API, and read your own recent media. Use when the user wants

• 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

Publish posts to your Blogger blog and read your blogs / posts via the Blogger API v3. Use when the user mentions Blogger, blogspot, publishing a post to their blog, listing their

• 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

Publish text, image, video or carousel posts to your Threads (@threads) account via the official Threads API, and read your own recent posts. Use when the user wants to post to Thr

• 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
• Does not say what the result is

Add a supplied layout image and bilingual layout prompt to the local handdraw-style layout library and gallery. Use for new SC-* social-card or IG-* infographic layouts; do not use

• References files that are not bundled: references/layouts.json, references/layouts/{ID}.md
• The skill tells the model to perform an irreversible action with no human approval
• 2 referenced file(s) missing: references/layouts.json, references/layouts/{ID}.md

Control the user's phone - an iPhone through the Mac's iPhone Mirroring window, an Android over adb, a rented cloud Android, or a cloud iPhone over HTTPS: open apps, tap, type, swi

• 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

Production-tested setup for Tailwind CSS v4 with shadcn/ui, Vite, and React. Use when: initializing React projects with Tailwind v4, setting up shadcn/ui, implementing dark mode,

• 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
• Does not say what the result is

Research TikTok videos, profiles, hashtags, comments and followers with engagement statistics through the harshmaur/tiktok-scraper Apify Actor. No TikTok login.

• The skill tells the model to perform an irreversible action with no human approval
• Does not say what the result is
• 9 mutating operations with no state check

Publish an HTML file or static folder to a permanent public https://<slug>.deed.page/ URL with one curl request. No account; the first publish returns a token for updates.

• 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

Methodological guide for the AI Agent to safely and systematically translate, refactor, and modernize giant legacy codebases (PHP, Python 2, old React) into modern stacks.

• 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 any time a .pptx or .potx file is involved in any way — as input, output, or both. This includes: creating slide decks, pitch decks, or presentations; reading, parsi

• 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

Design and build an official Apify integration for a company's product - workflow-automation apps (Zapier/n8n-style), AI agent plugins (coding-agent skills+MCP bundles or OpenClaw/

• 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

When a slides deck needs images, delegate to the Assets app over A2A so generations are grounded in the user's brand library — never call an image-generation API directly from slid

• 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

Source and generate images for slides with Assets-owned style grounding and provenance. Use when a slide needs a new still image, logo, or approved image asset.

• References files that are not bundled: url
• The skill tells the model to perform an irreversible action with no human approval
• 1 referenced file(s) missing: url

Build a fast, good-looking page: a data dashboard, or any page made with show_html (a landing page, a pricing page, a tool), in this chat or at a public link with publish_page. Use

• 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

Create or revise .univer.html pages connected to live Workspace Sheet data using HTML binding attributes and JavaScript. Validate and publish them with univer_html_view.

• The skill tells the model to perform an irreversible action with no human approval
• The response is described with custom markup (12 tags): a typed call is more reliable
• Does not say what the result is

Create, inspect, edit, import, export, and hand off remote Univer Workspace documents (Units) through DSH tools and isolated worktrees. Use proactively for any task involving Works

• 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
• Does not say what the result is

Upload, inspect, download and replace original files in remote Workspace with uvw, including ETag conflicts and recovery after uncertain writes. Use for Blob Resources rather than

• References files that are not bundled: ../core/SKILL.md
• The skill tells the model to perform an irreversible action with no human approval
• 1 referenced file(s) missing: ../core/SKILL.md

Refactor cleanly instead of layering sediment. Use for rename requests, stale or misleading names, legacy leftovers, changed scope, or when a change reveals duplicated concepts, lo

• 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

Audit or rewrite AGENTS.md so it holds only lasting principles. Run it only when the user asks for it by name; never invoke it on your own.

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

Create or revise agent skills. Use when adding a new skill file, renaming a skill, simplifying an existing skill, improving trigger descriptions, or deciding what belongs in a skil

• 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
• No condition that starts the skill

Review changed code for naming, stale references, unnecessary complexity, and comment quality. Use after completing implementation work, before committing, or when the user asks to

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

Write tests that pin real behavior instead of implementation details, config values, or lucky samples. Use when adding tests for new behavior, writing a regression test, fixing a b

• References files that are not bundled: ../audit-tests/SKILL.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