Skill reviews

Design and create a new hive task through guided conversation. Walks the user through problem definition, eval design, constraint specification, repo scaffolding, baseline testing

• 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
• No condition that starts the skill

Use when the user wants to use the UCP CLI to find, compare, buy, or track products from online merchants, or to set up and troubleshoot the local UCP profile required for merchant

• 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
• The response is described with custom markup (16 tags): a typed call is more reliable

Google Tasks: Manage task lists and tasks.

• 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

Walk through a live web app AS a real user to find usability + behavioural bugs that static reviews miss. REQUIRES proof of interaction (typing, clicking, sending, observing) befor

• 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
• The response is described with custom markup (7 tags): a typed call is more reliable

Use for Drizzle migrations: schema/table/column changes, migration generation or regeneration, sequence conflicts after rebase, idempotent SQL review, or migration renames.

• 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 when user wants their Claude Code pet (/buddy) to sing a song. Triggers on any request that combines the concept of their Claude Code buddy, pet, or companion with singing or m

• 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

Use this skill when the user wants to 'login/log in/sign in', 'authenticate', 'authorize', 'connect OKX account', 'set up credentials', 'first time setup', 'configure okx', '登录', '

• 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
• The response is described with custom markup (4 tags): a typed call is more reliable

This is the main on-chain DeFi skill. Use it for ALL of the following: Strategy discovery: 'how to make money on-chain', 'any profitable strategies', '链上有什么赚钱机会', '有什么盈利机会', '有什么套利

• 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

Browserless API for headless Chrome. Use when user mentions "headless Chrome", "browserless", or needs browser automation.

• 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

• 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

Write Metal/MPS kernels for PyTorch operators. Use when adding MPS device support to operators, implementing Metal shaders, or porting CUDA kernels to Apple Silicon. Covers native_

• 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

Generate, edit, and manage PowerPoint presentations via the SlideSpeak API. Use this skill when users want to create presentations from text or documents, edit existing presentatio

• 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

Guide for testing code changes in AEM Edge Delivery projects including blocks, scripts, and styles. Use this skill after making code changes and before opening a pull request to va

• 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

Instagram API for posts and media. Use when user mentions "Instagram", "instagram.com", shares an IG link, "Instagram post", or asks about social media content.

• 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
• Does not say what the result is

Run a Cyrus release by publishing all packages to npm in the correct dependency order, updating changelogs, and creating git tags.

• 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

Guidelines for upgrading Expo SDK versions and fixing dependency issues

• 14 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

This skill should be used when searching, fetching, or downloading emails from Gmail. Use for queries like "search Gmail for...", "find emails from John", "show unread emails", "em

• The skill tells the model to perform an irreversible action with no human approval
• No condition that starts the skill
• Linear process with no failure handling

Run an Anthropic Claude Managed Agent — a cloud agent harness (container + filesystem + tools), the cloud counterpart of the local wasm-agent runtime

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

Create, show, and guide with ScreenCI videos in an already-initialized project by editing `.screenci.ts` files and running the Screenci workflow.

• 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

Vitest testing guide. Use when writing or updating tests, fixing failing tests, improving coverage, debugging test issues, or setting up mocks.

• 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

Send images and screenshots via Feishu (Lark) messaging platform. Use when the user asks to send screenshots, images, or any visual content through Feishu. This skill handles the c

• 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

Turn the current conversation context into a PRD and publish it to the project issue tracker. Use when user wants to create a PRD from the current context.

• 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
• Does not say what the result is

Manage stacked branches and pull requests with the gh-stack GitHub CLI extension. Use when the user wants to create, push, rebase, sync, navigate, or view stacks of dependent PRs.

• 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

Always use when user asks to create, generate, draw, or design a diagram, flowchart, architecture diagram, ER diagram, sequence diagram, class diagram, network diagram, mockup, wir

• 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
• No condition that starts the skill

Land a PR by monitoring conflicts, resolving them, waiting for checks, and squash-merging when green; use when asked to land, merge, or shepherd a PR to completion.

• 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