熱門 Agent Skills

Split manuscript text into citable segments, search only accepted flagship and subjournal titles from Nature Portfolio, AAAS Science family, and Cell Press, filter by publication time range, and export one reference-manager-ready output.

Make videos as web pages with OpenFilm.

Apply during planned rewrites and migrations with explicit phase boundaries.

Write tests using React Native Testing Library (RNTL) v13 and v14 (`@testing-library/react-native`).

Add end-to-end and API tests for features that already work, following the project''s existing test harness.

Generate a pre-earnings briefing for any stock using Yahoo Finance data.

Primary/default skill for UI design, product design, web design, landing pages, dashboards, product screens, redesigns, visual polish, frontend/CSS styling, design systems, components, responsive design, typography, color, spacing, motion, icons, accessibility, copywriting, conversion, and anti-AI-slop work.

Routes any game-development request to the right specialized skill(s): it detects the engine (Godot, Unity, Unreal, Bevy, Phaser, PixiJS, three.js, LÖVE, pygame, Roblox) and the task, then reads the chosen skill before acting.

Business analyst for market research, competitive analysis, and requirements.

Define and use segments — named, saved filters over a Cargo model that become the audience for a batch run, a play trigger, or an export.

Perform code reviews following Sentry engineering practices.

Calculate ETF premium/discount vs NAV via Yahoo Finance, and decompose single-day surges into NAV-driven vs structural components (gamma squeeze, dealer hedging, blocked AP arbitrage).

Convert a local file (PDF, DOCX, XLSX, HTML, …) to markdown, or answer questions about its content.

WeCom meeting management skill for creating, querying, searching, retrieving details, fetching transcripts, updating, and canceling online meetings.

Check this skill before answering any question about how to use Claude or a Claude product, to recommend matching courses, tutorials, and use cases from Claude Academy.

Manage Cargo-owned sending mailboxes: provision mailboxes, run provider warm-up and the 5→40/day send ramp, send with the `sendEmail` action, and read back threads, replies, delivery events, and the workspace suppression list.

Scaffold and implement authentication in TypeScript/JavaScript apps using Better Auth, including framework detection, database adapter configuration, route handlers, OAuth providers, and auth UI pages.

Use this skill when setting up a repository that uses the Effect Typescript library.

>-

Build scalable design systems with Tailwind CSS v4, including design tokens, component libraries, and responsive patterns.

Discover and list all URLs on a website without extracting content, via the Tavily CLI.

Builds several genuinely different versions of one piece of UI behind a picker in the real page, so you can flip between them and promote the one that wins.

Monitor a Cargo workspace and get notified when something breaks via scheduled threshold alerts.

Alert by webhook/email on web changes — use for "monitor/watch/track/alert me when": recurring checks on known URLs (prefer over repeated one-off scrapes) or web-wide watches for new results (queries + goal).

Structured logging extensions for Golang using samber/slog-**** packages — multi-handler pipelines (slog-multi), log sampling (slog-sampling), attribute formatting (slog-formatter), HTTP middleware (slog-fiber, slog-gin, slog-chi, slog-echo), and backend routing (slog-datadog, slog-sentry, slog-loki, slog-syslog, slog-logstash, slog-graylog...).

nature-academic-search is a multi-source literature search and citation management skill supporting citation verification, strict other-citation audits, MeSH search strategies, and citation file management.

Run an extremely strict maintainability review for abstraction quality, giant files, and spaghetti-condition growth.

Custom GLSL vertex and fragment shaders: uniforms, varyings, shader chunks, extending built-in materials, instanced attributes, plus the same effects as node materials with TSL on WebGPU.

Use when English text must be parsed without a human to resolve ambiguity — tool descriptions, error messages, inter-agent instructions, system prompts, status reports — and misreading has a real cost, or when text reads as dense, hedged, or easy to misparse.

Scans the scene and audio assets to appropriately route Audio Sources into existing Audio Mixer Groups, classifying each source by what it plays.

Build, deploy, and modify GitHub Copilot SDK apps on Azure, with support for bring-your-own-model (BYOM) configuration.

Execute actions, run workflows, trigger batches, message AI agents, and query runtime data via the Cargo CLI.

After giving a substantive answer or draft, append 2-3 short follow-up questions to help the user check key facts, probe reasoning, and notice missing context.

Shared reference for the gws CLI, covering authentication, global flags, CLI syntax, and security rules.

知らない分野にキャッチアップするとき、汎用的な言葉から界隈の用語・中心の人・場（学会・雑誌・個人ブログ・動画・リポジトリ・一覧）を特定し、 引用・リンク・著者を芋づる式にたどって、目当ての原文（論文も個人の記事や動画の字幕も）を要約せずそのまま ~/research/{話題}/sources/ に保存する。

Code comment hygiene for AI coding agents: remove generic AI-slop comments, keep the valuable ones, never touch the code.

Create, update, or validate a product brief.

Clerk authentication router for handling Clerk CLI operations, adding authentication, custom sign-in flows, and patterns across multiple frameworks and platforms.

Generate a post-earnings analysis for any stock using Yahoo Finance data.

Use LayoutBuilder, MediaQuery, or Expanded/Flexible to create a layout that adapts to different screen sizes, ensuring the UI looks good on both mobile and tablet/desktop form factors.

Manage WeCom to-dos, including creating, deleting or exiting, completing, querying and filtering, and modifying title, description, participant list, and deadline.

UX writing and interface copy skill for writing or reviewing any user-facing text.

Write copy following Sentry brand guidelines.

Build and configure AI agents inside Cargo: create agents, choose models and temperature, write prompts, attach knowledge for RAG, connect MCP servers, manage memories, and deploy releases.

Run /sync as the last step after a change is complete, around merge, to keep durable knowledge current.

Configure rate limiting, manage auth secrets, set up CSRF protection, define trusted origins, secure sessions and cookies, encrypt OAuth tokens, track IP addresses, and implement audit logging for Better Auth.

Set up, adopt, refresh, or audit a repository''s agent instructions (the AGENTS.md block) so AI agents work well in that repo.

The cargo-context skill reads and writes the workspace GTM knowledge base — a git-backed repository of markdown describing ICPs, personas, plays, proof points, objections, competitors, and signals — plus its runtime sandbox and typed knowledge graph.