Coding & review skills

Use when the user wants a design doc, technical proposal, RFC, or architecture decision record (ADR) — comparing options for a technical problem and recording the decision.

Use when developing a browser extension.

Create reviewable launch videos and OSS promotion packets from repositories, products, briefs, and media.

Reads 3 to 5 recent reviews the user can legally open and writes a style brief: structure, section length, figure count, citation density, and tone. Trigger on "style brief", "exemplar reviews", "match the journal's…

Recommend an AI coding model and native effort, compare the next step's cost, or assess when to use a Coding Plan using Model Plan's published data and optional local quota observations.

Audits React components (JSX/TSX, including Next.js) for accessibility against WCAG 2.2 AA, covering color contrast, ARIA, focus, keyboard navigation, form labels and alt text, and proposes the code fix for each issue.…

Review and harden a Model Context Protocol (MCP) server before it leaves localhost - transport and bind address, bearer or OAuth auth, Origin validation, tool input limits, file and URL access, secrets, errors and…

A scoring scale for evaluating how well a CLI is designed for AI agents, based on the "Rewrite Your CLI for AI Agents" principles.

Create Gentle AI pull requests with issue-first checks. Trigger: creating, opening, or preparing PRs for review.

Professional context and harness engineering for Claude Code and OpenAI Codex. Build production-grade software with spec-driven development, TDD, persistent memory, quality gates, code intelligence, human oversight, and…

Use when the user wants a change or an area of code shown to them rather than searched: "visual diff", "visualize diff", "visualise diff", "visualize-diff", "visualize this PR", "visualise this branch", "visual recap",…

Vercel's official collection of agent skills

让你的 AI 不敢摆烂。用大厂 PUA 话术穷尽一切方案。触发条件:(1) 任务失败 2+ 次或反复微调同一思路; (2) 即将说'我无法解决'、建议用户手动操作、未验证就归因环境; (3) 被动等待——不搜索、不读源码、只等指示; (4) 用户不满:'try harder'、'stop giving up'、'换个方法'、'为什么还不行'、'你再试试'、'你怎么又失败了'。适用于所有任务类型。首次失败或已知修复正在执行时不触发。

Unified CloudBase execution guide for all-in-one skill installs. Use this first for CloudBase app tasks, especially existing apps with TODOs, fixed pages, or active handlers. Routes PostgreSQL / CloudBase PG / app.rdb()…

Official skill for the MobileBuildMCP CLI. Use when doing iOS/macOS/watchOS/tvOS/visionOS work (build, test, run, debug, log, UI automation).

Official skill for the MobileBuildMCP CLI. Use when doing iOS/macOS/watchOS/tvOS/visionOS work (build, test, run, debug, log, UI automation).

WCAG 2.2 compliance, ARIA patterns, keyboard navigation, screen readers, automated testing

Comprehensive GitHub code review with AI-powered swarm coordination

Use when composing an ask_user_question round inside a workflow, or when a workflow skill names it at a question step. Shared norms for the tool — not a workflow, nothing to execute.

Reference standards for writing pull request titles and descriptions in the tldraw repository, plus the pre-flight comment sweep over the diff. Use as supporting guidance when another skill or workflow needs PR content…

Vercel's official collection of agent skills

Adaptive-depth session recap and low-friction checkpoint capture for report-ready Tracework memory. Use this skill for "/tracework:capture" or when the user signals end of a work session, such as "收工", "今天到这", "done",…

MUST USE when the user or agent wants anything related to the AgentsEarth world: joining, genesis, avatar evidence, memory, live conversations, offline letters, movement, discovery, skill sharing and trading, the…

PR bug review and test planning with QAMap. Run `qamap qa brief` once; it prints the diff, each changed declaration's tests and callers with assertion lines, QA focus and unknowns in one bounded local response, so the…