Top Agent Skills

Full-cycle AI coding skill: plans, builds, tests, lints, fixes bugs, and writes production-grade docs. Auto-detects project state and adapts its 8-phase pipeline.

Use when the user asks to create a CodeTour .tour file — persona-targeted, step-by-step walkthroughs that link to real files and line numbers. Trigger for: create a tour, onboarding tour, architecture tour, PR review tour, explain how X works, vibe check, RCA tour, contributor guide, or any structured code walkthrough request.

Scrape and crawl websites for AI with Firecrawl — scrape single URLs to clean Markdown/HTML, crawl entire sites with depth/path filters, extract structured data with LLM schema, use map to discover all URLs, and batch scrape multiple pages in parallel.

Design for mobile — touch targets, thumb zones, gesture patterns, iOS and Material 3 platform conventions, mobile form design, and responsive breakpoints. Use when building mobile-first UI, reviewing a layout for phone/tablet, asked about "touch targets", "thumb zone", "iOS conventions", "Android Material", "mobile form", or "responsive design". Do NOT use for desktop-only UIs — use `ux-heuristics` for general usability.

Build full-stack web applications with SvelteKit — file-based routing, SSR, SSG, API routes, and form actions in one framework.

REST API design patterns including resource naming, status codes, pagination, filtering, error responses, versioning, and rate limiting for production APIs.

Build evaluation frameworks for agent systems. Use when testing agent performance systematically, validating context engineering choices, or measuring improvements over time.

Review L2 session facts and promote valuable ones to L1 Atomic Memory. Use at end of session or when L2 accumulates facts worth keeping permanently. Runs add-fact.sh for each promoted fact.

Use before touching any code when user gives a task, spec, or feature request. Forces writing a plan before implementation. Examples: 'implement X', 'add feature Y', 'fix Z and also update A', any multi-step task that would touch 2+ files.

Write and maintain Architecture Decision Records (ADRs) — when to write one, the standard format, status lifecycle, how to link related decisions, and how to surface ADRs in a codebase. Use when asked to "write an ADR", "document this decision", "architecture decision record", "why did we choose X over Y", or "we need a record of this choice". Do NOT use for: general documentation writing — ADRs are specifically for significant architecture decisions.

Use when an AI agent needs to control a browser, automate web tasks, scrape pages, fill forms, or click buttons autonomously. Triggers on: 'browser automation', 'web agent', 'browser-use', 'AI browse', 'tự động duyệt web', 'điều khiển trình duyệt', 'scrape with AI', 'click button automatically', 'fill form automatically', 'web task automation'.

This skill should be used when the user wants to "improve a skill", "update skill based on feedback", "optimize skill after use", or says "自更新", "/自更新". Collects user feedback after using a skill and automatically updates that skill with improvements.

Guide on using oh-my-codex plugin

Multi-platform content distribution across X, LinkedIn, Threads, and Bluesky. Adapts content per platform using content-engine patterns. Never posts identical content cross-platform. Use when the user wants to distribute content across social platforms.

Diagnose and fix oh-my-codex installation issues

Unified media generation via fal.ai MCP — image, video, and audio. Covers text-to-image (Nano Banana), text/image-to-video (Seedance, Kling, Veo 3), text-to-speech (CSM-1B), and video-to-audio (ThinkSound). Use when the user wants to generate images, videos, or audio with AI.

Anthropic Codex API patterns for Python and TypeScript. Covers Messages API, streaming, tool use, vision, extended thinking, batches, prompt caching, and Codex Agent SDK. Use when building applications with the Codex API or Anthropic SDKs.

Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skill should be used when the user is looking for functionality that might exist as an installable skill.

Setup and configure oh-my-codex using current CLI behavior

Interactive agent picker for composing and dispatching parallel teams

Create CodeTour `.tour` files — persona-targeted, step-by-step walkthroughs with real file and line anchors. Use for onboarding tours, architecture walkthroughs, PR tours, RCA tours, and structured "explain how this works" requests.

Interactive installer for Everything Codex — guides users through selecting and installing skills and rules to user-level or project-level directories, verifies paths, and optionally optimizes installed files.

当需要用 lark-cli 操作飞书多维表格（Base）时调用：适用于建表、字段管理、记录读写、视图配置、历史查询，以及角色/表单/仪表盘管理；也适用于把旧的 +table / +field / +record 写法改成当前命令写法。涉及字段设计、公式字段、查找引用、跨表计算、行级派生指标、数据分析需求时也必须使用本 skill。

Hand off the current task to another agent with full context. Use when the user says "handoff", "hand off", "hand this to", or wants to pass work to another agent (Codex or Claude).

Use only when writing/updating/fixing C++ tests, configuring GoogleTest/CTest, diagnosing failing or flaky tests, or adding coverage/sanitizers.

Socratic deep interview with mathematical ambiguity gating before execution

Review generated code for style, security, and architecture issues; suggest refactorings and performance improvements. Use after implementation is complete, before merging changes, or when refactoring existing code. Follows OWASP guidelines, SOLID principles, and best practices for maintainable code.

Generate clear documentation for each task including technical descriptions, architecture diagrams, and usage guides. Use when documenting completed features, creating README files, writing API documentation, generating architecture diagrams, or maintaining project documentation. Ensures knowledge is preserved and accessible.

Search external documentation (web pages, API docs, papers) and generate useful summaries for development. Use when investigating new technologies, understanding third-party APIs, researching best practices, or gathering information for technical decisions. Reduces hallucinations and expands agent knowledge.

Sync delta specs from a change to main specs. Use when the user wants to update main specs with changes from a delta spec, without archiving the change.

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes

Generate comprehensive checklists to validate requirements quality (Unit Tests for Specs). Critically examine the spec for clarity, completeness, and consistency before implementation starts.

WelineFramework local testing adapter. Use when working in this repo on how to write module tests, choose validation layers, or run PHPUnit, Pest, Vitest, Playwright, HTTP smoke, Browser smoke, or WLS-backed test flows. Read dev/ai/skills/testing/SKILL.md before acting.

口令「分仓」触发：将 DEV-workspace 中 app/code/Weline 模块同步到项目兄弟目录“框架-分仓” 下的独立 Composer 分仓；本地缺仓库时自动从 Gitee/GitHub clone，递增 git tag 后推送并刷新 Packagist。 仅在用户明确说出口令「分仓」时加载；不得因闲聊、发布、部署等相近词自动触发。 Keywords: 分仓, fencang, split-repo, composer sync, weline mirror.

visitor-pixel

Weline_Deploy：随机 Webhook 路径（~wh~）、ModuleRouter、webhook_secret、 deploy:webhook:setup、deploy:release、WLS+Nginx。

extension-points

E2E automation engineer skill for Playwright-driven flow validation, browser interaction coverage, and end-to-end regression checks. Disabled by default for E2E case/spec work; use only when the user explicitly asks for E2E tests or execution.

service-development

codex-task-workspace

unified-query-provider

create-framework-command

i18n-internationalization

.cursor 仅做引用。规则/技能/计划主仓在 dev/ai。新增/修改必须在 dev/ai 下操作。

Use when the user asks how code works, wants to understand architecture, trace execution flows, or explore unfamiliar parts of the codebase. Examples: "How does X work?", "What calls this function?", "Show me the auth flow"

Build ultra-fast web APIs and full-stack apps with Hono — runs on Cloudflare Workers, Deno, Bun, Node.js, and any WinterCG-compatible runtime.

Build content-focused websites with Astro — zero JS by default, islands architecture, multi-framework components, and Markdown/MDX support.

Launch RSVP speed reader for text

Convex reactive backend expert: schema design, TypeScript functions, real-time subscriptions, auth, file storage, scheduling, and deployment.

Interact with GitHub issues - create, list, and view issues.

Qiskit is the world's most popular open-source quantum computing framework with 13M+ downloads. Build quantum circuits, optimize for hardware, execute on simulators or real quantum computers, and analyze results. Supports IBM Quantum (100+ qubit systems), IonQ, Amazon Braket, and other providers.

Expert C4 Code-level documentation specialist. Analyzes code directories to create comprehensive C4 code-level documentation including function signatures, arguments, dependencies, and code structure.

Inngest expert for serverless-first background jobs, event-driven workflows, and durable execution without managing queues or workers.

Optimize content for AI Overviews, ChatGPT, Perplexity, and other AI search systems. Use when improving GEO, AI citations, llms.txt readiness, crawler accessibility, and passage-level citability.

Design user flows and screen structure using StyleSeed UX patterns such as progressive disclosure, hub-and-spoke navigation, and information pyramids.

BlockRun works with Claude Code and Google Antigravity.

Optimize any form that is NOT signup or account registration — including lead capture, contact, demo request, application, survey, quote, and checkout forms.

Install and configure the Manifest observability plugin for your agents. Use when setting up telemetry, configuring API keys, or troubleshooting the plugin.

Write idiomatic Ruby code with metaprogramming, Rails patterns, and performance optimization. Specializes in Ruby on Rails, gem development, and testing frameworks.

Interactive StyleSeed setup wizard for choosing app type, brand color, visual style, typography, and the first screen scaffold.