AI Skills Hub - Browse 180,000+ Agent Skills

Spring Authorization Server for building OAuth 2.1 and OpenID Connect providers. USE WHEN: user mentions "OAuth2 server", "authorization server", "OIDC provider", "token endpoint", asks about "how to implement OAuth2", "create authorization server", "issue JWT tokens", "custom OAuth provider" DO NOT USE FOR: OAuth2 client configuration - use `spring-security` instead, resource server JWT validation - use `spring-security` instead

Fastify high-performance Node.js framework. Covers routing, plugins, validation, and serialization. Use when building fast Node.js APIs. USE WHEN: user mentions "Fastify", "fastify", "TypeBox", "schema validation", asks about "fast Node.js framework", "high-throughput API", "JSON schema validation", "performance-critical backend", "plugin-based architecture" DO NOT USE FOR: Enterprise DI patterns - use `nestjs` instead, Minimalist approach - use `express` instead, Edge runtimes - use `hono` instead, Deno - use `oak` or `fresh` instead

Actix-web Rust web framework. Covers routing, extractors, middleware, state management, and WebSocket. Use for high-performance Rust APIs. USE WHEN: user mentions "actix-web", "actix", "rust web framework", "rust api", asks about "rust async web", "actix middleware", "actix extractors", "rust websocket", "high performance rust api" DO NOT USE FOR: Axum projects - use `axum` instead, Rocket projects - use `rocket` instead, Warp projects - use `warp` instead, non-Rust backends

Rocket Rust web framework. Covers routing, fairings, guards, state, and testing. Use for type-safe, boilerplate-free Rust APIs. USE WHEN: user mentions "rocket", "rust type-safe api", "rocket guards", asks about "rocket fairings", "rocket state", "compile-time route checking", "rust web macros", "rocket testing" DO NOT USE FOR: Axum projects - use `axum` instead, Actix-web projects - use `actix-web` instead, Warp projects - use `warp` instead, non-Rust backends

Axum Rust web framework by Tokio. Covers routing, handlers, extractors, middleware, and state. Use for ergonomic async Rust APIs. USE WHEN: user mentions "axum", "tokio web", "rust async api", "tower middleware", asks about "axum extractors", "axum state", "axum router", "rust websocket axum", "hyper server", "ergonomic rust api" DO NOT USE FOR: Actix-web projects - use `actix-web` instead, Rocket projects - use `rocket` instead, Warp projects - use `warp` instead, non-Rust backends

shadcn/ui component library with Radix primitives and Tailwind CSS. Covers component installation, customization, theming, and common patterns. USE WHEN: user mentions "shadcn", "shadcn/ui", asks about "shadcn components", "installing shadcn", "shadcn setup", "copy-paste components" DO NOT USE FOR: Radix UI only (use radix-ui skill), Tailwind only (use tailwindcss skill), Material-UI, Chakra UI, Ant Design

Svelte 5 with runes reactivity system. Covers components, state management, and reactive declarations. USE WHEN: user mentions "Svelte", "runes", "$state", "$derived", "$effect", "SvelteKit", asks about "Svelte 5 patterns", "reactive runes" DO NOT USE FOR: Svelte 4 and earlier - use Svelte 4 documentation, React - use `frontend-react`, Vue - use `vue-composition`, Angular - use `angular`

NATS cloud-native messaging system. Covers Core NATS, JetStream persistence, and request/reply patterns. Use for lightweight, high-performance microservices communication. USE WHEN: user mentions "nats", "jetstream", "cloud-native messaging", "request/reply", "subject wildcards", asks about "lightweight messaging", "microservices communication", "nats streaming" DO NOT USE FOR: event sourcing - use `kafka` or `pulsar`; complex routing - use `rabbitmq`; AWS-native - use `sqs`; Azure-native - use `azure-service-bus`; JMS compliance - use `activemq`; persistent queues only - use dedicated broker

RabbitMQ message broker with AMQP protocol. Covers exchanges, queues, bindings, and messaging patterns. Use for reliable message delivery and complex routing scenarios. USE WHEN: user mentions "rabbitmq", "amqp", "exchanges", "routing patterns", "topic exchange", "fanout", asks about "message routing", "work queues", "request/reply", "flexible routing" DO NOT USE FOR: high-throughput streaming - use `kafka` or `pulsar`; cloud-native - use `nats`; AWS-native - use `sqs`; JMS required - use `activemq`; simple pub/sub - use `redis-pubsub`

Redis Pub/Sub and Streams for messaging. Covers publish/subscribe, streams with consumer groups, and real-time patterns. Use for lightweight messaging and real-time features. USE WHEN: user mentions "redis pub/sub", "redis streams", "real-time messaging", "lightweight messaging", "pattern subscriptions", asks about "fast messaging", "simple pub/sub", "event streams with redis" DO NOT USE FOR: guaranteed delivery - use `kafka`, `rabbitmq`, or `pulsar`; complex routing - use `rabbitmq`; high durability needs - use `kafka`; enterprise features - use `activemq`; cloud-native - use cloud providers

Event-driven architecture patterns and best practices. Covers Saga, Outbox, CQRS, Event Sourcing, and messaging patterns for distributed systems. USE WHEN: user mentions "event-driven", "Saga", "Outbox pattern", "CQRS", "Event Sourcing", "distributed transactions", "eventual consistency", "message broker", "event bus", asks about "microservices communication", "async patterns", "compensating transactions" DO NOT USE FOR: Simple pub/sub - use messaging framework skills (Kafka, RabbitMQ), REST APIs - use API design skills, Real-time updates - use WebSocket skills, Basic async/await - use language-specific skills

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

Create effective skills for OpenCode agents. Load FIRST before writing any SKILL.md. Provides required format, naming conventions, progressive disclosure patterns, and validation. Use when building, reviewing, or debugging skills.

Local Docker Compose development workflows for the EPOS Open Source CLI. Use when working with `epos-opensource docker` commands (deploy/update/populate/clean/delete/export/list), preparing custom `.env` or `docker-compose.yaml` files, customizing ports/host, or troubleshooting local Docker environments.

Execute and monitor long-running RL training campaigns. Progress tracking, checkpoint management, experiment logging, and resume capabilities.

Plan weekly meals, generate grocery lists with real Kroger prices, and add items to the Kroger cart for pickup. Triggered by /meal-plan.

Create short-form finance videos with AI voiceover and animated slides.

Download videos, audio, subtitles, and clean paragraph-style transcripts from YouTube and any other yt-dlp supported site. Use when asked to “download this video”, “save this clip”, “rip audio”, “get subtitles”, “get transcript”, or to troubleshoot yt-dlp/ffmpeg and formats/playlists.

Customize or personalize a Claude Code plugin for a specific organization's tools and workflows. Use when users want to customize a plugin, replace tool placeholders, or configure MCP servers for a plugin. This skill requires Cowork mode with mounted plugin directories and will not work in remote or standard CLI sessions.

Run nf-core bioinformatics pipelines (rnaseq, sarek, atacseq) on sequencing data. Use when analyzing RNA-seq, WGS/WES, or ATAC-seq data—either local FASTQs or public datasets from GEO/SRA. Triggers on nf-core, Nextflow, FASTQ analysis, variant calling, gene expression, differential expression, GEO reanalysis, GSE/GSM/SRR accessions, or samplesheet creation.

This skill should be used after shogun writes a task to queue/shogun_to_karo.yaml. It sends a tmux send-keys notification to karo's pane, triggering karo to check for new tasks in shared_context/shogun_to_karo.yaml.

Run nf-core bioinformatics pipelines (rnaseq, sarek, atacseq) on sequencing data. Use when analyzing RNA-seq, WGS/WES, or ATAC-seq data—either local FASTQs or public datasets from GEO/SRA. Triggers on nf-core, Nextflow, FASTQ analysis, variant calling, gene expression, differential expression, GEO reanalysis, GSE/GSM/SRR accessions, or samplesheet creation.

Kubernetes and kubectl mastery for deployments, services, pods, debugging, and cluster management. Use when user asks to "deploy to k8s", "create deployment", "debug pod", "kubectl commands", "scale service", "check pod logs", "create ingress", or any Kubernetes tasks.

首次使用引导。交互式帮助用户完成 MyCC 初始化配置。触发词："/setup"、"帮我配置"、"初始化"、首次使用时自动触发。

Integrate RDKit analysis and retrosynthesis visualization into an executable closed loop. Use when the user needs one skill that consumes target SMILES plus route/audit JSON, generates visualization assets and markdown report, and can be plugged into host LLM tools such as Claude Code, OpenCode, and Cursor.

HEA and Sale-Leaseback eligibility calculation rules and patterns

Diagnostica errores comunes en producción rápidamente

This skill should be used when the user asks to "use codex", "ask codex", "let codex review", "get a second opinion", "compare with codex", "delegate to codex", "codex review my code", "have codex check this", "用 codex", "让 codex 看看", "codex 审查", "codex 帮我看", "用 codex 分析", "让 codex 帮忙", "交给 codex", "codex 看一下", "换 codex 看看", or when cross-model verification, code review, or collaborative generation with OpenAI Codex CLI is needed.

Use when implementation is complete, all tests pass, and you need to decide how to integrate the work - guides completion of development work by presenting structured options for merge, PR, or cleanup

Comprehensive skill for installing, configuring, and managing the OpenClaw ecosystem (Gateway, Channels, Models, Automation, Nodes, and Deployment).

Read and send email via IMAP/SMTP. Check for new/unread messages, fetch content, search mailboxes, mark as read/unread, and send emails with attachments. Works with any IMAP/SMTP server including Gmail, Outlook, 163.com, vip.163.com, 126.com, vip.126.com, 188.com, and vip.188.com.

No description available

Manages Google Calendar — creates, updates, and queries events, scheduling, and availability. Use when the user mentions calendar, meetings, appointments, agenda, or Google Calendar.

背景透過された画像を生成する。Gemini APIで画像生成後、WaveSpeed AI (Bria) で背景を自動透過。透過PNG、切り抜き画像、背景なし画像の生成に使用。

Use when creating datasets, uploading files, managing schemas, or configuring dataset connections

Deploy prompt-based Azure AI agents from YAML definitions to Azure AI Foundry projects. Use when users want to (1) create and deploy Azure AI agents, (2) set up Azure AI infrastructure, (3) deploy AI models to Azure, or (4) test deployed agents interactively. Handles authentication, RBAC, quotas, and deployment complexities automatically.

Complete installation and setup guide for OpenClaw, the personal AI assistant. Use this skill when the user wants to install OpenClaw, set up the gateway, configure channels (WhatsApp, Telegram, Slack, Discord, Signal, iMessage), troubleshoot installation issues, update OpenClaw, or understand the system architecture. Also triggers for queries about Clawdbot, Moltbot (previous names), skills management, or ClawdHub registry.

Regenerate Bruno API collections from OpenAPI spec. Use after adding or modifying API endpoints to keep interactive API documentation in sync.

Search arXiv preprint repository for papers in physics, mathematics, computer science, quantitative biology, and related fields

Generate AI images using Volcano Engine's Seedream 4.5 model. Use this skill when users want to create images, generate artwork, or mention image generation with specific styles such as Ghibli, Futuristic, Pixar, Oil Painting, Chinese Painting, Anime, Realistic, Cyberpunk, Watercolor, or other artistic styles.

Use when working with VueUse composables - provides reactive utilities for state, browser APIs, sensors, network, animations. Check VueUse before writing custom composables - most patterns already implemented.

テンプレートに基づきPDFファイルを添付してメールを送信する

AIニュースを収集・要約してPDF生成・Slack投稿する

Turborepo monorepo build system guidance. Triggers on: turbo.json, task pipelines, dependsOn, caching, remote cache, the "turbo" CLI, --filter, --affected, CI optimization, environment variables, internal packages, monorepo structure/best practices, and boundaries. Use when user: configures tasks/workflows/pipelines, creates packages, sets up monorepo, shares code between apps, runs changed/affected packages, debugs cache, or has apps/packages directories.

Insert urgent work as a decimal phase between existing phases, adding mid-milestone work, or creating intermediate phases. Triggers include "insert phase", "add urgent phase", "create decimal phase", "insert between phases", and "urgent work".

Build Python-native web apps with Mesop. Triggers when users want to build, debug, or deploy Mesop applications, including AI chat interfaces, internal tools, and ML demos.

Kanban-style task management dashboard for AI assistants. Manage tasks via CLI or dashboard UI. Use when user mentions tasks, kanban, task board, mission control, or wants to track work items with status columns (backlog, in progress, review, done).

A hard-edged writing style contract for timeless, forceful English prose without modern AI tics. Use when users ask for prose or rewrites that must be clean, exact, concrete, and free of AI cadence, filler, or therapeutic tone.

This skill should be used when the user asks to "send a Telegram message", "poll for Telegram updates", "check Telegram bot status", "respond to Telegram messages", "react to messages", "manage Telegram bot", or mentions Telegram Bot API operations. Provides comprehensive guidance for using the tg CLI to interact with Telegram bots.

Use this when installing dependencies, running scripts, filtering packages, or migrating this monorepo from pnpm to Bun (bun.lock, workspaces, bun ci) while keeping Cloudflare Workers + Wrangler workflows working.

Toolkit for comprehensive document creation, editing, and analysis with support for tracked changes, comments, formatting preservation, and text extraction. Use to work with professional documents (.docx files) for: (1) Creating new documents, (2) Modifying or editing content, (3) Working with tracked changes, (4) Adding comments, or any other document tasks

Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.

Authoring data collection forms in Excel for mobile surveys. XLSForm converts Excel files to XForms for ODK, KoBoToolbox, and similar platforms. Use for field surveys, data collection, conditional forms, GPS tracking, and offline data gathering.

Generate C ABI wrappers for third-party C++ libraries, enabling FFI access from languages like Clojure (via Panama), Rust, Python, etc. Use when wrapping C++ classes/functions into C-compatible shared libraries (.dylib/.so), creating extern "C" interfaces, or building FFI-friendly APIs from C++ code.

Root cause analysis framework that prevents guess-and-check debugging

Expert assistance with GraphPad Prism scientific graphing and statistics software, specializing in Prism scripting for automation, batch processing, and data analysis workflows.

Manage your installed Claude Code skills - install, update, rename, uninstall, and list skills from GitHub URLs. Use when the user wants to install a skill, update a skill, list installed skills, rename a skill, remove/delete/uninstall a skill, or provides a GitHub URL to a skills directory.

Configure Claude Code hooks in settings.json for event-driven automation. Use when setting up or modifying lifecycle hooks.

Reference documentation for Claude Code memory hierarchy, imports, and shortcuts. For memory management workflows (audit, migrate, create rules), use the orchestrate-memory agent instead.

全面的文档创建、编辑和分析功能，支持修订跟踪、注释、格式保留和文本提取。当Claude需要处理专业文档（.docx文件）时，适用于：(1) 创建新文档，(2) 修改或编辑内容，(3) 处理修订跟踪，(4) 添加注释或其他文档任务

使用 Playwright 与本地 Web 应用程序交互和测试的工具包。支持验证前端功能、调试 UI 行为、捕获浏览器截图和查看浏览器日志。

Use when extracting structured data from websites using Playwright MCP tools, when handling login/authentication flows, when crawling paginated content, or when building scrapers that navigate dynamic SPAs with tabs, accordions, or React/HeadlessUI components

Use the domino-data Python SDK (dominodatalab-data) for programmatic data access in Domino. Covers DataSourceClient for SQL queries and object storage, DatasetClient for dataset files, TrainingSets for ML data versioning, Feature Store, and VectorDB (Pinecone) integration. Use when querying data sources, downloading datasets, managing training sets, or working with vector databases in Domino.

Search arXiv preprint repository for papers in physics, mathematics, computer science, quantitative biology, and related fields

Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.

Allocate the next available Business Central AL object ID/number by scanning .al files and idRanges in app.json using the bundled PowerShell script. Use when creating new tables/pages/codeunits/extensions and you need a free object number.

Build and test AL/Business Central projects. Use after modifying AL code or tests to verify the build gate passes. Runs compilation, publishing, and test execution in a single command. Required gate before committing AL changes.

Routes natural language to Obsidian capture commands. Triggers on: spending ("spent", "bought", "paid", "log spending"), tasks ("add task", "todo", "remind me"), workouts ("went to gym", "swam", "ran", "workout"), evenings ("build night", "drift", "productive evening"), notes ("note to self", "capture note"), lists ("add to reading list", "add to list"), savings ("saved", "deposited", "savings fund"), reviews ("how was my week", "monthly review"), bored/stuck ("bored", "stuck", "what should I do", "what now", "need something to do"), completion ("done with", "finished reading", "read that article", "watched that", "listened to"), syncing ("sync vault", "sync obsidian", "sync configs", "push my changes"), planning ("plan", "deep plan", "help me plan", "let's plan"), context ("pull context", "get context", "what do I have on", "find my notes on").

自动将 HTML 文章发布到微信公众号草稿箱，支持封面图上传、标题、作者和元数据管理。当用户说"推送到微信"、"发布到公众号草稿"、"上传到草稿箱"或提到微信文章发布时使用。

Integrates with Carta API for real-time cap table data, portfolio holdings, fund performance (TVPI/DPI/IRR), and 409A valuations. Use when pulling cap tables from Carta, checking ownership data, analyzing fund performance, or syncing investment data. Triggers on "Carta cap table", "portfolio holdings", "fund performance", "409A valuation", "equity data from Carta".

Analyzes financial CSV/Excel files for VC due diligence. Calculates revenue trends, burn rate, margins, and runway from P&L data. Use when processing financial statements, analyzing expense breakdowns, or validating financial data quality. Triggers on "analyze financials", "P&L analysis", "burn rate", "revenue breakdown", "financial model".

Spec-Driven Development methodology for Aider Desk - specifications as executable truth

Playwrightを使用してローカルWebアプリケーションと対話し、テストするためのツールキット。フロントエンド機能の検証、UI動作のデバッグ、ブラウザスクリーンショットのキャプチャ、ブラウザログの表示をサポートします。

| 模式 | 路由到 | 输出工件 | |------|--------|----------| | auto | (自动检测) | 取决于路由目标 | | blocker | /thingking | blocker.latest.yaml, trail.latest.yaml | | research | /thingking_web | research.latest.yaml, delta.latest.yaml, plan.latest.yaml | | full | /thingking → /thingking_web | 所有工件 |

YouTube収録用のMarpスライドを作成するスキル。レイアウト制約を遵守し、視認性の高いスライドを生成する。

Interactive Metis integration for knowledge base and project management via REST API. On first use, asks for Metis host URL. Use when searching documentation, managing projects/tasks, or querying indexed knowledge. Provides RAG-powered semantic search, website crawling, document upload, hierarchical project/task management, and document versioning. Always try Metis first for external documentation and knowledge retrieval before using other sources.

Verifies test coverage using Codecov API, compares coverage between commits/branches, validates coverage claims against thresholds. Use when verifying PR coverage improvements, investigating local tool discrepancies, or validating CI/CD coverage reports.

Search past reasoning for relevant decisions and approaches

Configure and compile FFmpeg from source for any platform and architecture. Handles cross-compilation (Linux→Windows, x86_64→ARM), license compliance (LGPL/GPL/nonfree), codec dependencies, and Docker-based builds. Use when building FFmpeg binaries, creating CI/CD pipelines for FFmpeg compilation, debugging configure failures, or selecting codecs and features for custom builds.

Interpret and analyze CMSIS SVD (System View Description) files for ARM Cortex-M microcontrollers. Use when working with SVD files, querying microcontroller register definitions, looking up peripheral information, finding register addresses, or understanding bit field layouts. Triggers on mentions of SVD files, microcontroller registers, CMSIS peripherals, or embedded system memory maps.

Software engineer specializing in creating production-ready ADK agents with best practices, code structure, testing, and deployment automation. Use when asked to "build ADK agent", "create agent code", or "engineer ADK application". Trigger with relevant phrases based on skill purpose.

臺灣學測專家級技能，涵蓋國文、社會、價值觀三大領域。採用三層漸進式知識架構：導航→概覽→主題→細節，僅載入必要知識。使用智慧標籤系統和 ripgrep 快速檢索，提供結構化高品質答案。

Draft changelog PRs by collecting GitHub/Slack/Git changes, formatting with templates, running quality gates, and preparing a branch/PR. Use when generating weekly/monthly release notes or when the user asks to create a changelog from recent merges. Trigger with "changelog weekly", "generate release notes", "draft changelog", "create changelog PR".

Convert Twitter/X posts into Instagram Reels format. Screenshots tweets, crops to show username/caption/media, creates a 9:16 vertical canvas with matching background color, and overlays downloaded video content. Works alongside twitter-media-downloader skill. Use when user wants to repurpose Twitter content for Instagram, TikTok, or other vertical video platforms.

Download images and videos from X/Twitter using gallery-dl. Use when user wants to download media from Twitter/X URLs including tweets, user profiles, timelines, or likes. Supports single tweets, entire user media galleries, bookmarks, and lists. Handles authentication via cookies for accessing protected content.

Generate and edit system architecture diagrams from JSON definitions. Supports incremental editing with eval command. Outputs HTML, SVG, or enriched JSON. Also provides icon catalog search. Use when asked to create, modify, or visualize AWS/Azure/GCP architecture diagrams, or when searching for available icons.

Comprehensive code review assistant that analyzes code for security vulnerabilities, performance issues, and code quality. Use when reviewing pull requests, conducting code audits, or analyzing code changes. Supports Python, JavaScript/TypeScript, and general code patterns. Includes automated analysis scripts and structured checklists.

This skill should be used when the user asks to "implement LLM-as-judge", "compare model outputs", "create evaluation rubrics", "mitigate evaluation bias", or mentions direct scoring, pairwise comparison, position bias, evaluation pipelines, or automated quality assessment.

React Native and Expo best practices guide. Use this skill when: - Writing or reviewing React Native / Expo code - Debugging runtime errors (undefined is not an object, maximum update depth, etc.) - Fixing build failures (Gradle, CocoaPods, Metro bundler) - Working with React Navigation - Optimizing FlatList or fixing performance issues - Handling state management (Redux, Zustand, Context) - Working with native modules, permissions, camera, push notifications - Fixing Expo-specific issues (EAS Build, OTA updates, config plugins) - CSS properties not working (grid, animations, vh/vw units, pseudo-elements) - Styling differences between iOS and Android - Reviewing code for anti-patterns Triggers: react native error, expo error, build failed, flatlist slow, navigation error, state not updating, memory leak, permission denied, expo build, eas build, css not working, style not applied, grid layout, animation, shadow not showing

Audits and validates skill definitions for quality, completeness, and best practices. Use when reviewing existing skills for proper formatting, evaluating if skills should be split into sub-skills, or ensuring skills follow established conventions.

Programmatic Python debugging with breakpoints, state inspection, and stack traces. Use when debugging Python code that requires inspecting variable values at specific lines, understanding program state at runtime, capturing exception context, or when print-debugging is insufficient. Triggers on requests to "set a breakpoint", "inspect variables at line X", "debug this Python script", "capture the state when this crashes", or "trace execution".

Use when writing SysML v2 code, asking about "SysML syntax", "naming conventions", "how to write" a part def or calc def, "imports", "syntax error", "parse error", "common mistakes", "pitfalls", "SysML patterns", attribute declarations, units notation, doc comment format, ADR-002, or definition vs usage rules. Provides the canonical syntax rules and patterns for SysML v2 modeling.

Draw or fix ASCII art boxes, terminal wireframes, TUI mockups, and monospaced tables with proper CJK/emoji alignment. Use when user says "画个框"、"终端表格"、"ASCII box"、"字符画"、"线框图"、"TUI mockup"、"表格边框对齐"、"draw a box"、"terminal table"、"CLI layout"、"dashboard layout"、"UI skeleton"、"控制台输出"、"console output"、"边框歪了"、"borders broken", or shows misaligned +---+ borders. Not for Markdown tables or prose.

Download videos, audio, subtitles, and clean paragraph-style transcripts from YouTube and any other yt-dlp supported site. Use when asked to “download this video”, “save this clip”, “rip audio”, “get subtitles”, “get transcript”, or to troubleshoot yt-dlp/ffmpeg and formats/playlists.

Build AI-agent-optimized Model Context Protocol (MCP) servers following the MCP Excellence Standard. Use when creating new MCPs, enhancing existing MCPs, wrapping APIs as MCPs, or when the user mentions MCP, Model Context Protocol, or wants to build tools for AI agents. This skill ensures MCPs are token-efficient (returnOnlyIds, compact mode, pagination), include composite operations (search_and_action, get_or_create), handle errors properly (partial success, structured errors), and implement safety guardrails (dryRun, confirmation tokens, batch limits).

Create new dynamic pages from a short spec (keywords, route/path, reference content).

See `templates/` for more patterns: API health checks, dependency verification, TypeScript AST analysis, Python DB schema checks, ephemeral session setup.

使用 Playwright 与测试本地 Web 应用的工具包。支持验证前端功能、调试 UI 行为、截取浏览器截图，以及查看浏览器日志。

Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.

Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.