9.5万 个 · 按人气排序
Set up @changesets/cli for semantic versioning, CHANGELOG generation, and npm publishing in a monorepo or single package. Covers init, config, contributor workflow, GitHub Actions release automation, and npm provenance.
中文简介正在准备中。当前显示原文说明。
Set up GitHub Actions CI pipeline with test, lint, type-check, and build jobs for a Node.js/TypeScript project. Includes output grouping, error annotations, and job summary patterns.
中文简介正在准备中。当前显示原文说明。
Set up tsup (esbuild-based bundler) for a TypeScript package. Use when you need single-file bundled output, faster builds, and better startup time for Node.js CLIs or libraries. Covers tsup config, bin entry point, package.json scripts, and keeping tsc for type-checking only.
中文简介正在准备中。当前显示原文说明。
Implement a structured error class hierarchy with actionable messages, proper exit codes, debug mode via env var, and bug report hints on unexpected errors. Generic pattern for any CLI tool or Node.js application.
中文简介正在准备中。当前显示原文说明。
Add zod schema validation for CLI options and YAML/JSON config files. Generic pattern for runtime validation with type-safe parsing and clear error messages in any Commander.js CLI.
中文简介正在准备中。当前显示原文说明。
Use this skill when building applications with Gemini models, Gemini API, working with multimodal content (text, images, audio, video), implementing function calling, using structured outputs, or needing current model specifications. Covers SDK usage (google-genai for Python, @google/genai for JavaScript/TypeScript, com.google.genai:google-genai for Java, google.golang.org/genai for Go), model selection, and API capabilities.
中文简介正在准备中。当前显示原文说明。
Expert guidelines for Chrome extension development with Manifest V3, covering security, performance, and best practices
中文简介正在准备中。当前显示原文说明。
ScepticAgent internal architecture reference. Use whenever the user asks how the extension works, wants to add a new AI provider, add a new highlight category, debug communication between components, understand the agent loop or streaming, or work with provider routing and the Gemini CORS proxy.
中文简介正在准备中。当前显示原文说明。
ScepticAgent packaging and Chrome Web Store publishing workflow. Use whenever the user wants to build the zip, package the extension, publish or submit to the Chrome Web Store, update the store listing, or deal with manifest/icon/permission requirements for publishing.
中文简介正在准备中。当前显示原文说明。
Searches multiple web sources, synthesizes findings, and produces cited research reports using delegated subagents. Use when the user asks to research a topic online, search the web, look something up, find current information, compare options, or produce a research report.
中文简介正在准备中。当前显示原文说明。
ScepticAgent UI and styles reference. Use whenever the user wants to change the side panel UI, modify highlight colours, update the markdown renderer, work with CSS architecture, add or change category colours, or understand how the sidepanel renders analysis output.
中文简介正在准备中。当前显示原文说明。
ScepticAgent AI prompt reference. Use whenever the user asks about the prompts, wants to change analysis behaviour, modify what the AI looks for, adjust highlight categories or scoring, understand what instructions are sent to the AI, or tune the output format of analysis or highlights.
中文简介正在准备中。当前显示原文说明。
OneClickVirt operations skill for managing containers, virtual machines, provider nodes, health checks, and metrics through MCP.
中文简介正在准备中。当前显示原文说明。
Drive a native GUI app (macOS, Windows, Linux) via the cua-driver CLI (default) or MCP server; snapshot its accessibility tree, act through snapshot-bound element tokens, native menu paths, exact window geometry, or pixel coordinates, and verify from fresh state. Use when the user asks you to operate, drive, automate, or perform a GUI task in a real application on the host.
中文简介正在准备中。当前显示原文说明。
Use when you need to visually interact with a GUI — test buttons, fill forms, verify visual layouts, fuzz web pages, automate user flows, take screenshots, or perform end-to-end QA on any application. Works on cloud VMs, Docker containers, local machines, and sandboxes. Install: pip install cua.
中文简介正在准备中。当前显示原文说明。
Build FastAPI endpoints in the layered router → service → Supabase pattern, with Pydantic v2 schemas, JWT/admin gating, and consistent HTTPException-based domain errors. Use when adding/modifying any endpoint under backend/.
中文简介正在准备中。当前显示原文说明。
pytest + httpx + TestClient patterns for the FastAPI backend. Dependency overrides for auth, FakeSupabase mocking, HTTPException assertions. Use when writing or reviewing backend/tests/test_*.py.
中文简介正在准备中。当前显示原文说明。
Drive Chrome via the claude-in-chrome MCP to exercise plan.md::Verify steps for a shipped feature. Loads deferred MCP tool schemas, asserts console/network cleanliness, records a GIF for the PR. Used by the browser-verifier agent.
中文简介正在准备中。当前显示原文说明。
Build pages and components in the Next.js 15 App Router (RSC by default, "use client" only when needed), Tailwind for styling, typed props, and the existing CartProvider for cart state. Use when creating or modifying pages, layouts, components, or forms in frontend/.
中文简介正在准备中。当前显示原文说明。
Integrate with the FastAPI backend through the typed wrapper in frontend/lib/api.ts, attach Supabase JWTs for admin calls, and handle errors via ApiError. Use when adding/modifying API calls or wiring auth.
中文简介正在准备中。当前显示原文说明。
Pre-PR code review checklist for this repo. Plan alignment, security gates, layering, dead code, API-surface completeness. Used by the code-reviewer agent.
中文简介正在准备中。当前显示原文说明。
Vitest + React Testing Library patterns for the Next.js 15 frontend. Co-located component tests, mocking lib/api.ts, testing Server Components, CartProvider harness. Use when writing or reviewing *.test.ts(x) files in frontend/.
中文简介正在准备中。当前显示原文说明。
Supabase Postgres + Storage + Auth operations from FastAPI — service-role client, RLS-aware queries, additive SQL migrations under backend/db/migrations, the create_order RPC, and the product-images bucket. Use when adding tables/columns, writing queries, calling RPCs, or working with Storage.
中文简介正在准备中。当前显示原文说明。
Orchestrate multi-agent swarms with agentic-flow for parallel task execution, dynamic topology, and intelligent coordination. Use when scaling beyond single agents, implementing complex workflows, or building distributed AI systems.
中文简介正在准备中。当前显示原文说明。