hap-as-database
**立即触发条件**：用户提到"搭建网站"、"企业官网"、"HAP 作为数据库"、"前后端分离"、"内容管理系统"、"HAP 网站"、"HAP 后台"、"数据展示平台"。提供完整的 HAP + 前端项目搭建指导，使用 HAP 作为后台内容管理系统。
hap-frontend-project
**立即触发条件**：用户提到"HAP 搭建网站"、"HAP 前端项目"、"HAP 作为数据库"、"企业官网"、"官网"、"通过 HAP 搭建"、"用 HAP 做网站"、"HAP 网站"、"搭建官网"、"前后端分离"、"内容管理系统"、"HAP 前端"、"HAP 官网"。提供完整的 HAP + 前端项目搭建指南，包括 HAP 后台配置、前端项目结构、API 集成和数据渲染。
hap-mcp-usage
明道云 HAP MCP 自动化配置技能。**立即触发条件**：用户提到"配置 MCP"、"添加 MCP"、"MCP 配置"、"MCP 连接"、"设置 MCP"、提供包含"hap-mcp-"的配置、提供包含"HAP-Appkey"和"HAP-Sign"的 URL。支持 9 种 AI 工具的自动化配置，配置完成后自动验证连通性。
hap-skills-updater
HAP Skills Collection 技能更新和维护技能。当用户提到"更新技能"、"维护技能"、"更新 hap-skills"、"更新 skill"等需求时使用。帮助用户更新和维护 HAP Skills Collection 中的 4 个核心技能。
hap-v3-api
使用明道云 HAP V3 接口搭建页面和操作数据的专业技能。**立即触发条件**：用户提到"HAP V3"、"HAP API"、"接口调用"、"数据接口"、"Appkey"、"Sign"、"接口鉴权"、"Filter 筛选"、"查询数据"、"创建记录"。提供完整的 API 使用指南：鉴权配置、接口调用、筛选器使用、数据操作等。如果用户已配置 HAP MCP，AI 应该自动从 MCP 配置中提取鉴权密钥。
hap-view-plugin
创建和开发明道云 HAP 自定义视图插件的技能。**立即触发条件**：用户提到"HAP 视图插件"、"自定义视图"、"mdye"、"视图开发"、"插件开发"、"初始化视图项目"、"启动视图调试"。提供完整的开发工作流程、API 使用指南和最佳实践。
skill-creator
Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.
pptx
Presentation creation, editing, and analysis. When Claude needs to work with presentations (.pptx files) for: (1) Creating new presentations, (2) Modifying or editing content, (3) Working with layouts, (4) Adding comments or speaker notes, or any other presentation tasks
social-media-automation
自媒体运营自动化技能，支持小红书、抖音、微信公众号、视频号等平台的内容生成、图片生成、数据管理和自动化发布。包含 Tavily API 搜索、内容生成、图片生成、HAP 数据管理和自动化发布等完整流程。新增每日热点内容推荐功能。图片生成支持并行生成、自动下载、自动跳过已存在图片等优化功能。强制要求从 HAP "账号人设" 表读取账号人设配置，禁止使用本地文件。
wechat-article-writer
公众号文章自动化写作流程。支持资料搜索、文章撰写、爆款标题生成、排版优化。当用户提到写公众号、微信文章、自媒体写作、爆款文章、内容创作时使用此 skill。
list-global-npm
Lists the global npm packages installed. Use this when asked to list global npm packages or "list global npm" or "list g packages"
skill-search
Use when working with ANY external library, framework, tool, or API. Use when starting a project, adding dependencies, debugging unfamiliar code, or when user mentions technologies like React, Next.js, PostgreSQL, AWS, Docker, etc. Be generous - if there might be a skill, search for it.
code-review-executor
This skill should be used when the user asks to "review code", "do a code review", "review my branch", "review MR !1234", "review PR #567", "review feature/auth branch", "review feature/auth vs dev", "check code quality", "manage review skills config", "update review skills", "discover review skills", or wants to execute code review using configured skill presets.
llm-api-benchmark
This skill should be used when the user asks to "benchmark LLM API", "test API speed", "measure response time", "check API latency", "test TPS", "benchmark endpoint", "compare endpoint performance", "测试端点性能", "基准测试", "测试LLM速度", or needs to evaluate LLM API performance metrics (TTFT, TPS, latency).
webnovel-dashboard
启动可视化小说管理面板（只读 Web Dashboard），实时查看项目状态、实体图谱与章节内容。
webnovel-init
深度初始化网文项目。通过分阶段交互收集完整创作信息，生成可直接进入规划与写作的项目骨架与约束文件。
webnovel-learn
从当前会话提取成功模式并写入 project_memory.json
webnovel-plan
Builds volume and chapter outlines from the total outline, inherits creative constraints, and prepares writing-ready chapter plans. Use when the user asks for outlining or runs /webnovel-plan.
webnovel-query
Queries project settings for characters, powers, factions, items, and foreshadowing. Supports urgency analysis and golden finger status. Activates when user asks about story elements or /webnovel-query.
webnovel-resume
Recovers interrupted webnovel tasks with precise workflow state tracking. Detects interruption point and provides safe recovery options. Activates when user wants to resume or /webnovel-resume.
webnovel-review
Reviews chapter quality with checker agents and generates reports. Use when the user asks for a chapter review or runs /webnovel-review.
webnovel-write
Writes webnovel chapters (default 2000-2500 words). Use when the user asks to write a chapter or runs /webnovel-write. Runs context, drafting, review, polish, and data extraction.
auditing-bdd-tests
Analyzes BDD (Gherkin) + Playwright test solutions. Produces aspect scoring (0/5/10), A–F grade, issues by severity, and Markdown + HTML report formats for deep test-solution analysis.
skills-guide
Comprehensive guide for discovering, understanding, and installing Claude Code skills from skills.sh marketplace. Use this skill when users want to (1) browse or search skills.sh for recommendations, (2) get skill recommendations by role (developer, marketer, designer, product manager), (3) understand how a specific installed skill works by reading and explaining its SKILL.md, (4) learn the anatomy and structure of skills, or (5) find and install skills that match their specific workflow needs. This is NOT for creating new skills (use skill-creator instead).
code-review
Conducts comprehensive code reviews identifying poor practices, inefficiencies, potential bugs, security vulnerabilities, and provides recommendations for making code DRYer and more maintainable. Use when reviewing files, PRs, or code quality.
expo-audio
Guide for using expo-audio to implement audio playback and recording in React Native apps. Apply when working with audio features, sound playback, recording, or text-to-speech functionality.
expo-glass-effect
Guide for using expo-glass-effect to create iOS native liquid glass UI effects. Apply when implementing glass effect UI components, cards, or surfaces on iOS.
expo-router
Patterns for Expo Router including Stack configuration, native tabs, and file-based routing best practices. Apply when working with navigation, routing, or screen configuration.
gemini-api
Patterns for using Google Gemini API with structured output, JSON mode, and proper configuration. Apply when implementing AI features, text generation, or working with Gemini models.
rn-button-component
Ensures buttons use the unified Button component with proper state management, icon support, and glass effect integration. Apply when creating or modifying buttons in the app.
spaced-repetition
This document describes the translation-based spaced repetition system, its data model, and study flow.
watermelondb
WatermelonDB models, observation patterns, and React integration. Use when writing or debugging model code, observers (findAndObserve, query.observe), or screens that display live-updating DB data.
zod-v4-patterns
Ensures Zod v4 patterns are used correctly throughout the codebase. Apply when creating or modifying validation schemas, form schemas, or any Zod validators. Enforces v4 syntax and prevents deprecated v3 patterns.
analyzing-source
Conducts in-depth analysis of a specific source or topic, producing comprehensive summaries for research synthesis. Use when you need detailed analysis and documentation of individual sources as part of a larger research effort.
correcting-mistakes
Self-corrects skill and command instructions after resolving errors. Use when Claude errors during skill/command execution and finds a solution, or when user indicates a mistake was made. Finds the relevant instruction file and applies succinct fixes.
creating-skills
Creates high-quality Claude skills following official best practices. Use when the user asks to create a new skill, improve an existing skill, or needs guidance on skill authoring. Includes proper structure, naming conventions, progressive disclosure patterns, and quality validation.
pdf-to-video
Use when user wants to convert a PDF document into a showcase video, extract key points from PDF, or create video presentation from PDF file
effect-ts
Effect-TS (Effect) guidance for TypeScript. Use when building, refactoring, reviewing, or explaining Effect code, especially for: typed error modeling (expected errors vs defects), Context/Layer/Effect.Service dependency wiring, Scope/resource lifecycles, runtime execution boundaries, schema-based decoding, concurrency/scheduling/streams, @effect/platform APIs, Effect AI workflows, and Promise/async migration.
effect-v4
Effect v4 (beta) development and v3 → v4 migration guidance. Use when building new Effect v4 code or upgrading from v3, including API renames, behavior changes, before/after examples, and v4-specific patterns for services, layers, generators, yieldable, error handling, and schema codecs.
faion-sdd
SDD workflow: specs, designs, implementation plans, quality gates.
faion-seo-manager
SEO: on-page, off-page, technical optimization for organic visibility.
faion-product-manager
Product orchestrator: planning (MVP, roadmaps) and operations (prioritization, backlog).
faion-product-operations
Product operations: prioritization (RICE, MoSCoW), backlog, analytics, feedback.
faion-product-planning
Product planning: MVP/MLP scoping, roadmaps, user story mapping, OKRs.
faion-project-manager
PM orchestrator: coordinates agile and traditional PM approaches.
faion-python-developer
Python development: Django, FastAPI, async patterns, testing, type hints.
faion-rag-engineer
RAG engineering: embeddings, chunking, vector databases, hybrid search, reranking.
faion-researcher
Research: idea generation, market research, competitors, personas, pricing, validation.
faion-sdd-execution
SDD execution: quality gates, reflexion learning, pattern/mistake memory, code review.
faion-sdd-planning
SDD planning: specifications, design docs, implementation plans, task creation.
Page 362 of 1446 · 72270 results