发现 文档写作 相关 Skills，比较来源仓库和用途，查看适合你工作流的技能说明。
Essential framework for creating solid Veo 3 prompts. Use when constructing video prompts, validating prompt completeness, or teaching prompt structure. Defines 8 mandatory components (Subject, Setting, Action,...
Strategy for creating efficient short-form video prompts. Use when creating filler shots, atmospheric scenes, or quick video clips that don't require full Production Brief methodology. Covers when to go short v...
Prepare detailed, professional prompts for Google Imagen 3/4 image generation. Supports character, environment, and object prompts using natural language with technical photography specifications. Extensible su...
Production Brief methodology for complex Veo 3 video scenes. Use when creating scenes with dialogue, character continuity, structured settings, or multi-beat sequences. Provides 11-block framework (Format & Ton...
Manage git worktrees with shell scripts for listing, creating, and deleting worktrees. Use when working with git repositories and need to create worktrees with new branches, delete existing worktrees, or view a...
TEST PHASE: Testing strategies, patterns, and quality assurance workflows. Provides test strategy frameworks, coverage guidelines, unit/integration/e2e patterns, performance testing approaches, and security te...
CODE PHASE (Frontend): Client-side implementation patterns and best practices. Provides component architecture patterns, state management strategies, accessibility guidelines, performance optimization, and res...
ARCHITECT PHASE: Architectural design patterns, component templates, and system design guidance. Provides proven architectural patterns including microservices, layered architecture, event-driven systems, C4 d...
CODE PHASE (Database): Data layer implementation patterns and best practices. Provides schema design patterns, query optimization strategies, indexing guidelines, data integrity constraints, migration patterns...
CROSS-CUTTING: API contract design patterns for architects and implementers. Provides REST API design patterns, GraphQL schema design, API versioning strategies, error response formats, pagination patterns, an...
CODE PHASE (Backend): Server-side implementation patterns and best practices. Provides service layer patterns, API implementation guidance, error handling strategies, data validation approaches, middleware pat...
CROSS-CUTTING: Security patterns and best practices for ALL PACT phases. Provides OWASP Top 10 guidance, authentication/authorization patterns, input validation, secure coding practices, secrets management, an...
PREPARE PHASE: Research methodologies and documentation gathering workflows. Provides systematic research approaches, source evaluation criteria, documentation templates, API exploration techniques, and techno...
Record project activity, decisions, and outputs; query history and status. Provides institutional memory across sessions.
Create, organize, and prioritize tasks from briefs or brain dumps. Sync with Taskmaster MCP. Use to plan work, track status, and pick next steps.
Orchestrate project work: detect intent, run ADD checkpoints, and coordinate project-brief, task-engine, delegation-advisor, and project-logger.
Recommend who should do a task (Claude Code, Gemini, ChatGPT, Human, Taskmaster, MCPs) and generate handoff prompts.
Turn ideas/brain dumps into a structured project brief (problem, goals, scope, milestones, success criteria). Use when starting a project.
Integrate OpenAI Agent SDK with Google Gemini backend into FastAPI service using the official Google Gemini API via OpenAI compatibility layer.
Integrates Better Auth client with ChatKit UI or custom Next/Vite UI. Adds login/logout buttons, protected routes, session hooks.
Add selection-based Q&A functionality to ChatKit UI allowing users to ask about highlighted text with proper integration.
Generate the full production Dockerfile for the backend with multi-stage build, proper dependencies, and Hugging Face Spaces compatibility.
Generates Drizzle ORM schema files for users, sessions, tokens, OAuth accounts, and audit logs. Syncs schema to Neon Postgres.
Generate the complete RAG ingestion script to crawl textbook from sitemap.xml, chunk content, embed using Gemini, and push to Qdrant following MCP documentation.
默认按已收录数据中的 GitHub 仓库 Stars 排序。Stars 属于来源仓库，同一仓库的多个技能可能共享相同数值；它反映仓库关注度，不代表单个技能的安装量或质量评分。