菜单
Use this skill when users need to scope an MVP, define minimum viable features, plan early product development, or determine what to build first. Activates for "what should my MVP include," "scope my MVP," "what to build first," or product scoping questions.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
OpenClaw Gateway setup, configuration, and best practices. Use when installing OpenClaw, configuring channels (WhatsApp/Telegram/Discord), setting up providers (OpenAI/Google/Anthropic), creating skills, managing the gateway daemon, or troubleshooting OpenClaw issues. Triggers on: openclaw, gateway, whatsapp channel, telegram bot, openclaw skill, openclaw config, openclaw install, openclaw cron, openclaw security.
Use when the user asks how to build with OpenAI products or APIs and needs up-to-date official documentation with citations, help choosing the latest model for a use case, or explicit GPT-5.4 upgrade and prompt-upgrade guidance; prioritize OpenAI docs MCP tools, use bundled references only as helper context, and restrict any fallback browsing to official OpenAI domains.
Use this skill for setting up vector similarity search with pgvector for AI/ML embeddings, RAG applications, or semantic search. **Trigger when user asks to:** - Store or search vector embeddings in PostgreSQL - Set up semantic search, similarity search, or nearest neighbor search - Create HNSW or IVFFlat indexes for vectors - Implement RAG (Retrieval Augmented Generation) with PostgreSQL - Optimize pgvector performance, recall, or memory usage - Use binary quantization for large vector datasets **Keywords:** pgvector, embeddings, semantic search, vector similarity, HNSW, IVFFlat, halfvec, cosine distance, nearest neighbor, RAG, LLM, AI search Covers: halfvec storage, HNSW index configuration (m, ef_construction, ef_search), quantization strategies, filtered search, bulk loading, and performance tuning. **This project:** We use OpenAI text-embedding-3-small (1536) and store as vector(1536) in knowledge_chunks. halfvec is an optional future optimization; apply this skill's tuning (ef_search, iterative_scan
Supabase pgvector setup, RAG pipeline, and vector search for StartupAI. Covers knowledge_chunks schema, HNSW/IVFFlat indexes, search_knowledge + hybrid_search_knowledge RPCs, embedding generation via OpenAI, Edge Function integration, and Gemini web search grounding. **Trigger when user asks to:** - Set up or modify vector search, embeddings, or knowledge base - Ingest documents into knowledge_chunks - Debug search quality or missing results - Tune HNSW parameters or search performance - Wire RAG into edge functions or AI chat - Use Google Search grounding or URL Context with Gemini **This project:** OpenAI text-embedding-3-small (1536 dims), stored in knowledge_chunks, HNSW index, search via search_knowledge() and hybrid_search_knowledge() RPCs.
pgvector - PostgreSQL extension for vector similarity search. Use for embedding storage, cosine similarity, IVFFlat indexes, and HNSW indexes.
Channel the strategic thinking of fastest-growing AI startup founders. Use when asked to analyze current state, brainstorm strategy, set OKRs, or create execution plans. Provides founder personas, strategic frameworks, and battle-tested patterns from Anthropic, OpenAI, Mistral, Scale AI, and others.
| name | mvp-architect |
| description | Use this skill when users need to scope an MVP, define minimum viable features, plan early product development, or determine what to build first. Activates for "what should my MVP include," "scope my MVP," "what to build first," or product scoping questions. |
| version | 1.0.0 |
| tags | ["business","hexa","mvp","product","scope","build","features"] |
| auto_activate | true |
Help indie founders scope the smallest possible product that validates their core hypothesis using Hexa's methodology. Get to market in 3 months or less.
Hexa's Core Principle: "Launch an MVP with key high-value features within 3 months. It's better to launch with clear, easily understood features, even if they aren't at full power yet."
We believe that [customer] has a problem with [pain point].
We believe that [solution] will solve this.
We will know we're right when [success metric].
For each feature ask:
Target: 3-5 features maximum.
Only build features that remained stable through ALL design partner feedback.
Before adding ANY feature:
If you HAD to launch in 2 weeks, what would you cut? Whatever you'd cut... cut it now. That's your real MVP.
idea-validator - Validate before scopingstartup-icp-definer - Define who you're building forfullstack-workspace-init - Set up codebasebrand-architect - Name and position productFor complete hypothesis framework, feature prioritization matrix, dry elements identification, screen mapping, technical architecture checklist, timeline templates, and output format, see: references/full-guide.md