菜单
Map a product into Pages/Database/Auth/API/Integrations blocks using the LEGO framework, then write the results into PRD.md's Data model and Integrations sections. Use after /founding-prompt and before first prototyping, and again whenever a major feature changes the data model.
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
Run the SHIP checklist (Stable, Hidden secrets, Inputs validated, Performance) immediately before every deploy, using the agent's own tools directly. Use right before any git push to a branch that auto-deploys, after /verify-path and /security-audit have already passed.
Run a short retrospective right after a feature actually ships (post /ship-checklist Green, post-deploy) — capture what worked, what didn't, and any surprise, then feed genuine lessons forward into PRD.md's non-goals or behavior rules. Use once per shipped feature/milestone, not on a calendar cadence (that's /weekly-plan's reconciliation step).
Orient a founder who has never used an AI coding agent (Claude Code, OpenCode, or Codex CLI) before to how the *tool* works, before anything about their product idea comes up. Use this first, before /validate-demand, whenever the founder seems unfamiliar with AI coding agents generally — confused by terminal/CLI concepts, unsure what a "slash command" is, or asking how to talk to the agent at all.
Turn a rough product idea into a structured Founding Prompt using the BRIEF framework, then generate PRD.md, AGENTS.md, and llms.txt from it. Use this once demand is validated (after /validate-demand) and before any prototyping begins.
Reverse-engineer a PRD.md/AGENTS.md from a codebase that already exists (with no PRD, or one from another tool/convention), instead of eliciting from scratch. Use this instead of /validate-demand + /founding-prompt whenever a project already has code before founder-os is installed.
Commit in small, atomic "save points" (roughly one logical change each) during any non-trivial task, so a broken step is one git revert/reset away from a known-good state instead of losing a whole session's progress. Use during any multi-step build/fix/refactor, not just at the end.
| name | map-architecture |
| description | Map a product into Pages/Database/Auth/API/Integrations blocks using the LEGO framework, then write the results into PRD.md's Data model and Integrations sections. Use after /founding-prompt and before first prototyping, and again whenever a major feature changes the data model. |
The founder can't read an ERD or a system diagram. LEGO reframes architecture as blocks that snap together — Pages, Database, Auth, API, Integrations — producing one plain artifact any downstream agent invocation can read, instead of tribal knowledge in your head.
Walk the five LEGO blocks in conversation. Pages (what users see), Database (a spreadsheet in the cloud), Auth (the lock on the door), API (the messenger between rooms), Integrations (plug-ins) — ask what's needed for each, in plain terms, one block at a time.
Read PRD.md first, and re-run its quality gate
(node <founder-os-plugin-dir>/bin/lint-prd.js <project>/PRD.md) before
mapping anything — /founding-prompt runs this once at generation time,
but PRD.md may have been hand-edited since. Don't map architecture on
top of a PRD with unfilled placeholders or vague, non-WHEN/THEN behavior
rules; send the founder back to fix the specific gaps it names first.
The map must match already-committed core features and the non-goals
list — it doesn't get to invent new scope mid-mapping.
Draft the product map and read it back for confirmation before writing anything, using the LEGO shape: Pages / Data / Connections / User flow.
Write into PRD.md's ## Data model and ## Integrations sections
(the exact headers in templates/PRD.md.tpl) — don't fork a separate
architecture doc that can silently drift out of sync.
Cross-check integrations against reality. For each named
integration, confirm a real MCP server exists in .mcp.json or a plan
is stated in references/mcp-servers.md. Hand the actual connection
work to /integrate-service — this skill maps, it doesn't wire.
Flag Auth explicitly. It's the block founders skip most. Nail down "who can access what" concretely — e.g. row-level security — before any building starts, not after.
