一键导入
lamina-design-process
Agent-native design loop — domain contract, external build, verify, iterate. Not human workshop ceremony.
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。
菜单
Agent-native design loop — domain contract, external build, verify, iterate. Not human workshop ceremony.
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
Product design workflows — domain contracts, implement brief, verify loop. Load via Read or Skill tool when /lamina-* workflows need it.
Use only when explicitly invoked as lamina-design. Also matches /lamina-design and $lamina-design. Turn a product idea or brownfield change into a ready_to_build contract under .lamina/runs (run.json + implement.md). Prefer scripts/seed-ready-run.mjs for concrete feature briefs. Vague briefs must clarify-and-STOP before any seed.
Use only when explicitly invoked as lamina. Also handles /lamina-design, /lamina-verify, and /lamina-init. Route product design for developers building with AI — design, verify, init, or direct capability answers. For /lamina-design seed via seed-ready-run.mjs; for /lamina-verify seed via seed-verify-run.mjs.
Use only when explicitly invoked as lamina-verify. Verify a live or brownfield product against its product graph: critical promises, reachable workflows, authority, invariants, state integrity, recovery, accessibility, and contract drift; emit evidence-backed fixes before merge. Vague “audit our app” briefs must clarify-and-STOP before any seed.
Product design skill for developers who build with AI coding agents. Use when you need to know what to build before prompting your agent — domain model, workflows, edge cases, product states, and UX gaps handled upfront. Works alongside Cursor, Claude Code, Codex, Gemini, Pi. Any stack, any UI library. Do NOT use for visual styling, pixel layouts, or writing app source.
Use only when explicitly invoked as lamina-init. Turn an incomplete product idea into usable business context and evidence-grounded personas, asking only high-leverage questions and labeling provisional assumptions for later product-graph design.
| name | lamina-design-process |
| description | Agent-native design loop — domain contract, external build, verify, iterate. Not human workshop ceremony. |
| metadata | {"lamina":{"id":"design-process","problems":["design workflow for agents","iterate after verify"],"related":["lamina-design","lamina-verify","lamina-evolutionary-rules"]}} |
The loop for coding agents: design contract → implement (external) → verify → fix.md → re-verify.
/lamina-init — domain charter/lamina-design — run.json + implement.md at ready_to_build/lamina-verify — actor walks, invariants, a11y → findings[] + fix.mdfix.md/lamina-verify on updated build/lamina-design delta (prompts in fix.md); re-verify