菜单
Use when implementing a feature with clear, well-understood requirements. Quick planning via architect agent, then parallel agent development, then browser testing. Faster than craft — use when requirements don't need deep exploration.
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
| name | implement |
| description | Use when implementing a feature with clear, well-understood requirements. Quick planning via architect agent, then parallel agent development, then browser testing. Faster than craft — use when requirements don't need deep exploration. |
Fast end-to-end implementation pipeline. Quick planning, then development, then testing.
Pipeline: Architect → Develop → Browser Test → Report
The user input is: $ARGUMENTS
Prompt File Number (e.g., 01, 07):
.claude/prompts/{number}*.mdDirect Prompt Text:
Empty Input:
craft-skills:architect with the requirementsIf the architect raises too many ambiguities, suggest switching to craft-skills:craft for deeper exploration.
After plan approval, invoke craft-skills:develop with the approved plan.
After a successful build, invoke craft-skills:browser-test.
Summarize:
| implement | craft | |
|---|---|---|
| Planning | Quick architect agent | Deep brainstorming + spec review |
| User involvement | Medium — plan review | High — design questions, approach selection |
| Best for | Clear requirements, well-understood scope | Complex domains, unclear requirements |
Use when the user needs to plan and architect a new feature before implementation begins. This includes analyzing requirements, asking clarifying questions, and creating a detailed implementation plan aligned with the project's architecture. Invoke BEFORE any coding work starts.
Use when implementation + verification are complete and the work needs to be integrated — commit, open a PR, merge, or clean up the branch. The final step of the craft pipeline (after develop/test/report). Works in the current checkout; no worktree assumption.
Use when starting a new feature that needs thorough design exploration. This is the most comprehensive workflow: collaborative brainstorming with the user, then planning, then parallel agent development, then browser testing. Use for complex features, unclear requirements, or when the user wants to explore approaches before committing.
Post-develop visual regression + design-contract audit. Starts the dev server, captures screenshots of changed UI routes, and dispatches a Haiku-vision agent to compare the result against .claude/aesthetic-direction.md and the feature's ux-brief.md. Flags regressions before browser-test runs. Escalates to Sonnet or Opus only when Haiku flags issues.
Use when an approved implementation plan exists and is ready to be executed. Initializes shared state, dispatches parallel developer agents, performs integration review, and runs full verification (lint, tsc, format, build).
Generate or refresh .claude/reuse-index.md — a one-page inventory of the project's shared utilities, enums, hooks, and components that downstream implementer agents must consult before writing new code. Project-agnostic scan: no framework assumptions baked in. Invoke once per project (or when the shared surface changes meaningfully).