菜单
Cost-optimized craft variant: Qwen3.6-35B-A3B handles implementation and reviews locally, Opus orchestrates, Sonnet as fallback. Requires LM Studio running. Targets ~45-60% API cost reduction vs base /craft.
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
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).
| name | craft-ace |
| description | Cost-optimized craft variant: Qwen3.6-35B-A3B handles implementation and reviews locally, Opus orchestrates, Sonnet as fallback. Requires LM Studio running. Targets ~45-60% API cost reduction vs base /craft. |
Full design-first pipeline with Qwen3.6 as the primary implementer and reviewer. Opus orchestrates and handles integration. Sonnet serves as fallback for tasks the local model can't handle.
Profile: claude+ace
Pipeline: Brainstorm -> Plan -> Develop -> Browser Test -> Report (same as /craft)
This wrapper writes a profile marker, then delegates to the canonical craft pipeline. The claude+ace profile triggers:
echo -n "claude+ace" > .craft-profile
Read skills/craft/SKILL.md from this plugin and follow every phase exactly as written. The profile gating in that file ensures:
llm-implement.sh instead of Claude agentsThe user input is: $ARGUMENTS
Pass the input through to the craft pipeline as if the user had invoked /craft directly.
${LLM_URL:-http://127.0.0.1:1234}| Activity | Savings vs /craft |
|---|---|
| Reviews (spec, plan, post-develop) | 100% (all local) |
| Data layer implementation (~40-50% LoC) | 100% (all local) |
| UI implementation (~30-40% LoC) | ~30-50% (Qwen3.6 first, Sonnet fallback) |
| Integration (~10-20% LoC) | 0% (stays on Opus) |
| Total estimated savings | ~45-60% |