菜单
[Internal pipeline stage — run by /build (use --doc-only standalone for an ARB narrative); invoke directly only as a power user.] Generate system architecture, machine-readable schemas, and UI mockups. Spawns planner + generator concurrently.
默认使用会先检查来源的 Prompt；你也可以切换为直接命令，或下载本地副本。
决定是否安装前，请先阅读 SKILL.md，以及 SkillsMP 当前展示的配套文件。
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。
直接命令不会经过审查 Prompt；运行前请先检查来源。
npx skills add https://github.com/cwijayasundara/claude_harness_eng_v5 --skill design命令会保持在同一行。复制前请横向滚动并检查完整内容。
想先保存到本地？可下载 SkillsMP 当前能够提供的文件。
Code generation quality principles — TDD, typing, error handling, logging, API integration, LLM integration.
Use when creating or editing .claude/agents/*.md, .claude/skills/*/SKILL.md, or .claude/commands/* — apply docs/prompting-standards.md (trigger conditions, model-agnostic bodies, no reasoning-as-text, effort floors).
Autonomous build loop with Karpathy ratcheting, GAN evaluator, and session chaining. Iterates story groups until all features pass or stopping criteria met.
基于 SOC 职业分类
正在显示 SKILL.md
| name | design |
| description | [Internal pipeline stage — run by /build (use --doc-only standalone for an ARB narrative); invoke directly only as a power user.] Generate system architecture, machine-readable schemas, and UI mockups. Spawns planner + generator concurrently. |
| argument-hint | [--doc-only [path] | --delta --stories <dir> | --story <file> --amendment-id <id> | --baseline-recovery] |
| context | fork |
Ultracode tip: This is the most reasoning-heavy, divergent phase in the pipeline — exploring a wide space of architecture and schema alternatives. Run
/effort ultracodebefore invoking it so the design space is explored as a judge-panel of approaches, then drop back to/effort highbefore the execution phases (/auto,/implement).
This skill is an orchestrator index. Read only the reference file for the mode you are running.
| Mode / section | Read |
|---|---|
| Usage | references/mode-01-usage.md |
Doc-Only Mode (--doc-only) | references/mode-02-doc-only-mode-doc-only.md |
Delta Mode (--delta) | references/mode-03-delta-mode-delta.md |
Baseline Recovery Mode (--baseline-recovery) | references/mode-04-baseline-recovery-mode-baseline-recovery.md |
| Overview (full mode) | references/mode-05-overview-full-mode.md |
Prerequisites (full mode only — --doc-only has none) | references/mode-06-prerequisites-full-mode-only-doc-only-has-none.md |
| Step 0 — Brainstorm Architecture Direction | references/mode-07-step-0-brainstorm-architecture-direction.md |
| Step 0.5 — Clarify Load-Bearing Design Decisions | references/mode-08-step-0-5-clarify-load-bearing-design-decisions.md |
| Step 0.7 — Pre-Code Modularity Assessment | references/mode-09-step-0-7-pre-code-modularity-assessment.md |
| Step 1 — Spawn Two Agents Concurrently | references/mode-10-step-1-spawn-two-agents-concurrently.md |
| Machine-Readable Artifacts | references/mode-11-machine-readable-artifacts.md |
| Output | references/mode-12-output.md |
| Gate | references/mode-13-gate.md |
| Gotchas | references/mode-14-gotchas.md |
--doc-only, --delta, --baseline-recovery, default full).--doc-only.Full/delta modes still run trace-check.js, validate-canvas.js, vocabulary-check.js, modularity-pack.js, record-modularity-review.js, and contract-drift-gate.js where the mode file specifies them. Wiring tests scan this entry file and references/*.md as one corpus.