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.
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
Autonomous build loop with Karpathy ratcheting, GAN evaluator, and session chaining. Iterates story groups until all features pass or stopping criteria met.
Change the behavior of existing code — story-driven by default, or --issue N for a GitHub bug fix. Test-first, full verification, code review.
Code generation quality principles — TDD, typing, error handling, logging, API integration, LLM integration.
Brownfield change route — take an existing-code feature request from intent to a reviewed PR, scaling from a single /change to an epic via /spec→/design→/auto. Linear-tracked, backed by a committed DeepWiki.
[Internal pipeline stage — run by /auto self-heal and /implement validation when lint/type error volume is high; invoke directly only as a power user.] Turn compiler/linter output into a sharded work queue; fix per package with optional adversarial review — no full monorepo suite mid-shard.
[Internal pipeline stage — run by /auto (follow with /gate); invoke directly only as a power user.] Generate production code and tests for a story group using agent teams for parallel execution.
| 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.