ANWS

当用户在 skills-only 环境中需要判断应该从哪个 anws 工作流开始，或需要在 forge / change / genesis / probe / blueprint / challenge / upgrade 之间路由时使用。它是 anws 工作流集合的导航入口。

纯静态「契约忠实度 / 实现侧证据」审查：对照 PRD、ADR、系统设计、05A_TASKS 与 05B_VERIFICATION_PLAN，围绕契约闭合、任务兑现、架构健康、安全边界、验证证据与回流一致性产出可追溯结论；供 /challenge（CODE/FULL）与 /forge（Step 3 §3.6 波末）共用。

当用户需求模糊、术语不清晰时使用。通过交互式追问澄清领域概念，提取实体、流程与暗物质（missing_components）。由 **`/genesis` Step 1** 在 Step 0 已确定 `TARGET_DIR = .anws/v{N}` 后调用；与 **同工作区 `/genesis`** 连用。

执行 /craft 时必读。提供 Workflow / Skill / Prompt 骨架与质量护栏。以判断准绳替代堆砌步骤。

当 `/challenge` 需要设计侧规范契约闭合证据（架构与系统设计文档三维审查）时加载；产出可锚点、按严重度分级的发现供纳入 07_CHALLENGE_REPORT，不作脱离 challenge 上下文的终局裁决。

规定面向真人的 E2E / 手动验证《测试指南》与《E2E Verification》报告骨架（PRD 可追溯、人机走查顺序、评测列仅能 PASS/PARTIAL_PASS/FAIL）；**不含实机浏览器编排**——先后顺序与回填义务由宿主 **`/forge` §3.7**（及 `/forge` 对应条文）统一写死。

Generate a persistent .nexus-map/ knowledge base that lets any AI session instantly understand a codebase's architecture, systems, dependencies, and change hotspots. Use when starting work on an unfamiliar repository, onboarding with AI-assisted context, preparing for a major refactoring initiative, or enabling reliable cold-start AI sessions across a team. Produces INDEX.md, systems.md, concept_model.json, git_forensics.md and more. Requires shell execution and Python 3.10+. For ad-hoc file queries or instant impact analysis during active development, use nexus-query instead.

Precise, instant code structure queries for active development — answer 'who depends on this interface before I refactor it', 'how many modules break if I change this', 'what is the real impact radius of this feature change', 'which module is the true high-coupling hotspot in this legacy codebase'. Essential before any interface change, continuous refactoring task, sprint work estimation, or when navigating unfamiliar or large legacy codebases. Requires Python 3.10+ and shell. Use nexus-mapper instead when building a full .nexus-map/ knowledge base.

当 `/probe` 需要识别运行时入口、进程边界、spawn 链、IPC 通道、协议强度与生命周期风险时加载。只做静态/可观察探测，不修改代码。

genesis Step 2：将模糊或高层需求转化为严格的产品需求文档（PRD）；含 craft 脚手架、PRD spec 契约、可选子代理分片编排与 Step 完成信号。适用于需求含糊、范围过大或表达停留在概念层的场景。

`/genesis` Step 4 专用：识别独立系统、定义边界与依赖，产出 `.anws/v{N}/02_ARCHITECTURE_OVERVIEW.md`（含源码根目录与物理结构）；为 Step 5 ADR 与后续 `references/rfc_template.md` 级契约提供输入，本人不写入 `03_ADR/*.md`。

当 `/design-system <system-id>` 需要为单个系统生成 L0/L1 详细设计文档时加载。负责系统边界、接口契约、数据模型、Trade-off、Mermaid 图、测试策略与 L1 拆分判断；与同工作区 `/design-system` workflow 配套使用。

使用 WBS 将系统设计文档分解为执行主清单（05A_TASKS.md）与验证计划（05B_VERIFICATION_PLAN.md），支持依赖分析、验证追溯与证据定义。

系统性审查 05A_TASKS.md 与 05B_VERIFICATION_PLAN.md，作为 `/challenge` 工作流的任务契约与验证契约证据层；7 Pass（A→G）、四语义模型、发现上限与跨文档门禁不变，落盘叙述遵循 output-contract 与本 SKILL 专属门禁。

服务于 `/genesis` Step 3「技术选型」：以 ATAM 与 12 维加权矩阵评估候选栈，产出可追溯的对比结论与 ADR 升格素材；不写正式 ADR 文件（落盘在 Step 5）。优先读本 SKILL 旁 `references/`。

Use when users in a skills-only environment need to decide which anws workflow to start from, or need routing among forge / change / genesis / probe / blueprint / challenge / upgrade. It is the navigation entry for the anws workflow set.

Pure static "contract fidelity / implementation-side evidence" review: Against PRD, ADR, system design, 05A_TASKS, and 05B_VERIFICATION_PLAN, produce traceable conclusions on contract closure, task fulfillment, architecture health, security boundaries, verification evidence, and backflow consistency; shared by /challenge (CODE/FULL) and /forge (Step 3 §3.6 end-of-wave).

Use when user needs are vague or terminology is unclear. Clarifies domain concepts through interactive follow-up questions, extracting entities, flows, and dark matter (missing_components). Invoked by **`/genesis` Step 1** after Step 0 has set `TARGET_DIR = .anws/v{N}`; use with **`/genesis`** in the same workspace.

Required when running /craft. Provides Workflow / Skill / Prompt scaffolds and quality guardrails using judgment-driven criteria.

Load when `/challenge` needs design-side contract-closure evidence (three-dimensional architecture and system-design doc review); deliver anchorable, severity-graded findings for inclusion in 07_CHALLENGE_REPORT—not final rulings outside challenge context.

Specifies the human-facing E2E / manual verification *Testing Guide* and *E2E Verification* report skeleton (PRD traceability, human walk-through order, verdict columns may only be PASS/PARTIAL_PASS/FAIL); **does not include real-browser orchestration**—order of operations and backfill obligations are fixed by the host **`/forge` §3.7** (per `/forge` wording).

Generate a persistent .nexus-map/ knowledge base that lets any AI session instantly understand a codebase's architecture, systems, dependencies, and change hotspots. Use when starting work on an unfamiliar repository, onboarding with AI-assisted context, preparing for a major refactoring initiative, or enabling reliable cold-start AI sessions across a team. Produces INDEX.md, systems.md, concept_model.json, git_forensics.md and more. Requires shell execution and Python 3.10+. For ad-hoc file queries or instant impact analysis during active development, use nexus-query instead.

Precise, instant code structure queries for active development — answer 'who depends on this interface before I refactor it', 'how many modules break if I change this', 'what is the real impact radius of this feature change', 'which module is the true high-coupling hotspot in this legacy codebase'. Essential before any interface change, continuous refactoring task, sprint work estimation, or when navigating unfamiliar or large legacy codebases. Requires Python 3.10+ and shell. Use nexus-mapper instead when building a full .nexus-map/ knowledge base.

Load when `/probe` needs to identify runtime entrypoints, process boundaries, spawn chains, IPC channels, protocol strength, and lifecycle risks. Observes and reports only; does not modify code.

genesis Step 2: turn fuzzy or high-level needs into strict product requirement documents (PRDs); includes craft scaffolding, PRD spec contract, optional sub-agent shard orchestration, and Step completion signals. Use when requirements are vague, scope is too large, or expression stays conceptual.

Dedicated to `/genesis` Step 4: identify independent systems, define boundaries and dependencies, produce `.anws/v{N}/02_ARCHITECTURE_OVERVIEW.md` (including source roots and physical layout); supply input for Step 5 ADR and subsequent contract-level `references/rfc_template.md`; this skill does **not** write `03_ADR/*.md`.

Load when `/design-system <system-id>` needs to produce L0/L1 detailed design documents for one system. Defines boundaries, interface contracts, data models, trade-offs, Mermaid diagrams, testing strategy, and L1 split rules; paired with the same-bundle `/design-system` workflow.

Systematically reviews 05A_TASKS.md and 05B_VERIFICATION_PLAN.md as the task-contract and verification-contract evidence layer for the `/challenge` workflow; 7 passes (A→G), four semantic models, finding cap, and cross-document gates are unchanged; on-disk narration follows output-contract plus this skill's gates.

Serves `/genesis` Step 3 "Technical selection": evaluates candidate stacks with ATAM and a 12-dimension weighted matrix, producing traceable comparison conclusions and ADR promotion material; does not author formal ADR files (persisted in Step 5). Prefer `references/` beside this SKILL.

当在本模板 bundle 内需持久化报告、并行子会话、或与多工作流产出对齐时使用。收录共用落盘 spec 与委派闭环；与 craft-authoring（/craft 撰写脚手架）无关。

当复杂问题需要系统性逐步推理时使用。适用于多阶段分析、设计规划、问题分解，或初始范围不明确且需要受控收敛的任务。

Load when persisting reports in this template bundle, running parallel child sessions, or aligning outputs across workflows. Holds shared on-disk spec and delegation loop; unrelated to craft-authoring (/craft scaffolds).

Use when complex problems require systematic step-by-step reasoning. Suitable for multi-stage analysis, design planning, problem decomposition, or tasks with unclear initial scope that require controlled convergence.

Use WBS to decompose system design into an execution list (05A_TASKS.md) and a verification plan (05B_VERIFICATION_PLAN.md), with dependency analysis, traceability, and evidence ownership.