audit

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

stardust:audit

One URL in. One scored, evidence-bound audit out.

audit

looks at an existing website from three perspectives — design (brand tensions + concrete improvement opportunities), SEO/technical, and LLM/AI-search visibility — measures Core Web Vitals, and synthesizes everything into a seven-dimension scorecard plus a prioritized findings ledger that tells the owner what to improve to generate a better business outcome. The report is also the natural seed for a redesign: its findings feed

stardust:uplift

's improvements list and

stardust:direct

's Phase 2.5, and it closes with uplift-shaped redesign directions so "run

stardust:uplift

" is the obvious next step.

输入一个URL，输出一份带评分、有证据支撑的审计报告。

audit

从三大维度审视现有网站——设计（品牌张力+具体改进机会）、SEO/技术层面、LLM/AI搜索可见性——测量Core Web Vitals指标，并将所有信息整合为一份七维度评分卡，以及一份按优先级排序的问题清单，告知网站所有者需改进哪些方面以获得更好的业务成果。该报告也是网站重设计的天然基础：其发现结果可为

stardust:uplift

的改进列表和

stardust:direct

的2.5阶段提供输入，报告结尾还会给出符合uplift风格的重设计方向，因此“运行

stardust:uplift

”显然是下一步的最佳选择。

Opinionated defaults

预设规则（带主观倾向）

Multi-page by default —
```
stardust:extract <url> --cap 8
```
(home + seven IA pillars) unless
```
--single
```
or
```
--pages
```
overrides.
Non-interactive — the audit never asks questions. Every assumption it makes instead is recorded in
```
audit.json#assumptions
```
and stated in the report's executive summary.
Evidence-bound — every claim cites a measurement, a
```
T-*
```
tension id, a check result, or a screenshot observation. A claim with no citation does not ship.
No fabricated data — a measurement that could not be taken is reported as
```
not measured (<reason>)
```
, never estimated silently. An estimate, where reasoned, is labeled as one with its basis.
Graceful degradation, not failure — optional capabilities (refero, marketing-skills, modern-web-guidance, PageSpeed Insights) are probed once and their absence is recorded, never fatal. See § Degradation ladder.

默认多页面审计 —— 默认执行
```
stardust:extract <url> --cap 8
```
（首页+7个信息架构核心页面），除非使用
```
--single
```
或
```
--pages
```
参数覆盖。
非交互式 —— 审计过程中不会提问，所有假设都会记录在
```
audit.json#assumptions
```
中，并在报告的执行摘要中说明。
有证据支撑 —— 每一项结论都引用了测量数据、
```
T-*
```
张力ID、检查结果或截图观察结果。无引用的结论不会纳入最终报告。
无伪造数据 —— 无法获取的测量数据会标注为
```
not measured (<reason>)
```
，绝不会静默估算。若确需估算，必须明确标注并说明依据。
优雅降级而非失败 —— 可选功能（refero、marketing-skills、modern-web-guidance、PageSpeed Insights）仅探测一次，若不可用则记录下来，不会导致审计失败。详见§ 降级机制。

Inputs

输入参数

```
<url>
```
— required. The site to audit. A path narrows the crawl to that subtree (extract's semantics).
```
--pages <n>
```
— optional. Override the default 8-page extraction cap (passed through as
```
--cap <n>
```
).
```
--single
```
— optional. One-page audit of the given URL only. The cross-page checks (duplicate titles, sitemap coverage, CTA fragmentation across pages) then run on a single page and say so.
```
--deploy
```
— optional. After the report renders, publish
```
report.html
```
as a single self-contained page via the DA transport (
```
../deploy/da-deploy-protocol.md
```
: source PUT → preview → live) and print the delivered URL. Transport only — the report never goes through deploy's section→block conversion, which would decompose the self-contained file.
```
--benchmark
```
— optional. Force Phase 5 reference benchmarking: probe the refero MCP even when the earlier capability probe was slow or ambiguous. Without this flag Phase 5 fires only when the probe succeeds quickly.

There are no other flags. Everything else is derived from the captured surface or governed by the underlying skills' contracts.

```
<url>
```
— 必填。待审计的网站URL。若包含路径，则仅爬取该子路径（遵循extract的语义规则）。
```
--pages <n>
```
— 可选。覆盖默认的8页面提取上限（传递为
```
--cap <n>
```
参数）。
```
--single
```
— 可选。仅对给定URL进行单页面审计。此时跨页面检查（重复标题、站点地图覆盖范围、各页面CTA碎片化）仅针对单个页面执行，并会在报告中说明。
```
--deploy
```
— 可选。报告生成后，通过DA传输协议将
```
report.html
```
发布为独立页面（参考
```
../deploy/da-deploy-protocol.md
```
：源文件PUT → 预览 → 上线），并输出交付URL。仅负责传输，报告不会经过deploy的区块转换流程，以免破坏独立文件结构。
```
--benchmark
```
— 可选。强制执行第5阶段的参考基准测试：即使早期功能探测缓慢或结果模糊，仍会调用refero MCP。若无此标志，仅当探测快速成功时才会触发第5阶段。

无其他标志参数，所有其他配置均从捕获的页面内容推导，或由底层技能的协议决定。

Phase 0 — Setup

第0阶段 — 准备工作

Run the master skill's setup (
```
../stardust/SKILL.md
```
§ Setup) — with one audit-specific carve-out: impeccable absence is a degradation here, not the master setup's hard stop. When the dep check fails, record
```
impeccable: unavailable
```
in
```
audit.json#degradations
```
and continue — Phase 2 runs without the critique/audit arms (VISION pass + accessibility fold-in still fire) and Phase 6 skips the report render; the run ends at stop condition (b) after
```
audit.json
```
is written.
Extraction freshness check. If
```
stardust/current/
```
holds an extraction of the same origin less than 7 days old — origin from
```
stardust/state.json
```
(the site record extract stamped), recency from the newest
```
pages/<slug>.json#_provenance.fetchedAt
```
— reuse it and record
```
site.extraction.reused: true
```
. Otherwise invoke
```
stardust:extract <url> --cap 8
```
(or
```
--single
```
/
```
--pages <n>
```
per the inputs). Extract owns the crawl, the screenshots,
```
_brand-extraction.json
```
,
```
pages/<slug>.json
```
,
```
PRODUCT.md
```
/
```
DESIGN.md
```
, and
```
brand-review.html
```
with its Tensions section.
Probe optional capabilities once, recording each outcome in the degradation record (
```
audit.json#degradations
```
):
- ```
marketing-skills
```
  plugin (
```
seo-audit
```
  ,
```
ai-seo
```
  skills present?)
- ```
modern-web-guidance
```
  (
```
npx -y modern-web-guidance@latest search "<query>"
```
  responds?)
- refero MCP (attempt
```
mcp__refero__refero_search_styles
```
  ; treat a tool-not-found or timeout as unavailable)
- PageSpeed Insights API (network-reachable without a key?)
- rollout project (
```
stardust/rollout/rollout.json
```
  present?)

If extract fails entirely (site unreachable, bot-management block past the headed-Chrome fallback), stop and surface extract's error verbatim — there is nothing to audit. This is the only hard stop before synthesis; see § Stop conditions.

运行主技能的准备流程（参考
```
../stardust/SKILL.md
```
§ Setup）—— 针对审计有一项特殊例外：impeccable不可用时仅触发降级，而非主准备流程的强制终止。若依赖检查失败，在
```
audit.json#degradations
```
中记录
```
impeccable: unavailable
```
并继续——第2阶段将跳过评论/审计模块（仍会执行VISION扫描+无障碍功能整合），第6阶段跳过报告渲染；在写入
```
audit.json
```
后，触发停止条件(b)终止运行。
提取内容新鲜度检查。若
```
stardust/current/
```
中存在同一源站的提取内容，且时间不超过7天（源站信息来自
```
stardust/state.json
```
，新鲜度由最新的
```
pages/<slug>.json#_provenance.fetchedAt
```
决定）——则复用该内容，并记录
```
site.extraction.reused: true
```
。否则调用
```
stardust:extract <url> --cap 8
```
（或根据输入参数使用
```
--single
```
/
```
--pages <n>
```
）。Extract模块负责爬取、截图、生成
```
_brand-extraction.json
```
、
```
pages/<slug>.json
```
、
```
PRODUCT.md
```
/
```
DESIGN.md
```
，以及包含Tensions章节的
```
brand-review.html
```
。
一次性探测可选功能，将每个结果记录到降级记录中（
```
audit.json#degradations
```
）：
- ```
marketing-skills
```
  插件（是否存在
```
seo-audit
```
  、
```
ai-seo
```
  技能？）
- ```
modern-web-guidance
```
  （执行
```
npx -y modern-web-guidance@latest search "<query>"
```
  是否有响应？）
- refero MCP（尝试调用
```
mcp__refero__refero_search_styles
```
  ；若工具未找到或超时则标记为不可用）
- PageSpeed Insights API（无需密钥即可访问网络？）
- rollout项目（是否存在
```
stardust/rollout/rollout.json
```
  ？）

若extract完全失败（网站无法访问、结构无法解析、绕过有头Chrome fallback后仍被反爬虫拦截），则终止并直接输出extract的错误信息——无内容可审计。这是合成阶段前唯一的强制终止情况；详见§ 停止条件。

Procedure

执行流程

Phase 1 — Brand surface & tension analysis

第1阶段 — 品牌呈现与张力分析

Read

stardust/current/_brand-extraction.json

and

stardust/current/brand-review.html

§ Tensions surfaced (rule catalog in

../extract/reference/brand-review-template.md

§ Tensions). Every fired

T-*

tension is candidate evidence for a finding — carry the ids forward, do not re-derive the detections.

Compute the four brand-expression measurements the report needs. Each lands in

audit.json#measurements

with

status

method

per

reference/report-format.md

brandColorShare
— brand-color share of painted pixels on the captured home screenshot. Preferred method: Playwright pixel sampling (
```
method: "pixel-sample"
```
) — load the screenshot, sample a grid (e.g. every 8th pixel), classify each sample to the nearest palette entry within a tolerance, and divide brand-hue samples by painted (non-white/near-white) samples. When sampling is infeasible in the session, a reasoned estimate from the captured surfaces is allowed but must ship as
```
method: "surface-estimate"
```
with its basis — never presented as measured.
ctaFragmentation
— distinct CTA labels per equivalence bucket, aggregated from
```
pages/*.json#ctas[].label
```
(the same buckets that drive
```
T-cta-vocab
```
).
typeScale
— distinct heading sizes and scale kind/ratio from
```
_brand-extraction.json#type.scaleAudit
```
.
radiusSprawl
— distinct border-radius values with occurrence counts from
```
_brand-extraction.json#motifs.borderRadius
```
.

读取

stardust/current/_brand-extraction.json

和

stardust/current/brand-review.html

中的§ Tensions章节（规则目录参考

../extract/reference/brand-review-template.md

§ Tensions）。每个触发的

T-*

张力都是结论的候选证据——保留ID，无需重新推导检测结果。

计算报告所需的四项品牌呈现测量指标。每项指标都按

reference/report-format.md

的要求，以

status

method

的格式存入

audit.json#measurements

：

brandColorShare
—— 捕获的首页截图中品牌色像素占比。优先方法：Playwright像素采样（
```
method: "pixel-sample"
```
）——加载截图，按网格采样（例如每8个像素采样一次），将每个样本按容差分类到最近的调色板条目，然后用品牌色调样本数除以已绘制（非白色/近白色）样本数。若会话中无法执行采样，则允许从捕获的页面内容进行合理估算，但必须标记为
```
method: "surface-estimate"
```
并说明依据——绝不能伪装成实测数据。
ctaFragmentation
—— 按等效分组统计的不同CTA标签数量，从
```
pages/*.json#ctas[].label
```
聚合而来（与驱动
```
T-cta-vocab
```
的分组规则一致）。
typeScale
—— 从
```
_brand-extraction.json#type.scaleAudit
```
获取的不同标题尺寸及缩放类型/比例。
radiusSprawl
—— 从
```
_brand-extraction.json#motifs.borderRadius
```
获取的不同边框圆角值及其出现次数。

Phase 2 — Design & experience critique

第2阶段 — 设计与体验评论

Three passes over the captured home page (screenshot + live URL), folded into one set of design findings:

impeccable critique + audit. Invoke via the Skill tool using the delegation mechanic in
```
../prototype/SKILL.md
```
§ Invoking impeccable (
```
Skill { skill: "impeccable:impeccable", args: "critique <target>" }
```
, then
```
"audit <target>"
```
for the accessibility / responsive / performance passes). Normalize its findings into the audit's finding shape.
VISION pass. Study the captured screenshots directly (
```
stardust/current/assets/screenshots/<slug>.png
```
) and name what a design director would: dated patterns the field has moved past, hierarchy failures, missed opportunities the captured surface doesn't capitalize on. The claim discipline is absolute — every observation cites a measurement, a tension id, or a screenshot region ("
```
home.png
```
, hero: three equal-weight CTAs compete"). Adjectives without evidence do not become findings.
Accessibility fold-in. Contrast computed (WCAG ratios for the captured palette pairs in the roles they are actually used in), alt coverage from
```
pages/*.json#media.images
```
, landmark presence and heading order from
```
pages/*.json#landmarks
```
, content-free link labels (reuse
```
T-link-content-free
```
when fired).

对捕获的首页（截图+实时URL）进行三轮扫描，整合为一组设计结论：

impeccable评论+审计。通过Skill工具调用，使用
```
../prototype/SKILL.md
```
§ Invoking impeccable中的委托机制（
```
Skill { skill: "impeccable:impeccable", args: "critique <target>" }
```
，然后调用
```
"audit <target>"
```
执行无障碍/响应式/性能扫描）。将其结论标准化为审计的结论格式。
VISION扫描。直接分析捕获的截图（
```
stardust/current/assets/screenshots/<slug>.png
```
），站在设计总监的视角指出问题：行业已淘汰的陈旧模式、层级结构缺陷、页面未充分利用的潜在机会。结论必须严格遵循规范——每一项观察结果都要引用测量数据、张力ID或截图区域（例如“
```
home.png
```
，hero区域：三个权重相同的CTA相互竞争”）。无证据支撑的形容词不能成为结论。
无障碍功能整合。计算对比度（捕获调色板对在实际使用场景中的WCAG比率）、
```
pages/*.json#media.images
```
中的替代文本覆盖率、
```
pages/*.json#landmarks
```
中的地标存在性和标题顺序、无内容链接标签（触发时复用
```
T-link-content-free
```
）。

Phase 3 — SEO & technical

第3阶段 — SEO与技术层面

When the

marketing-skills

plugin is installed, follow

marketing-skills:seo-audit

's methodology and normalize its issue/impact/evidence/fix items into findings. When absent, run the checks directly — they are all curl/Playwright-derivable:

area	checks	method
Crawlability	`robots.txt` present and sane; sitemap declared and valid XML	curl
Indexation	canonical present and self-referential; `meta robots` not accidentally `noindex` ; http→https single-hop redirect; redirect chains	curl -I
Semantics	`main` / `nav` / `footer` landmarks; single `<h1>` ; heading hierarchy without skips	pages/*.json + Playwright
Metadata	title/description presence + quality per page; duplicates across pages; Open Graph completeness	pages/*.json#metadata
Structured data	JSON-LD presence, parse validity, entity types vs page type	Playwright / curl

Where a failure matches a

rollout:baseline

check id (

../rollout/reference/checks.md

single-h1

title-missing

meta-description

canonical

sitemap

jsonld

img-alt

landmark-main

duplicate-title

), reuse that id as the finding's

evidence.ref

(

check:<id>

) — findings recorded into a rollout ledger under a known id get picked up by the AEM autofix registry automatically.

Core Web Vitals. Measure LCP / CLS / TBT via Playwright performance APIs (

PerformanceObserver

for

largest-contentful-paint

and

layout-shift

longtask

entries for TBT) on two viewports: mobile (375×667, CPU throttled where the session supports it) and desktop (1440×900). When the PageSpeed Insights API is network-reachable without a key, prefer it and record

method: "psi-api"

(it adds field INP); otherwise record

method: "playwright-lab"

and say in the measurement note that lab TBT is a proxy for INP. Classify every metric against the Google thresholds tabled in

reference/scoring.md

§ performance.

Remediation guidance. When

modern-web-guidance

is installed, run

npx -y modern-web-guidance@latest search "<specific failure>"

for each distinct failure class and cite the returned guide ids in the finding's

guides[]

. When absent, write the generic remediation and leave

guides: []

若已安装

marketing-skills

插件，则遵循

marketing-skills:seo-audit

的方法，将其问题/影响/证据/修复项标准化为审计结论。若未安装，则直接执行以下检查——所有检查均可通过curl/Playwright实现：

领域	检查项	方法
可爬取性	`robots.txt` 存在且配置合理；站点地图已声明且为有效XML	curl
可索引性	canonical标签存在且指向自身； `meta robots` 未意外设置为 `noindex` ；http→https单次跳转；无跳转链	curl -I
语义化	`main` / `nav` / `footer` 地标；单个 `<h1>` 标签；标题层级无跳跃	pages/*.json + Playwright
元数据	每页标题/描述的存在性+质量；跨页面重复情况；Open Graph完整性	pages/*.json#metadata
结构化数据	JSON-LD存在性、解析有效性、实体类型与页面类型匹配	Playwright / curl

若失败项与

rollout:baseline

检查ID匹配（参考

../rollout/reference/checks.md

：

single-h1

、

title-missing

、

meta-description

、

canonical

、

sitemap

、

jsonld

、

img-alt

、

landmark-main

、

duplicate-title

）——复用该ID作为结论的

evidence.ref

（格式为

check:<id>

）——记录到rollout清单中的已知ID结论会被AEM自动修复注册表识别。

Core Web Vitals指标。通过Playwright性能API（使用

PerformanceObserver

监听

largest-contentful-paint

和

layout-shift

，通过

longtask

条目获取TBT）在两个视口测量LCP/CLS/TBT：移动端（375×667，会话支持时启用CPU节流）和桌面端（1440×900）。若无需密钥即可访问PageSpeed Insights API，则优先使用该API，并标记

method: "psi-api"

（它会增加真实用户环境的INP指标）；否则标记

method: "playwright-lab"

，并在测量说明中注明实验室环境的TBT是INP的替代指标。根据

reference/scoring.md

§ performance中列出的Google阈值对每个指标进行分类。

修复指导。若已安装

modern-web-guidance

，则针对每个不同的失败类别执行

npx -y modern-web-guidance@latest search "<specific failure>"

，并在结论的

guides[]

中引用返回的指南ID。若未安装，则编写通用修复建议，保留

guides: []

。

Phase 4 — LLM visibility

第4阶段 — LLM可见性

When

marketing-skills:ai-seo

is installed, follow its methodology. When absent, assess directly:

llms.txt
— present at the origin root?
Answerability — does each audited page answer the question a user would ask of it ("what does this cost", "what is this") in extractable, well-structured prose — and how early on the page?
schema.org coverage — do the JSON-LD entities cover the organization plus the page-type entities an answer engine needs for entity understanding?
Heading-as-question coverage — what share of
```
h2
```
/
```
h3
```
map to askable questions or scannable topics rather than slogans?
Content depth — extractable prose word counts on key pages; specific, citable claims vs thin marketing copy.
Key facts in crawlable text — are pricing, what-it-is, and who-it's-for stated in crawlable text, or locked in images and JS-rendered widgets?

Every Phase 4 finding names the concrete fix ("state the three price points in the pricing table as text; they currently render only inside the plan-card images"), not a category ("improve content").

若已安装

marketing-skills:ai-seo

，则遵循其方法。若未安装，则直接评估以下内容：

llms.txt
—— 是否存在于源站根目录？
可回答性 —— 每个被审计页面是否能用可提取、结构清晰的文本回答用户可能提出的问题（如“价格是多少”“这是什么”），且回答位置是否靠前？
schema.org覆盖范围 —— JSON-LD实体是否涵盖组织信息，以及回答引擎理解实体所需的页面类型实体？
标题对应问题的覆盖范围 ——
```
h2
```
/
```
h3
```
标题中有多少比例对应可提问的问题或可快速浏览的主题，而非口号？
内容深度 —— 关键页面的可提取文本字数；具体、可引用的声明 vs 空洞的营销文案。
关键信息是否在可爬取文本中 —— 价格、产品定义、目标用户等信息是否在可爬取文本中，还是被锁定在图片或JS渲染的组件中？

第4阶段的每一项结论都要明确具体的修复方案（例如“将定价表中的三个价格点以文本形式呈现；目前它们仅在套餐卡片图片内渲染”），而非笼统的类别（如“改进内容”）。

Phase 5 — Reference benchmarking (optional)

第5阶段 — 参考基准测试（可选）

Fires when the refero MCP tools are reachable — the Phase 0 probe attempted

mcp__refero__refero_search_styles

;

--benchmark

forces a re-probe. Skip gracefully when unavailable (

benchmarks: { status: "skipped", reason: … }

When available: retrieve 2–3 same-vertical reference styles, compare the audited site's brand expression (Phase 1 measurements) against what best-in-class in the category does, and cite each reference — title, URL, one line on what they do better — in the relevant design findings and in

audit.json#benchmarks.references

当refero MCP工具可访问时触发——第0阶段已尝试调用

mcp__refero__refero_search_styles

；

--benchmark

参数会强制重新探测。若不可用则优雅跳过（

benchmarks: { status: "skipped", reason: … }

）。

若可用：获取2-3个同行业参考样式，将被审计网站的品牌呈现（第1阶段的测量指标）与行业最佳实践进行对比，并在相关设计结论和

audit.json#benchmarks.references

中引用每个参考项——标题、URL、以及它们做得更好的一个要点。

Phase 6 — Synthesis & report

第6阶段 — 合成与报告

Scorecard. Score the seven dimensions per
```
reference/scoring.md
```
— anchors first, evidence floor enforced, not-measured dimensions nulled and renormalized. Compute the weighted overall.
Findings. Consolidate Phases 1–5 into the prioritized ledger: P1 (actively losing business or excluding users) / P2 (material drag) / P3 (polish). Per finding:
```
dimension
```
,
```
evidence
```
(measurement / tension / screenshot / check / benchmark citation),
```
businessImpact
```
one-liner, concrete
```
fix
```
,
```
guides[]
```
.
Uplift directions. Close with 2–3 redesign directions framed exactly like uplift's variant role contract (
```
../uplift/SKILL.md
```
§ The three-variant role contract): A faithful + fixes (names the findings it resolves), B one captured-but-underused trait amplified, C cinematic (motion as identity, register suggested per
```
../prototype/reference/motion-registers.md
```
§ Selection heuristic). Drop B when the captured surface can't support a differentiated middle — two strong directions beat three weak ones.
Write
stardust/audit/<domain-slug>/audit.json
— schema, slug convention, and measurement rules in
```
reference/report-format.md
```
Part 1. Provenance
```
_provenance
```
first key.
Render
stardust/audit/<domain-slug>/report.html
by delegating to
```
$impeccable craft
```
with the brief in
```
reference/report-format.md
```
Part 2 — the same Skill-tool mechanic as prototype, and the same rule: never hand-template the report. Run the post-render validation checklist; on failure re-invoke craft with the specific violation. Open the result with
```
open stardust/audit/<domain-slug>/report.html
```
.

Ledger recording (rollout projects only). When

stardust/rollout/rollout.json

exists, record each finding into the delivery ledger via

node skills/rollout/scripts/findings.mjs record

with source namespace

audit:

—

--source audit:<dimension>

--layer

from the mapping below, severity carried through,

--fixability

normalized per

../rollout/reference/audit-sources.md

§ Recording an external finding. Write each returned id into the finding's

ledgerId

audit dimension	ledger layer
`brand-expression`	`brand-tensions`
`visual-hierarchy-craft`	`design-ux`
`conversion-focus`	`content-conversion`
`accessibility`	`accessibility`
`technical-seo`	`seo` (site-wide: `cross-page` )
`content-llm-visibility`	`ai-search`
`performance`	`seo`

--deploy
. When passed, publish
```
report.html
```
via the DA transport per
```
../deploy/da-deploy-protocol.md
```
— PUT the file as a single source, POST preview, POST live, verify the delivered URL returns 200 — and print the delivered URL. Transport only; never run deploy's section→block conversion on the report.

Chat summary. Short — the work is on disk and openable:

audit complete — <url>

Site health: <overall>/100
  <dimension>: <score>   × 7 (not-measured dimensions listed with reasons)

Findings: <n> P1 · <n> P2 · <n> P3
Top lever: <the single highest-impact P1, one line>

Report: stardust/audit/<domain-slug>/report.html
Data:   stardust/audit/<domain-slug>/audit.json

Next: run stardust:uplift <url> — the report's closing directions
are its variant briefs.

评分卡。根据
```
reference/scoring.md
```
对七个维度进行评分——先确定锚点，严格遵循证据底线，未测量的维度设为null并重新归一化。计算加权总分。
结论清单。将第1-5阶段的内容整合为按优先级排序的清单：P1（直接导致业务损失或用户流失）/ P2（对业务有实质性拖累）/ P3（优化打磨）。每项结论包含：
```
dimension
```
、
```
evidence
```
（测量数据/张力ID/截图/检查项/基准测试引用）、
```
businessImpact
```
（一句话业务影响）、具体
```
fix
```
方案、
```
guides[]
```
。
Uplift重设计方向。结尾给出2-3个重设计方向，完全遵循uplift的变体角色协议（参考
```
../uplift/SKILL.md
```
§ The three-variant role contract）：A 忠实还原+修复（明确列出解决的结论）、B 强化一个已存在但未充分利用的特性、C 动态视觉化（以动效为核心标识，参考
```
../prototype/reference/motion-registers.md
```
§ Selection heuristic选择动效等级）。若捕获的页面内容无法支撑差异化的中间方案，则去掉B选项——两个有力的方向胜过三个薄弱的方向。
写入
stardust/audit/<domain-slug>/audit.json
—— 格式、命名规则和测量规则参考
```
reference/report-format.md
```
第1部分。
```
_provenance
```
作为第一个键。
渲染
stardust/audit/<domain-slug>/report.html
—— 通过委托给
```
$impeccable craft
```
工具完成，参考
```
reference/report-format.md
```
第2部分的要求——与prototype使用相同的Skill工具委托机制，且遵循同一规则：绝不手动模板化报告。执行渲染后验证清单；若失败则根据具体问题重新调用craft工具。使用
```
open stardust/audit/<domain-slug>/report.html
```
打开结果。

清单记录（仅rollout项目）。若存在

stardust/rollout/rollout.json

，则通过

node skills/rollout/scripts/findings.mjs record

将每项结论记录到交付清单中，源命名空间为

audit:

——

--source audit:<dimension>

、

--layer

对应下方映射，保留严重程度，

--fixability

根据

../rollout/reference/audit-sources.md

§ Recording an external finding进行标准化。将返回的每个ID写入结论的

ledgerId

。

审计维度	清单层级
`brand-expression`	`brand-tensions`
`visual-hierarchy-craft`	`design-ux`
`conversion-focus`	`content-conversion`
`accessibility`	`accessibility`
`technical-seo`	`seo` （全站范围： `cross-page` ）
`content-llm-visibility`	`ai-search`
`performance`	`seo`

--deploy
参数处理。若传入该参数，则根据
```
../deploy/da-deploy-protocol.md
```
通过DA传输协议发布
```
report.html
```
——将文件作为单个源PUT、POST预览、POST上线，验证交付URL返回200状态码——并输出交付URL。仅负责传输；绝不针对报告执行deploy的区块转换流程。

聊天摘要。简洁明了——成果已保存到本地并可打开：

audit complete — <url>

Site health: <overall>/100
  <dimension>: <score>   × 7（未测量维度会列出原因）

Findings: <n> P1 · <n> P2 · <n> P3
Top lever: <单个最高影响的P1结论，一句话>

Report: stardust/audit/<domain-slug>/report.html
Data:   stardust/audit/<domain-slug>/audit.json

Next: run stardust:uplift <url> — 报告结尾的方向即为其变体需求。

Degradation ladder

降级机制

Probed once in Phase 0; every degradation is recorded in

audit.json#degradations

and rendered in the report's methodology appendix. None of these stops the audit.

capability absent	behavior
refero MCP	skip Phase 5; `benchmarks.status: "skipped"` with reason
marketing-skills	run the Phase 3 / Phase 4 checks directly (tabled above)
modern-web-guidance	generic remediation text; `guides: []`
PageSpeed Insights	Playwright-only lab metrics; measurement note says lab TBT proxies INP
Playwright pixel sampling infeasible	`brandColorShare` ships as `method: "surface-estimate"` with basis
rollout project	no ledger recording; `ledgerId: null` on every finding

在第0阶段一次性探测；所有降级情况都记录在

audit.json#degradations

中，并在报告的方法附录中呈现。这些情况均不会终止审计。

缺失功能	行为
refero MCP	跳过第5阶段； `benchmarks.status: "skipped"` 并说明原因
marketing-skills	直接执行第3/4阶段的检查（如上文表格所示）
modern-web-guidance	使用通用修复文本； `guides: []`
PageSpeed Insights	仅使用Playwright实验室指标；测量说明中注明实验室TBT是INP的替代指标
Playwright像素采样不可行	`brandColorShare` 标记为 `method: "surface-estimate"` 并说明依据
rollout项目	不记录到清单；所有结论的 `ledgerId: null`

Hard constraints

硬性约束

No fabricated data. A measurement that could not be taken is
```
not measured (<reason>)
```
in both artifacts. Estimates are labeled with method + basis. This is the same discipline extract enforces against synthesis (
```
../extract/SKILL.md
```
§ Failure modes) — fabricated audit numbers are worse than missing ones because they are actionable-looking and wrong.
Evidence discipline. Every finding cites observable evidence: a measurement key, a
```
T-*
```
tension id, a screenshot region, a check id, or a benchmark URL. Uncited claims are cut in synthesis.
Report is craft-rendered.
```
report.html
```
is authored by
```
$impeccable craft
```
against the brief in
```
reference/report-format.md
```
, validated afterward — never hand-templated, never hand-patched.
Provenance is mandatory on both artifacts, per
```
../stardust/reference/artifact-map.md
```
§ Provenance shapes.
Non-interactive. No questions in normal flow; assumptions are stated in the report. The only stops are the two below.
Audit does not fix. Fixes belong to
```
uplift
```
(page redesign),
```
direct
```
Phase 2.5 (improvements list), and rollout's optimize loop (platform autofix). Audit names the fix; it never edits the site.

无伪造数据。无法获取的测量数据在两个工件中都标注为
```
not measured (<reason>)
```
。估算数据必须标记方法+依据。这与extract对合成的约束一致（参考
```
../extract/SKILL.md
```
§ Failure modes）——伪造的审计数据比缺失数据更糟，因为它们看起来可执行但实际错误。
证据规范。每一项结论都引用可观察的证据：测量数据键、
```
T-*
```
张力ID、截图区域、检查项ID或基准测试URL。无引用的结论在合成阶段会被剔除。
报告由craft工具渲染。
```
report.html
```
由
```
$impeccable craft
```
工具根据
```
reference/report-format.md
```
的要求生成，生成后会进行验证——绝不手动模板化、绝不手动修补。
必须包含溯源信息。两个工件都需遵循
```
../stardust/reference/artifact-map.md
```
§ Provenance shapes的要求。
非交互式。正常流程中不会提问；假设会在报告中说明。仅以下两种情况会终止审计。
审计不执行修复。修复工作属于
```
uplift
```
（页面重设计）、
```
stardust:direct
```
第2.5阶段（改进列表）和rollout的优化循环（平台自动修复）。审计仅指出修复方案；绝不修改网站。

Stop conditions

停止条件

Stop and surface only if:

(a) Extract fails entirely — site unreachable, structure unparseable, bot-management block past the headed-Chrome fallback. Surface extract's error verbatim; nothing to audit. (b) impeccable unavailable — Phase 2's critique/audit arms and Phase 6's report render require it. Per the Phase 0 carve-out, the run continues in degraded mode (VISION pass, SEO/technical, LLM visibility, benchmarks all still fire) and writes

audit.json

; then stop and tell the user the designed report needs the impeccable plugin — deliver the data, not a hand-templated substitute.

Everything else degrades per the ladder; the audit never stops for confirmation in normal flow.

仅在以下情况终止并输出信息：

(a) Extract完全失败 —— 网站无法访问、结构无法解析、绕过有头Chrome fallback后仍被反爬虫拦截。直接输出extract的错误信息；无内容可审计。 (b) impeccable不可用 —— 第2阶段的评论/审计模块和第6阶段的报告渲染依赖该工具。根据第0阶段的例外规则，运行会进入降级模式（仍执行VISION扫描、SEO/技术、LLM可见性、基准测试）并写入

audit.json

；然后终止并告知用户，完整报告需要impeccable插件——交付数据，而非手动模板化的替代报告。

其他所有情况均按降级机制处理；正常流程中审计绝不会因等待确认而终止。

Outputs

输出结果

stardust/
├── current/                             ← from extract (reused when <7 days old)
│   ├── _brand-extraction.json
│   ├── brand-review.html                ← Tensions section = Phase 1 input
│   ├── pages/<slug>.json
│   └── assets/screenshots/<slug>.png    ← VISION-pass + report evidence figures
└── audit/
    └── <domain-slug>/                   ← hostname, www-stripped, dots → dashes
        ├── audit.json                   ← scorecard, measurements, findings[], provenance
        └── report.html                  ← craft-rendered, self-contained

stardust/rollout/optimize/findings.json  ← appended via findings.mjs (rollout projects only)

Audit writes no

state.json

entries — extraction state belongs to

extract

; audit's own artifacts are self-describing via provenance. Re-running audit against a fresh extraction overwrites

stardust/audit/<domain-slug>/

; ledger recordings dedupe by the ledger's own id hash.

stardust/
├── current/                             ← 来自extract模块（7天内的内容会复用）
│   ├── _brand-extraction.json
│   ├── brand-review.html                ← Tensions章节 = 第1阶段输入
│   ├── pages/<slug>.json
│   └── assets/screenshots/<slug>.png    ← VISION扫描+报告证据图片
└── audit/
    └── <domain-slug>/                   ← 主机名，移除www，点替换为横杠
        ├── audit.json                   ← 评分卡、测量数据、findings[]、溯源信息
        └── report.html                  ← craft工具渲染的独立页面

stardust/rollout/optimize/findings.json  ← 通过findings.mjs追加（仅rollout项目）

审计不会写入

state.json

条目——提取状态属于

extract

模块；审计自身的工件通过溯源信息实现自描述。针对新提取内容重新运行审计会覆盖

stardust/audit/<domain-slug>/

；清单记录会通过自身ID哈希去重。

Scope

范围

Audits and prescribes; never modifies the site or its redesign artifacts.
One origin per run. Auditing a competitor set is N runs.
The natural continuations:
```
stardust:uplift <url>
```
(the closing directions are its variant briefs),
```
stardust:direct
```
(findings feed the Phase 2.5 improvements list), rollout's optimize loop (ledger findings with known check ids autofix on AEM).

仅执行审计和给出建议；绝不修改网站或其重设计工件。
每次运行仅审计一个源站。若要审计竞品集合，需执行N次运行。
后续自然操作：
```
stardust:uplift <url>
```
（报告结尾的方向即为其变体需求）、
```
stardust:direct
```
（发现结果会输入到2.5阶段的改进列表）、rollout的优化循环（带有已知检查ID的清单发现结果可在AEM上自动修复）。

References

参考文档

```
reference/scoring.md
```
— the seven dimensions, weights, observable anchors at 40/70/90, scoring procedure.
```
reference/report-format.md
```
—
```
audit.json
```
schema (Part 1) and the
```
report.html
```
craft brief + post-render validation (Part 2).
```
../extract/SKILL.md
```
— crawl, capture, brand-surface extraction; § Failure modes for the anti-synthesis discipline.
```
../extract/reference/brand-review-template.md
```
§ Tensions — the
```
T-*
```
detector catalog Phase 1 carries forward.
```
../prototype/SKILL.md
```
§ Invoking impeccable — the Skill-tool delegation mechanic reused for critique (Phase 2) and the report render (Phase 6).
```
../rollout/reference/audit-sources.md
```
— the findings-ledger normalization rules (severity, fixability) Phase 6 applies.
```
../rollout/reference/checks.md
```
— baseline check ids to reuse so AEM autofix picks the findings up.
```
../rollout/scripts/findings.mjs
```
— the ledger writer (
```
record
```
).
```
../uplift/SKILL.md
```
§ The three-variant role contract — the frame for the closing uplift directions.
```
../prototype/reference/motion-registers.md
```
§ Selection heuristic — register suggestion for direction C.
```
../direct/SKILL.md
```
§ Phase 2.5 — the improvements list audit findings feed on a subsequent redesign.
```
../deploy/da-deploy-protocol.md
```
— the DA transport behind
```
--deploy
```
(source PUT → preview → live; no block conversion).
```
../stardust/SKILL.md
```
§ Setup — master-skill setup run in Phase 0.
```
../stardust/reference/artifact-map.md
```
— provenance shapes.

```
reference/scoring.md
```
—— 七个维度、权重、40/70/90分的可观察锚点、评分流程。
```
reference/report-format.md
```
——
```
audit.json
```
格式（第1部分）和
```
report.html
```
的craft工具要求+渲染后验证规则（第2部分）。
```
../extract/SKILL.md
```
—— 爬取、捕获、品牌呈现提取；参考§ Failure modes了解反合成规范。
```
../extract/reference/brand-review-template.md
```
§ Tensions —— 第1阶段复用的
```
T-*
```
检测器目录。
```
../prototype/SKILL.md
```
§ Invoking impeccable —— 第2阶段评论和第6阶段报告渲染复用的Skill工具委托机制。
```
../rollout/reference/audit-sources.md
```
—— 第6阶段使用的结论清单标准化规则（严重程度、可修复性）。
```
../rollout/reference/checks.md
```
—— 可复用的基线检查ID，以便AEM自动修复识别结论。
```
../rollout/scripts/findings.mjs
```
—— 清单写入工具（
```
record
```
命令）。
```
../uplift/SKILL.md
```
§ The three-variant role contract —— 结尾uplift重设计方向的框架。
```
../prototype/reference/motion-registers.md
```
§ Selection heuristic —— 方向C的动效等级建议。
```
../direct/SKILL.md
```
§ Phase 2.5 —— 后续重设计中，审计发现结果会输入到改进列表。
```
../deploy/da-deploy-protocol.md
```
——
```
--deploy
```
参数背后的DA传输协议（源文件PUT → 预览 → 上线；无区块转换）。
```
../stardust/SKILL.md
```
§ Setup —— 第0阶段运行的主技能准备流程。
```
../stardust/reference/artifact-map.md
```
—— 溯源信息格式。