narrative-quality-auditor

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

Narrative Quality Auditor

叙事质量审核器

Audit narrative truth, message-system coherence, or measured effectiveness as separate TALE profiles. There is no v18 overall composite: truth cannot be averaged away by coherence, and coherence cannot stand in for effectiveness evidence.

将叙事真实性、信息体系一致性或可衡量的有效性作为独立的TALE分析报告进行审核。不存在v18综合版本：真实性不能通过一致性来平均抵消，一致性也不能替代有效性证据。

When This Must Trigger

触发条件

The user asks whether positioning/differentiation is defensible.
A flagship surface needs a pre-publish canon/message-match gate.
A message experiment or resonance claim needs evidence-integrity review.
A full narrative review is requested; run linked profiles rather than one blended score.

用户询问定位/差异化是否具有合理性。
核心展示内容需要发布前的标准/信息匹配校验。
信息实验或共鸣效果声明需要证据完整性审查。
用户要求进行完整叙事审查；需运行关联的分析报告，而非生成一个混合分数。

Quick Start

快速开始

text

Run TALE truth on canon v7 against named alternatives and approved claims.
Run TALE system on homepage/pricing/deck against canon v7 before release.
Run a full review as three linked profile results; do not compute an overall score.

text

Run TALE truth on canon v7 against named alternatives and approved claims.
Run TALE system on homepage/pricing/deck against canon v7 before release.
Run a full review as three linked profile results; do not compute an overall score.

Skill Contract

Skill 契约

Reads: one canon/surface set or message experiment plus current narrative/claims truth. Writes: only permissioned v3 artifacts. Done when: each requested profile is independently complete or its Unknowns are explicit, with no canon, claims, or surface mutation.

narrative-registry

owns canon/version state and

offer-claims-registry

owns claims. This skill judges; authoring/fixing belongs to Trace/Architect/Land skills.

读取： 一组标准/展示内容或信息实验，加上当前叙事/声明的真实性数据。写入： 仅允许写入授权的v3工件。完成条件： 每个请求的分析报告均独立完成，或明确标注未知项，且未修改标准、声明或展示内容。

narrative-registry

负责管理标准/版本状态，

offer-claims-registry

负责管理声明。本Skill仅负责判断；创作/修复工作由Trace/Architect/Land类Skill负责。

Data Sources

数据源

Need	Preferred evidence
Truth	Named alternatives, interviews/win-loss, product reality, claims projection
Architecture	Exact canon/version, message hierarchy, voice/naming/version history
Landing	Declared rendered flagship surfaces linked to canon version
Effectiveness	Preregistered comprehension/recall/behavior evidence and locked panels
Public resonance	Dated own/public signals with explicit measured/proxy provenance

需求	首选证据
真实性	指定竞品、访谈/输赢分析、产品实际情况、声明预测
体系架构	精确的标准/版本、信息层级、语气/命名/版本历史
落地一致性	已声明的核心展示内容链接至对应版本的标准
有效性	预先注册的理解/记忆/行为证据及固定样本组
公众共鸣	带有明确测量/代理来源的自有/公开信号数据（标注日期）

Instructions

操作说明

Runtime Reads

运行时读取

```
../../../references/auditor-runbook.md
```

../../../references/scoring-semantics.md

```
../../../references/tale-benchmark.md
```

../../../references/runtime-invocation.md

```
references/auditor-runtime.md
```

```
../../../references/auditor-runbook.md
```

../../../references/scoring-semantics.md

```
../../../references/tale-benchmark.md
```

../../../references/runtime-invocation.md

```
references/auditor-runtime.md
```

Runtime and Setup

运行时与设置

Read

../../../references/auditor-runbook.md

scoring-semantics.md

tale-benchmark.md

, and the TALE catalog entry. Standalone installs use bundled immutable

references/auditor-runtime.md

; never fetch mutable

main

. Before deterministic calls, follow

runtime-invocation.md

, resolve

AARON_SKILLS_ROOT="${CLAUDE_PLUGIN_ROOT:-$(git rev-parse --show-toplevel 2>/dev/null || true)}"

, and require the scorer, validator, and typed catalogs. If unavailable, still collect the selected profile's typed observations and Unknowns, but return

score_state: NOT_SCORED

score_confidence: not_scored

with no gate verdict or persistent artifact; runtime absence blocks deterministic scoring, not the observation pass.

Declare target, profile/mode, brand scope, market, audience, canon version, observation date, and evidence window.

读取

../../../references/auditor-runbook.md

、

scoring-semantics.md

、

tale-benchmark.md

以及TALE目录条目。独立安装时使用捆绑的不可变

references/auditor-runtime.md

；切勿获取可变的

main

分支内容。在进行确定性调用前，遵循

runtime-invocation.md

，解析

AARON_SKILLS_ROOT="${CLAUDE_PLUGIN_ROOT:-$(git rev-parse --show-toplevel 2>/dev/null || true)}"

，并调用评分器、验证器和类型化目录。若上述资源不可用，仍需收集所选分析报告的类型化观察结果和未知项，但返回

score_state: NOT_SCORED

score_confidence: not_scored

，且不给出校验结论或持久化工件；运行时资源缺失会阻止确定性评分，但不会阻止观察流程。

声明目标、分析报告/模式、品牌范围、市场、受众、标准版本、观察日期和证据时间范围。

Profile Procedure

分析报告流程

truth
: score T1–T10 for material differentiation and factual grounding.
system
: score A1–A10 and L1–L10 for canon coherence and landing consistency.
effectiveness
: score E1–E10 for one experiment/locked panel/date.
full
: run the three profiles independently and keep three artifacts/results. Aggregate release language conservatively: any BLOCK → block; otherwise any UNDECIDED → undecided; otherwise any FIX → fix; all SHIP → ship. Never average scores.

For a flagship pre-publish gate, always execute the

system

profile procedure and require a compatible current

truth

result. If no compatible truth result exists, run

truth

separately when its evidence is available; otherwise record the truth prerequisite as Unknown while still rendering the requested system-profile result. A missing scorer/runtime changes that result to

NOT_SCORED/UNDECIDED

; it does not justify skipping the profile. Run

effectiveness

separately only when the user requests it or the surface makes an effectiveness claim.

Every observed state needs source/date/type/confidence. A missing canon is Unknown, not N/A. A2/A4/A8 are conditional: three pillars, a change arc, and fixed boilerplate lengths are patterns only when deliberately chosen. Run the typed scorer per profile.

Verify profile-relevant vetoes:

TALE-T1

false/contradictory/unsubstantiated material differentiation,

TALE-A1

demonstrated canon contradiction,

TALE-L1

material flagship/canon contradiction, and

TALE-E1

unsupported effectiveness claim or proxy-as-measured.

truth
（真实性）：针对实质性差异化和事实基础对T1–T10进行评分。
system
（体系性）：针对标准一致性和落地一致性对A1–A10和L1–L10进行评分。
effectiveness
（有效性）：针对单个实验/固定样本组/日期对E1–E10进行评分。
full
（完整审核）：独立运行上述三个分析报告，保留三个工件/结果。发布语言需保守汇总：任何BLOCK（阻止）→ 阻止；否则任何UNDECIDED（未决）→ 未决；否则任何FIX（需修复）→ 需修复；全部SHIP（可发布）→ 可发布。绝不平均分数。

对于核心内容的发布前校验，必须执行

system

分析报告流程，并要求有兼容的当前

truth

结果。若不存在兼容的真实性结果，在证据可用时单独运行

truth

；否则记录真实性前提为未知项，同时仍生成请求的体系性分析报告结果。缺失评分器/运行时会将结果改为

NOT_SCORED/UNDECIDED

；但这不能成为跳过分析报告的理由。仅当用户要求或展示内容包含有效性声明时，才单独运行

effectiveness

分析报告。

每个观察状态都需要标注来源/日期/类型/置信度。缺失的标准属于未知项，而非N/A。A2/A4/A8为条件性指标：三大支柱、变化弧线和固定模板长度仅在刻意选择时才视为模式。针对每个分析报告运行类型化评分器。

验证与分析报告相关的否决项：

TALE-T1

（虚假/矛盾/无依据的实质性差异化）、

TALE-A1

（已证实的标准矛盾）、

TALE-L1

（核心展示内容与标准存在实质性矛盾）以及

TALE-E1

（无依据的有效性声明或混淆代理数据与实测数据）。

§2 TALE Worked Examples

§2 TALE 示例

Complete truth profile, raw 86, no veto/fail:
```
DONE/SHIP
```
, final 86.
Complete system profile, raw 80, one verified L1 failure:
```
DONE_WITH_CONCERNS/FIX
```
, final 59.
Complete system profile with A1 and L1 failures:
```
DONE/BLOCK
```
, no final score.
Effectiveness profile before test results exist:
```
NEEDS_INPUT/UNDECIDED
```
, no score.

完整的真实性分析报告，原始分数86，无否决/失败：
```
DONE/SHIP
```
，最终分数86。
完整的体系性分析报告，原始分数80，存在一个已验证的L1失败项：
```
DONE_WITH_CONCERNS/FIX
```
，最终分数59。
存在A1和L1失败项的完整体系性分析报告：
```
DONE/BLOCK
```
，无最终分数。
测试结果出来前的有效性分析报告：
```
NEEDS_INPUT/UNDECIDED
```
，无分数。

§3 TALE Guardrails

§3 TALE 约束规则

A literal “onlyness” sentence is not required; judge the material differentiation actually asserted.
Three pillars, a Raskin/change arc, and 25/50/100-word boilerplates are conditional patterns.
A governed draft can be audited as a draft; missing access is Unknown, not an A1 failure.
Share of voice, sentiment, answer-engine descriptions, comprehension, and behavior are distinct constructs.
Narrative change frequency is a drift signal, not an automatic veto.

不要求必须有字面意义上的“唯一性”表述；需判断实际主张的实质性差异化。
三大支柱、Raskin/变化弧线以及25/50/100字模板为条件性模式。
受管控的草稿可作为草稿进行审核；访问权限缺失属于未知项，而非A1失败。
声量份额、情感倾向、搜索引擎描述、用户理解和行为是不同的概念。
叙事变更频率是漂移信号，而非自动否决项。

§5 TALE Translation

§5 TALE 翻译规则

Always name truth/system/effectiveness. On trace request, qualify

TALE-T1/A1/L1/E1

, especially

TALE-E1

versus

ECHO-E1

and

TALE-A1

versus ROAS/RAMP.

必须明确标注真实性/体系性/有效性。在追踪请求时，需明确

TALE-T1/A1/L1/E1

的类别，尤其是

TALE-E1

与

ECHO-E1

、

TALE-A1

与ROAS/RAMP的区别。

Report and Verdict

报告与结论

Begin with the auditor-runbook's exact typed conversation header. Never replace

status

verdict

, or

score_state

with prose; list each explicitly missing qualified item as ``ID: `unknown``` before findings.

For each profile show verdict, target/canon/context/date, score or coverage/interval, confidence, evidence, Unknowns, and fixes. A full report shows three side-by-side results and no overall number. Do not claim market effectiveness from system coherence.

以审核器运行手册中精确的类型化对话标题开头。绝不能用散文替代

status

、

verdict

或

score_state

；在结果前将每个明确缺失的合格项列为 ``ID: `unknown```。

针对每个分析报告展示结论、目标/标准/上下文/日期、分数或覆盖范围/区间、置信度、证据、未知项和修复建议。完整报告需展示三个并排的结果，无综合分数。不得从体系一致性推断市场有效性。

Validation Checkpoints

验证检查点

One profile/unit per score; full mode preserves three results.
Canon/surface/experiment versions and audience/market are explicit.
Conditional templates use N/A only with reason; missing evidence stays Unknown.
Current truth/claims projections are read, not candidate files.
No canon/claim/surface write or publish action occurred.

每个分数对应一个分析报告/单元；完整模式保留三个结果。
明确标注标准/展示内容/实验版本以及受众/市场。
条件性模板仅在有理由时使用N/A；缺失的证据仍标记为未知项。
读取的是当前真实性/声明预测数据，而非候选文件。
未执行任何标准/声明/展示内容的写入或发布操作。

Persistence

持久化

Persist only after explicit authorization to

memory/audits/narrative/YYYY-MM-DD-<topic>-<profile>.md

. Preserve the scorer's orthogonal

status

and

verdict

; validate the complete v3 draft with

validate-audit-artifact.py

against the intended relative path, persist only through one full-content Write, and revalidate the target per the auditor runbook. Edit/shell/MCP mutations of the reserved sink are unsupported. Never overwrite another profile or update canon/claims/hot cache autonomously.

仅在获得明确授权后，将内容持久化至

memory/audits/narrative/YYYY-MM-DD-<topic>-<profile>.md

。保留评分器的正交

status

和

verdict

；使用

validate-audit-artifact.py

针对预期相对路径验证完整的v3草稿，仅通过一次完整内容写入进行持久化，并根据审核器运行手册重新验证目标。不支持对保留存储区进行编辑/Shell/MCP修改。绝不能覆盖其他分析报告或自主更新标准/声明/热缓存。