ad-account-auditor

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

Ad Account Auditor

广告账户审计工具

Audit one paid-media account or portfolio for incremental contribution and operating quality under declared constraints. Platform-reported ROAS is one input, never the objective or truth set by itself.

在指定约束条件下，审计单个付费媒体账户或账户组合的增量贡献与运营质量。平台上报的ROAS仅作为一项输入数据，绝非最终目标或唯一真实依据。

When This Must Trigger

触发场景

Before launching, materially increasing spend, or changing a risky bid/targeting strategy.
When tracking, attribution inflation, unsafe placements, claims, or wasted spend are in doubt.
When the user requests a ROAS/RQS account audit from their exports.

在启动广告、大幅增加预算或调整高风险出价/定向策略之前。
当对追踪数据、归因膨胀、不安全投放位置、合规声明或无效支出存在疑虑时。
当用户基于自有导出数据请求ROAS/RQS账户审计时。

Quick Start

快速开始

text

Audit this USD account for direct response using 7-day click, 3-day lag, and $120 CAC ceiling.
Run the incremental-profit profile against the holdout and order-ID exports.

text

Audit this USD account for direct response using 7-day click, 3-day lag, and $120 CAC ceiling.
Run the incremental-profit profile against the holdout and order-ID exports.

Skill Contract

技能约定

Reads: one normalized account/portfolio evidence set. Writes: only a permissioned v3 artifact. Done when: required context and all 20 states are explicit, vetoes use verified evidence, and scorer output is reported without executing spend changes.

This skill judges.

conversion-signal-qa

attribution-reconciler

campaign-architect

ad-creative-builder

, and

budget-pacing-monitor

build/fix the inputs. Never enable campaigns, change bids, upload audiences, or scale budgets without separate explicit approval.

For a pre-launch account-audit request, use the narrow route

conversion-signal-qa

immediately before this gate. Do not automatically insert

placement-exclusion-manager

conversion-value-mapper

between signal QA and the audit; missing placement or value evidence remains Unknown in this run, and those sibling builders become separate remediation only when the user requests them or the completed gate identifies the corresponding finding.

读取权限： 一套标准化的账户/账户组合证据集。写入权限： 仅可写入经过授权的v3版本审计产物。完成标志： 所需上下文明确、20项评估状态全部确定、否决机制使用已验证证据，且评分结果已上报，未执行任何预算调整操作。

本技能仅负责评估判断。

conversion-signal-qa

、

attribution-reconciler

、

campaign-architect

、

ad-creative-builder

和

budget-pacing-monitor

负责构建/修复输入数据。未经单独明确授权，绝不能启用广告系列、调整出价、上传受众群体或扩大预算。

对于预启动阶段的账户审计请求，需先通过

conversion-signal-qa

这个前置环节。请勿在信号验证与审计之间自动插入

placement-exclusion-manager

或

conversion-value-mapper

；缺失的投放位置或转化价值证据在本次审计中标记为未知，只有当用户提出请求或审计完成后发现对应问题时，才需调用这些关联工具进行单独修复。

Data Sources

数据源

Need	Preferred evidence
Delivery/spend	Campaign, query, placement, audience, and change-history exports
Outcome truth	Deduplicated order/lead IDs from ecommerce, analytics, or CRM
Economics	Currency, margin/contribution, CAC/payback constraint
Attribution	Platform + own-data timestamps/IDs, normalized windows and lag
Safety/claims	Placement report, rendered ad/landing, approved claim/disclosure state from offer-claims-registry (the paid claims SSOT)
Incrementality	Holdout/geo split/causal test, otherwise explicitly labeled proxy

需求	首选证据
投放/支出数据	广告系列、查询、投放位置、受众群体及变更历史导出数据
转化真实数据	来自电商平台、分析工具或CRM系统的去重订单/销售线索ID
经济指标	货币类型、利润率/贡献值、CAC/投资回报周期约束
归因数据	平台数据+自有数据的时间戳/ID、标准化窗口期与延迟时间
安全/合规声明	投放位置报告、已渲染广告/落地页、来自offer-claims-registry（付费广告合规声明唯一可信来源）的已批准声明/披露状态
增量效果	对照组/地域分割/因果测试数据，否则需明确标记为替代指标

Instructions

操作说明

Runtime Reads

运行时读取文件

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

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

```
../../../references/roas-benchmark.md
```

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

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

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

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

```
../../../references/roas-benchmark.md
```

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

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

Runtime and Setup

运行与设置

Read

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

scoring-semantics.md

roas-benchmark.md

, and the ROAS 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, return

score_state: NOT_SCORED

score_confidence: not_scored

with no gate verdict or persistent artifact.

Declare profile (

direct-response|prospecting|incremental-profit

), target, currency, attribution window, conversion lag, business constraint, goal, and observation date. If any required context is missing, return

NEEDS_INPUT/UNDECIDED

读取

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

、

scoring-semantics.md

、

roas-benchmark.md

以及ROAS目录条目。独立安装版本使用捆绑的不可变

references/auditor-runtime.md

；绝不能获取可变的

main

分支内容。在确定性调用前，遵循

runtime-invocation.md

，设置

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

，并确保评分器、验证器和标准化目录可用。若不可用，返回

score_state: NOT_SCORED

score_confidence: not_scored

，且不提供决策闸门结论或持久化审计产物。

声明评估模型类型（

direct-response|prospecting|incremental-profit

）、目标、货币类型、归因窗口期、转化延迟时间、业务约束、目标及观测日期。若任何必要上下文缺失，返回

NEEDS_INPUT/UNDECIDED

。

Evidence and Scoring

证据与评分

Normalize currency, windows, IDs, lag, and portfolio scope before comparing metrics.
Score all 20
```
R1..S5
```
criteria from the benchmark with source/date/type/confidence.
Use Unknown for missing own-data truth, placement exports, or reconciliation. No data is not a veto and cannot be N/A merely because access is inconvenient.
Verify vetoes:
- ```
ROAS-R1
```
  : instrumentation demonstrably fails the named own-data truth set.
- ```
ROAS-R2
```
  : material double-counting/inflation is demonstrated.
- ```
ROAS-O1
```
  : material claim/disclosure failure against the
```
offer-claims-registry
```
  approved state.
- ```
ROAS-O2
```
  : applicable platform/restricted-category violation.
- ```
ROAS-A1
```
  : placement evidence demonstrates a material safety breach.
Run the typed scorer. Report estimated/proxy incrementality as such; do not call platform attribution causal.

在对比指标前，统一货币类型、窗口期、ID、延迟时间及账户组合范围。
根据基准对所有20项
```
R1..S5
```
标准进行评分，并标注来源/日期/类型/可信度。
若缺失自有真实数据、投放位置导出数据或对账数据，标记为未知。无数据不属于否决情况，不能仅因获取不便就标记为不适用。
验证否决条件：
- ```
ROAS-R1
```
  : 追踪工具已被证实不符合自有真实数据标准。
- ```
ROAS-R2
```
  : 已证实存在重大重复统计/数据膨胀问题。
- ```
ROAS-O1
```
  : 与
```
offer-claims-registry
```
  中已批准状态相比，存在重大声明/披露违规。
- ```
ROAS-O2
```
  : 存在适用的平台/受限类目违规。
- ```
ROAS-A1
```
  : 投放位置证据显示存在重大安全漏洞。
运行标准化评分器。需明确标注预估/替代增量效果；不得将平台归因数据称为因果性结论。

§2 ROAS Worked Examples

§2 ROAS 示例

Complete direct-response profile, raw 78, no veto/fail:
```
DONE/SHIP
```
, final 78.
Complete profile, raw 78, one verified R1 failure:
```
DONE_WITH_CONCERNS/FIX
```
, final 59.
Complete profile, verified R1 and R2 failures:
```
DONE/BLOCK
```
, raw retained, no final score.
Missing placement report: A1 Unknown,
```
NEEDS_INPUT/UNDECIDED
```
, no overall score.

完整的直接响应模型，原始评分78，无否决/不合格项：
```
DONE/SHIP
```
，最终评分78。
完整模型，原始评分78，1项已验证的R1不合格：
```
DONE_WITH_CONCERNS/FIX
```
，最终评分59。
完整模型，已验证R1和R2均不合格：
```
DONE/BLOCK
```
，保留原始评分，无最终评分。
缺失投放位置报告：A1标记为未知，
```
NEEDS_INPUT/UNDECIDED
```
，无整体评分。

§3 ROAS Guardrails

§3 ROAS 防护规则

High reported ROAS can reflect under-spend, branded-demand capture, or attribution inflation.
Learning-phase disruption is an S2 finding, not an automatic veto.
ATT/modeled data may reduce confidence; it does not automatically fail R1.
Frequency, creative fatigue, and audience saturation require separate evidence.
Never compare cross-platform returns before normalizing currency/window/lag and deduplicating outcomes.

高上报ROAS可能反映预算不足、品牌需求捕获或归因膨胀。
学习阶段中断属于S2类问题，不自动触发否决。
ATT/建模数据可能降低可信度，但不会自动导致R1不合格。
曝光频率、创意疲劳和受众饱和需要单独证据支持。
在统一货币类型/窗口期/延迟时间并去重转化数据前，绝不能跨平台对比收益。

§5 ROAS Translation

§5 ROAS 结果输出规范

Lead with business impact and evidence. On trace request, qualify

ROAS-R1/R2/O1/O2/A1

; do not expose bare IDs that collide with RAMP/ECHO/TALE.

优先展示业务影响及证据。当被要求溯源时，需明确说明

ROAS-R1/R2/O1/O2/A1

的判定依据；不得暴露与RAMP/ECHO/TALE冲突的裸ID。

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.

Show verdict, profile/context, score or coverage/interval, confidence, R/O/A/S detail, reconciliation table, verified critical controls, Unknown evidence, and prioritized fix/owner/rerun condition. The scorer owns status/verdict and the 59 ceiling.

以审计手册中明确的标准化对话标题开头。绝不能用描述性文字替代

status

、

verdict

或

score_state

；在列出发现问题前，需将每个明确缺失的合格项标记为``ID: `unknown```。

展示结论、评估模型/上下文、评分或覆盖范围/区间、可信度、R/O/A/S细节、对账表、已验证关键控制项、未知证据、优先级排序的修复方案/负责人/重审条件。评分器负责状态/结论及59分上限的判定。

Validation Checkpoints

验证检查点

Scope/currency/window/lag/constraint/goal are explicit.
Own-data outcome truth is separated from platform self-report.
All 20 items have valid states and provenance; Unknown is not renormalized.
Veto failures are positively verified.
No spend/account mutation occurred without separate approval.

范围/货币类型/窗口期/延迟时间/约束/目标已明确。
自有真实转化数据与平台自报数据已分离。
所有20项指标均有有效状态及来源；未知状态未被重新归一化。
否决不合格项已被正面验证。
未经单独授权，未执行任何预算/账户变更操作。

Persistence

持久化存储

Persist only after explicit authorization to

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

. Assemble and validate the complete v3 draft with

validate-audit-artifact.py

against that intended

--relative-path

, persist only through one full-content Write, then revalidate the target as required by the auditor runbook. Edit/shell/MCP mutations of the reserved sink are unsupported. Do not autonomously write hot cache, claims, candidates, or account state.

仅在获得明确授权后，将审计产物存储至

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

。使用

validate-audit-artifact.py

针对指定

--relative-path

组装并验证完整的v3版本草稿，仅通过一次完整内容写入操作完成存储，然后根据审计手册要求重新验证目标文件。不支持对保留存储路径进行编辑/Shell/MCP变更操作。不得自主写入热缓存、合规声明、候选数据或账户状态。

Reference Materials

参考资料

ROAS benchmark
Measurement protocol
Auditor runbook
Scoring semantics

ROAS 基准
测量协议
审计手册
评分语义

Next Best Skill

关联推荐技能

Tracking: conversion-signal-qa
Claims/disclosures: offer-claims-registry — the approved claim/disclosure state behind
```
ROAS-O1
```
Attribution: attribution-reconciler
Structure/audience: campaign-architect
Pacing: budget-pacing-monitor

追踪验证： conversion-signal-qa
合规声明/披露： offer-claims-registry ——
```
ROAS-O1
```
背后的已批准声明/披露状态来源
归因对账： attribution-reconciler
结构/受众设计： campaign-architect
预算 pacing： budget-pacing-monitor