Back to Details

email-quality-auditor

Compare original and translation side by side

🇺🇸

Original

English
🇨🇳

Translation

Chinese

Email Quality Auditor

邮件质量审计工具

Audit one email program/profile and observation window with SEND. Open rate is MPP-sensitive proxy evidence; direct action and the program's declared outcome truth set carry the outcome read.
审核单个邮件程序/配置文件及基于SEND框架的观察窗口期。打开率是受MPP影响的代理证据；直接操作及程序声明的结果真值集决定最终结论。

When This Must Trigger

触发场景

  • Before a material broadcast/sequence release when channel safety is uncertain.
  • When authentication, consent, suppression, complaints, frequency, claims, or attribution need a gate.
  • When the user requests an EQS/SEND baseline or rerun.
  • 当渠道安全性存疑时，在重要广播/序列发布前触发。
  • 当需要对身份验证、同意机制、抑制列表、投诉、发送频率、声明或归因进行审核时触发。
  • 当用户请求EQS/SEND基准评估或重新运行审核时触发。

Quick Start

快速开始

text
Audit this newsletter using the last 90 days, provider split, MPP share, and subscription truth set.
Check this promotional send against DMARC, consent events, live suppressions, claims, and order IDs.
text
Audit this newsletter using the last 90 days, provider split, MPP share, and subscription truth set.
Check this promotional send against DMARC, consent events, live suppressions, claims, and order IDs.

Skill Contract

技能约定

Reads: one program/profile, normalized window, provider evidence, live consent/suppression state, rendered messages, and outcome truth. Writes: only a permissioned v3 artifact. Done when: all expected SEND states are explicit and the scorer result is reported without sending email or changing provider settings.
Use 
deliverability-qa
to repair authentication, 
consent-registry
for lawful-basis/suppression facts, 
email-sequence-designer
for journeys, and 
send-experiment-designer
for preregistered tests.
读取内容： 单个程序/配置文件、标准化窗口期、服务商证据、实时同意/抑制状态、渲染后的邮件内容及结果真值。写入内容： 仅写入经授权的v3版本审计产物。完成标志： 所有预期的SEND状态均明确，且已报告评分结果，未发送邮件或修改服务商设置。
如需修复身份验证，请使用
deliverability-qa
；如需获取合法依据/抑制列表事实，请使用
consent-registry
；如需设计用户旅程，请使用
email-sequence-designer
；如需设计预注册测试，请使用
send-experiment-designer
。

Data Sources

数据源

NeedPreferred evidence
AuthenticationDNS, message headers, DMARC aggregate evidence
Consent/suppressionAppend-only consent events plus current live projection
Placement/reputationProvider/seed panel and dated ESP/provider reports
EngagementCohort/provider/MPP-segmented ESP export
LifecycleTrigger/flow configuration and event export
OutcomeEcommerce, CRM, subscription, sponsorship, or named equivalent truth set
ContentRendered message/destination and approved claim/disclosure state
需求首选证据
身份验证DNS、邮件头、DMARC聚合证据
同意/抑制仅追加的同意事件及当前实时预测数据
投递位置/信誉服务商/种子面板及标注日期的ESP/服务商报告
用户参与度按群组/服务商/MPP细分的ESP导出数据
生命周期触发/流程配置及事件导出数据
结果电商、CRM、订阅、赞助或同类命名的真值集
内容渲染后的邮件/目标地址及已获批的声明/披露状态

Instructions

操作说明

Runtime Reads

运行时读取文件

  • ../../../references/auditor-runbook.md
  • ../../../references/scoring-semantics.md
  • ../../../references/send-benchmark.md
  • ../../../references/runtime-invocation.md
  • references/auditor-runtime.md
  • ../../../references/auditor-runbook.md
  • ../../../references/scoring-semantics.md
  • ../../../references/send-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
, 
send-benchmark.md
, and the SEND 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 (
promotional|retention|cold-outbound|newsletter
), target/program, provider, market, normalized window, list age, MPP share, and observation date.
读取
../../../references/auditor-runbook.md
、
scoring-semantics.md
、
send-benchmark.md
及SEND目录条目。独立安装版本使用捆绑的不可变文件
references/auditor-runtime.md
；切勿获取可变的
main
分支内容。在确定性调用前，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、验证器及标准化目录。若上述资源不可用，返回
score_state: NOT_SCORED
/ 
score_confidence: not_scored
，不提供审核结论或持久化产物。
声明配置文件类型（
promotional|retention|cold-outbound|newsletter
）、目标/程序、服务商、市场、标准化窗口期、列表时长、MPP占比及观察日期。

Evidence and Scoring

证据与评分

  1. Freeze evidence and reconcile provider cohorts/windows before comparing rates.
  2. Score all 20 
    S1..D5
    criteria. Every observed state requires source/date/type/confidence.
  3. E2
    is N/A with reason when opens/CTOR are not used. 
    N3/N5
    are conditional by program design. Missing records or exports are Unknown, not N/A.
  4. Verify vetoes: 
    • SEND-S1
      : required authentication is demonstrably broken/unaligned.
    • SEND-S2
      : a purchased/scraped/unlawful list is verified; missing provenance is Unknown.
    • SEND-N1
      : opt-out is broken/absent or a recorded suppression is not honored.
    • SEND-D1
      : material claim/disclosure/offer term fails approved evidence.
  5. Run the typed scorer. Use clicks/replies/downstream actions as primary engagement evidence where available; opens/CTOR remain caveated proxy evidence.
For a send-only review without enough program evidence, report the verified red-line checks and exact gaps but return 
NOT_SCORED/UNDECIDED
; “no blocker observed in supplied evidence” is not a full SEND SHIP verdict.
  1. 在对比数据率之前，冻结证据并协调服务商群组/窗口期数据。
  2. 对全部20项
    S1..D5
    标准进行评分。每个观测状态均需注明来源/日期/类型/可信度。
  3. 当未使用打开率/CTOR时，
    E2
    标记为N/A并说明原因。
    N3/N5
    根据程序设计条件性适用。缺失记录或导出数据标记为未知，而非N/A。
  4. 验证否决项： 
    • SEND-S1
      : 必需的身份验证被证实存在故障/不一致。
    • SEND-S2
      : 核实为购买/抓取/非法列表；来源缺失标记为未知。
    • SEND-N1
      : 退订功能故障/缺失，或已记录的抑制列表未被遵守。
    • SEND-D1
      : 重要声明/披露/条款未通过已获批证据验证。
  5. 运行标准化评分器。在可用情况下，使用点击/回复/下游操作作为主要用户参与度证据；打开率/CTOR仍需标注为受限制的代理证据。
若仅进行发送审核但缺乏足够的程序证据，报告已验证的红线检查结果及明确的缺口，但返回
NOT_SCORED/UNDECIDED
；“在提供的证据中未发现阻碍”并非完整的SEND SHIP结论。

§2 SEND Worked Examples

§2 SEND示例

  • Complete newsletter profile, raw 81, no veto/fail: 
    DONE/SHIP
    , final 81.
  • Complete promotional profile, raw 76, one verified S1 failure: 
    DONE_WITH_CONCERNS/FIX
    , final 59.
  • Complete profile, verified S2 and N1 failures: 
    DONE/BLOCK
    , no final score.
  • Consent provenance absent: S2 Unknown, 
    NEEDS_INPUT/UNDECIDED
    , no score.
  • 完整的新闻通讯配置文件，原始得分81，无否决/不合格项：
    DONE/SHIP
    ，最终得分81。
  • 完整的营销推广配置文件，原始得分76，一项已验证的S1不合格：
    DONE_WITH_CONCERNS/FIX
    ，最终得分59。
  • 完整的配置文件，已验证存在S2和N1不合格项：
    DONE/BLOCK
    ，无最终得分。
  • 同意来源缺失：S2标记为未知，
    NEEDS_INPUT/UNDECIDED
    ，无得分。

§3 SEND Guardrails

§3 SEND约束规则

  • DMARC 
    p=none
    with aligned SPF/DKIM and active monitoring is not automatically an S1 failure.
  • Provider one-click-unsubscribe policy and statutory duties must be named separately.
  • Opens and CTOR require MPP segmentation/proxy caveat; they cannot establish human attention alone.
  • A newsletter need not have cart/post-purchase flows; score only journeys applicable to its declared program.
  • Over-frequency is a serious E4/E5 finding, not an automatic veto.
  • DMARC 
    p=none
    且SPF/DKIM对齐并处于主动监控状态，不会自动判定为S1不合格。
  • 服务商一键退订政策与法定义务必须单独列明。
  • 打开率和CTOR需标注MPP细分/代理说明；它们无法单独证明用户已关注邮件。
  • 新闻通讯无需包含购物车/售后流程；仅针对其声明程序适用的用户旅程进行评分。
  • 发送频率过高属于严重的E4/E5问题，但并非自动否决项。

§5 SEND Translation

§5 SEND结果解读

Explain channel and recipient risk in plain language. On trace request, qualify 
SEND-S1/S2/N1/D1
and show the underlying DNS/event/rendered evidence.
用通俗易懂的语言解释渠道及收件人风险。当用户请求追溯时，说明
SEND-S1/S2/N1/D1
的判定依据，并展示底层的DNS/事件/渲染证据。

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, S/E/N/D detail, outcome truth set, verified critical controls, Unknown inputs, and fix owners. Do not claim deliverability/inbox placement from DNS alone and do not execute a send.
以审计手册中明确的标准化对话标题开头。切勿用散文替代
status
、
verdict
或
score_state
；在列出发现结果前，将每个明确缺失的合格项标记为``ID: `unknown```。
展示结论、配置文件/上下文、得分或覆盖范围/区间、可信度、S/E/N/D细节、结果真值集、已验证的关键控制项、未知输入及修复负责人。不得仅依据DNS就声称邮件可送达/进入收件箱，且不得执行发送操作。

Validation Checkpoints

验证检查点

  • Program/profile/provider/window/list age/market/MPP share are declared.
  • Live suppression state was verified by replay, not a stale projection or pending proposal.
  • All 20 states are valid; conditional N/A has a reason.
  • Provider metrics and reconciled outcome truth are separated.
  • No email/provider mutation occurred without separate explicit approval.
  • 已声明程序/配置文件/服务商/窗口期/列表时长/市场/MPP占比。
  • 实时抑制状态已通过重放验证，而非使用过时的预测数据或待批准的方案。
  • 全部20项状态均有效；条件性N/A已说明原因。
  • 服务商指标与协调后的结果真值已区分开。
  • 在未获得单独明确授权的情况下，未对邮件/服务商进行任何修改。

Persistence

持久化存储

Persist only after explicit authorization to 
memory/audits/email/YYYY-MM-DD-<topic>.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. Do not autonomously modify consent, claims, provider settings, or hot cache.
仅在获得明确授权后，将审计结果持久化存储至
memory/audits/email/YYYY-MM-DD-<topic>.md
。保留评分器独立的
status
和
verdict
；使用
validate-audit-artifact.py
针对指定的
--relative-path
验证完整的v3版本草稿，仅通过一次全内容写入操作完成持久化，并根据审计手册重新验证目标内容。不支持对保留存储库进行编辑/Shell/MCP修改。不得自主修改同意机制、声明、服务商设置或热缓存。

Reference Materials

参考资料

  • SEND benchmark
  • Measurement protocol
  • Auditor runbook
  • Scoring semantics
  • SEND benchmark
  • Measurement protocol
  • Auditor runbook
  • Scoring semantics

Next Best Skill

推荐关联技能

  • Authentication/placement: deliverability-qa
  • Consent/suppression: consent-registry
  • Lifecycle: email-sequence-designer
  • Experiment: send-experiment-designer
  • 身份验证/投递位置： deliverability-qa
  • 同意/抑制： consent-registry
  • 生命周期： email-sequence-designer
  • 实验： send-experiment-designer