inbox-setup

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

Inbox-Setup — Email Triage Onboarding

Inbox-Setup — 邮件分类系统初始化配置

Paired with
inbox-triage
. This skill writes the 7-file knowledge base at
${WORKSPACE}/Email/
that
inbox-triage
reads on every run. The file contracts (names, sections, fields) MUST match between the two skills exactly. See
references/kb_file_contract.md
.

Run once (or re-run when business/priorities change). Interview the user about their email patterns, business context, reply style, and priorities. Generate the structured knowledge base in

${WORKSPACE}/Email/

that captures everything

inbox-triage

needs to process the inbox effectively.

与
inbox-triage
配套使用。本技能会在
${WORKSPACE}/Email/
路径下生成包含7个文件的知识库，
inbox-triage
每次运行时都会读取这些文件。两个技能的文件约定（名称、章节、字段）必须完全一致。详见
references/kb_file_contract.md
。

运行一次即可（业务/优先级变化时可重新运行）。通过访谈收集用户的邮件模式、业务背景、回复风格和优先级信息，在

${WORKSPACE}/Email/

路径下生成结构化知识库，为

inbox-triage

高效处理收件箱提供所需的全部信息。

Invocation Triggers

触发指令

"set up my inbox"
"configure inbox triage"
"set up my email system"
"configure email triage"
"build my email knowledge base"
"initialize email management"
"set up inbox triage"
"onboard email triage"

"set up my inbox"
"configure inbox triage"
"set up my email system"
"configure email triage"
"build my email knowledge base"
"initialize email management"
"set up inbox triage"
"onboard email triage"

Conduct Discipline

执行准则

Do NOT generate all files at once. Walk through the 8 sections one at a time. Each section commits its file(s) before moving on. Partial completion (e.g., user drops off mid-interview) still produces a usable partial KB.

Grill-me discipline applies throughout:

One question per turn. Never bundle. Even across section boundaries.
"Why I'm asking" on every question — so users can answer well.
Forcing format where possible. Multi-choice > open-ended.
Dependency-ordered. Q2 depends on Q1; downstream sections depend on upstream.

See

references/grill_me_section_walk.md

for the 8-section discipline detail.

禁止一次性生成所有文件。需逐个完成8个章节，每个章节完成后先提交对应文件再进入下一章节。即使中途中断（如用户中途退出），仍可生成可用的部分知识库。

全程遵循「grill-me」准则：

每次只提一个问题。绝不批量提问，即使跨章节也不行。
每个问题都要说明「提问原因」——帮助用户更好地作答。
尽可能采用固定格式。优先选择选择题而非开放式问题。
按依赖顺序提问。问题2依赖问题1的答案，后续章节依赖前置章节的内容。

8个章节的详细准则详见

references/grill_me_section_walk.md

。

Knowledge Base Contract — Files To Produce

知识库约定 — 需生成的文件

Exactly these files at

${WORKSPACE}/Email/

File	Purpose	Required?
`email-taxonomy.md`	Classification system + report preferences	Yes
`email-patterns.md`	Reply voice, tone, templates, hard rules	Yes
`evaluation-framework.md`	Decision tree for opportunity emails	Only if user receives pitches/opportunities
`rate-card.md`	Pricing, terms, negotiation posture	Only if user has pricing
`blocklist.md`	Auto-skip senders + learned decline patterns	Yes (seeded, grows over time)
`tracker.md`	Active follow-ups, overdue items, deadlines	Yes (starts mostly empty)
`triage-log/`	Directory for per-run logs	Yes (created empty)

The contract is identical to what

inbox-triage

expects — see

references/kb_file_contract.md

for the full spec.

必须在

${WORKSPACE}/Email/

路径下生成以下文件：

文件	用途	是否必填？
`email-taxonomy.md`	分类体系 + 报告偏好设置	是
`email-patterns.md`	回复语气、风格、模板、硬性规则	是
`evaluation-framework.md`	机会类邮件的决策树	仅当用户会收到推销/机会类邮件时需生成
`rate-card.md`	定价、条款、谈判立场	仅当用户有定价体系时需生成
`blocklist.md`	自动跳过的发件人 + 已总结的拒绝模式	是（初始为空，后续会自动更新）
`tracker.md`	跟进中事项、逾期项、截止日期	是（初始基本为空）
`triage-log/`	每次运行日志的存储目录	是（初始为空目录）

该约定与

inbox-triage

的预期完全一致——完整规范详见

references/kb_file_contract.md

。

Stop Condition (Full Interview)

完整访谈结束条件

~25–31 questions total across the 8 sections (depending on skip-logic). Hard ceiling: 35 questions including all sub-clarifications. Section 4 (Evaluation Framework) is skipped entirely when Section 1 surfaced no opportunity-email category, dropping the total by 6 questions and the rate-card file. After Section 8's confirmation + handoff message, intake is closed — never re-open it. To change preferences later, the user re-runs the skill (which detects existing files and asks per-file: replace / merge / skip). The grill-me one-at-a-time rule applies across section boundaries: do NOT batch questions even when moving from S{n} to S{n+1}.

8个章节共包含约25-31个问题（取决于跳过逻辑）。上限为35个问题，包含所有补充澄清问题。如果章节1未识别到机会类邮件分类，则直接跳过章节4，减少6个问题且不生成rate-card文件。完成章节8的确认与交接信息后，访谈即结束——绝不重新开启。后续如需修改偏好，用户需重新运行本技能（系统会检测现有文件，并针对每个文件询问：替换/合并/跳过）。跨章节时仍需遵循「grill-me」一次一个问题的规则：即使从第n章进入第n+1章，也不得批量提问。

Section 1: The Big Picture

章节1：整体概况

Six grill-me questions, one at a time:

S1.Q1: "What do you do? Give me your role and business in 1–2 sentences. Why I'm asking: Context shapes what email patterns to expect — a solo creator's inbox looks nothing like an enterprise PM's."
S1.Q2: "What dominates your inbox? Pick the top 1–2: sales pitches / client work / internal team / newsletters / customer support / financial / other. Why I'm asking: Dominant categories drive the taxonomy."
S1.Q3: "Rough volume split — e.g., '60% business inquiries, 20% ops, 20% noise'. Why I'm asking: The split tells me where to focus triage effort."
S1.Q4: "Which email address(es) should triage cover? Why I'm asking: If multiple, I'll set up per-address taxonomies."
S1.Q5: "Run frequency: once daily / 2x daily / 3x daily / on-demand only? Why I'm asking: Drives the default search window in triage (9h overlap for 2x/day)."
S1.Q6: "Anyone helping manage email — assistant, VA, team — or solo? Why I'm asking: Persona handling differs for delegated inboxes."

Action: Build mental model. Do NOT write files yet. Note whether opportunity emails are a category (drives S4 skip-logic).

6个「grill-me」问题，逐个提出：

S1.Q1： "你的职业是什么？用1-2句话描述你的职位和业务。提问原因： 业务背景决定了邮件模式的差异——独立创作者的收件箱与企业产品经理的收件箱完全不同。"
S1.Q2： "你的收件箱主要由哪些内容构成？选择Top1-2：销售推销 / 客户工作 / 内部团队沟通 / 新闻通讯 / 客户支持 / 财务相关 / 其他。提问原因： 占比最高的分类将主导整个分类体系。"
S1.Q3： "大致的邮件占比拆分——例如‘60%业务咨询，20%运营，20%无效信息’。提问原因： 占比情况决定了分类工作的重点方向。"
S1.Q4： "分类系统需要覆盖哪些邮箱地址？提问原因： 如果涉及多个邮箱，将为每个邮箱单独设置分类体系。"
S1.Q5： "运行频率：每日一次 / 每日两次 / 每日三次 / 仅按需运行？提问原因： 决定分类系统的默认搜索窗口（每日两次的话默认覆盖9小时重叠时段）。"
S1.Q6： "是否有他人协助管理邮件——助理、虚拟助手、团队成员，还是完全自己处理？提问原因： 委托管理的邮箱与个人邮箱的处理方式不同。"

操作： 建立用户画像模型。暂不生成文件。记录是否存在机会类邮件分类（决定章节4的跳过逻辑）。

Section 2: Email Categories

章节2：邮件分类

Propose 5–7 categories based on Section 1 — pre-recommend a subset, not the whole template menu:

New Opportunities
Active Conversations
Action Required
Financial
Important/Personal
Informational
Ignore/Low Priority

Then three forcing questions, one at a time:

S2.Q1: "Here's my proposed taxonomy: [list]. Does this match your inbox reality — yes / mostly / no? Why I'm asking: If 'no', I need to redo the taxonomy before any other section makes sense."
S2.Q2: "Missing categories? List them. (Skip if none.) Why I'm asking: Missing categories produce uncategorized emails downstream, which hurts triage quality."
S2.Q3: "Which category takes the MOST time per email? Why I'm asking: That's where draft-reply effort needs to focus most."

Action: Generate

email-taxonomy.md

with categories, signals (for each: trigger phrases / sender patterns / subject markers), and default actions per category.

基于章节1的内容，推荐5-7个分类——仅推荐部分分类，而非完整模板：

新机会
进行中对话
需要处理
财务相关
重要/私人
资讯类
忽略/低优先级

然后提出3个固定格式问题，逐个进行：

S2.Q1： "以下是我推荐的分类体系：[列表]。是否符合你的实际收件箱情况——是 / 基本符合 / 否？提问原因： 如果选‘否’，需要先重新调整分类体系，否则后续章节的内容都将失去意义。"
S2.Q2： "是否缺少某些分类？请列出。（无则跳过）提问原因： 遗漏的分类会导致后续出现未归类邮件，影响分类质量。"
S2.Q3： "哪个分类的单封邮件处理时间最长？提问原因： 这是回复草稿工作需要重点关注的领域。"

操作： 生成

email-taxonomy.md

文件，包含分类、每个分类的识别信号（触发短语/发件人模式/主题标记）和默认处理动作。

Section 3: Reply Style & Voice

章节3：回复风格与语气

Six grill-me questions plus the critical sample request:

S3.Q1: "Register: formal / casual / in-between? Why I'm asking: Calibrates default voice; we'll refine from samples next."
S3.Q2: "Three communication pet peeves — phrases you hate, openings you avoid. Why I'm asking: I treat these as forbidden tokens in drafts."
S3.Q3: "Phrases or sign-offs you always use — list as many as come to mind. Why I'm asking: These are your voice fingerprints."
S3.Q4: "Different persona for different contexts — e.g., assistant replies as you? Why I'm asking: Persona context changes pronoun + signature handling."
S3.Q5: "Typical reply length — one-liner / short paragraph / longer? Why I'm asking: Length is the easiest voice signal to get wrong."
S3.Q6: "Hard rules — never X / always Y? (E.g., never emojis, always reply within 24h, never take calls without context.) Why I'm asking: Hard rules are enforced as non-negotiable in every draft."

6个「grill-me」问题，加上关键的样本请求：

S3.Q1： "正式程度：正式 / 随意 / 介于两者之间？提问原因： 校准默认回复语气，后续会通过样本进一步优化。"
S3.Q2： "三个沟通禁忌——你讨厌的表述、避免使用的开场白。提问原因： 这些将被标记为草稿中的禁用内容。"
S3.Q3： "你经常使用的表述或签名——尽可能多列一些。提问原因： 这些是你的语气特征标识。"
S3.Q4： "不同场景下是否使用不同的身份——例如，助理以你的身份回复？提问原因： 身份背景会影响代词和签名的处理方式。"
S3.Q5： "典型回复长度：一句话 / 短段落 / 较长内容？提问原因： 回复长度是最容易出错的语气信号。"
S3.Q6： "硬性规则——绝对不能做/必须做的事？（例如：绝不使用表情符号，必须24小时内回复，绝不无预约接听电话）提问原因： 硬性规则会作为不可协商的要求应用于所有草稿。"

S3.SAMPLES (the critical highest-quality input)

S3.SAMPLES（最关键的高质量输入）

Paste 3–5 real sent emails from your inbox.
Why I'm asking: Self-description of voice is unreliable. Real samples are the best signal — I'll analyze them for voice patterns that supplement everything above. Use
scripts/voice_sample_analyzer.py
to extract patterns deterministically.

If user runs a business: also ask about media kits, rate sheets, standard pitches, repeated replies.

Action: Generate

email-patterns.md

with tone description (with do/don't examples), persona rules, templates, signatures, hard rules. See

references/voice_calibration.md

for the sample-extraction discipline.

粘贴3-5封你实际发送过的邮件。
提问原因： 自我描述的语气不可靠，真实样本是最佳信号——我会分析这些样本的语气模式，作为上述信息的补充。使用
scripts/voice_sample_analyzer.py
可确定性地提取模式。

如果用户经营企业：还需询问媒体资料、报价单、标准推销话术、重复使用的回复内容。

操作： 生成

email-patterns.md

文件，包含语气描述（含示例与禁忌）、身份规则、模板、签名、硬性规则。样本提取准则详见

references/voice_calibration.md

。

Section 4: Evaluation Framework (Conditional)

章节4：评估框架（可选）

Skip-logic: only run this section if Section 1 surfaced opportunity emails as a meaningful inbox category. Otherwise jump straight to Section 5.

Six grill-me questions, one at a time:

S4.Q1: "First thing you check when pitched something — give me your gut filter. Why I'm asking: That's the top of the decision tree."
S4.Q2: "Three instant deal-breakers — things that make you decline immediately. Why I'm asking: These become PASS-auto signals."
S4.Q3: "Three things that make you immediately interested. Why I'm asking: These become TAKE-IT signals."
S4.Q4: "Standard pricing / terms — or 'no fixed pricing' if you negotiate every time. Why I'm asking: If you have a rate card, I'll generate one; if not, I'll skip."
S4.Q5: "Negotiation posture: firm / flexible / depends on context? Why I'm asking: Drives draft tone on counter-offers."
S4.Q6: "VIP senders or organizations that always get engagement — list names or domains. Why I'm asking: VIP list bypasses normal PASS filters."

Action: Generate

evaluation-framework.md

(decision tree + recommendation categories + VIP list) AND

rate-card.md

if pricing exists.

跳过逻辑： 仅当章节1识别到机会类邮件是收件箱的重要分类时才运行本章节，否则直接跳至章节5。

6个「grill-me」问题，逐个提出：

S4.Q1： "收到推销邮件时你首先关注什么？说说你的直觉筛选标准。提问原因： 这是决策树的顶层规则。"
S4.Q2： "三个直接拒绝的理由——哪些情况会让你立即拒绝？提问原因： 这些将成为自动跳过的触发信号。"
S4.Q3： "三个让你立即感兴趣的点——哪些情况会让你产生兴趣？提问原因： 这些将成为重点跟进的触发信号。"
S4.Q4： "标准定价/条款——如果每次都协商则回答‘无固定定价’。提问原因： 如果有报价体系，我会生成对应的文件；否则跳过。"
S4.Q5： "谈判立场：坚定 / 灵活 / 视情况而定？提问原因： 决定还价草稿的语气。"
S4.Q6： "总能获得关注的VIP发件人或机构——列出名称或域名。提问原因： VIP列表会绕过常规的跳过筛选。"

操作： 生成

evaluation-framework.md

文件（决策树 + 推荐分类 + VIP列表），如有定价体系则同时生成

rate-card.md

文件。

Section 5: Blocklist & Patterns

章节5：黑名单与模式

Three grill-me questions, one at a time:

S5.Q1: "Senders or domains to always skip — list them. (Skip if none.) Why I'm asking: Auto-blocklist saves the most time per run."
S5.Q2: "Patterns in emails you always delete — e.g., 'unsubscribe' links from specific marketers, recruiter cold outreach, newsletters? Why I'm asking: Patterns let triage auto-skip variants without exact-match maintenance."
S5.Q3: "Specific companies / recruiters / newsletters wasting time — list any. Why I'm asking: These seed the blocklist; triage will add more as you override decisions."

Action: Generate

blocklist.md

(auto-maintained by triage thereafter).

3个「grill-me」问题，逐个提出：

S5.Q1： "需要永远跳过的发件人或域名——列出。（无则跳过）提问原因： 自动黑名单能为每次运行节省大量时间。"
S5.Q2： "你总会删除的邮件模式——例如：特定营销商的‘取消订阅’链接、招聘人员的冷邮件、新闻通讯？提问原因： 模式匹配能让分类系统自动跳过变体，无需维护精确匹配规则。"
S5.Q3： "浪费你时间的特定公司/招聘人员/新闻通讯——列出。提问原因： 这些将作为黑名单的初始内容；后续分类系统会根据你的手动调整不断补充。"

操作： 生成

blocklist.md

文件（后续分类系统会自动维护该文件）。

Section 6: Current State

章节6：当前状态

Three grill-me questions, one at a time:

S6.Q1: "Active threads you're tracking — list with one-line context each. (Skip if none.) Why I'm asking: These become tracker entries so triage knows existing context."
S6.Q2: "Overdue replies — anything you should have responded to but haven't? Why I'm asking: Triage flags these as priority every run until resolved."
S6.Q3: "Time-sensitive items with deadlines — list with dates. Why I'm asking: Tracker enforces deadlines and surfaces them as overdue at the right time."

Action: Generate

tracker.md

with active follow-ups table, overdue section, resolved section (empty), update log (empty). Also create empty

triage-log/

directory.

3个「grill-me」问题，逐个提出：

S6.Q1： "你正在跟进的活跃线程——每个用一句话说明背景。（无则跳过）提问原因： 这些将被添加到跟踪列表中，让分类系统了解已有上下文。"
S6.Q2： "逾期未回复的邮件——有没有你本该回复但还没回复的内容？提问原因： 分类系统每次运行都会将这些标记为优先级事项，直到处理完成。"
S6.Q3： "有截止日期的时间敏感事项——列出日期。提问原因： 跟踪列表会强制执行截止日期，并在合适的时间将其标记为逾期。"

操作： 生成

tracker.md

文件，包含跟进中事项表格、逾期项章节、已完成章节（空）、更新日志（空）。同时创建空的

triage-log/

目录。

Section 7: Report Preferences

章节7：报告偏好

Three grill-me questions, one at a time:

S7.Q1: "Delivery format — pick one: email draft to self / file in workspace / chat summary only. Why I'm asking: The triage report goes here every run."
S7.Q2: "Detail level — pick one: 30-second scan / detailed breakdown / both (scan first, expand on request). Why I'm asking: Affects report length."
S7.Q3: "Anything always shown first — e.g., overdue payments, VIP messages? Why I'm asking: Custom 'top-of-report' rules surface what you care about above standard sections."

Action: Save these preferences into

email-taxonomy.md

under a "Report Preferences" section.

3个「grill-me」问题，逐个提出：

S7.Q1： "交付格式——选择一种：给自己发邮件草稿 / 保存到工作区文件 / 仅聊天摘要。提问原因： 分类报告每次运行都会发送到指定位置。"
S7.Q2： "详细程度——选择一种：30秒快速浏览 / 详细 breakdown / 两者兼具（先快速浏览，按需展开）。提问原因： 影响报告长度。"
S7.Q3： "需要始终优先显示的内容——例如：逾期付款、VIP消息？提问原因： 自定义‘报告顶部’规则会将你关注的内容显示在标准章节之前。"

操作： 将这些偏好设置保存到

email-taxonomy.md

文件的「报告偏好」章节中。

Section 8: Confirmation & Handoff

章节8：确认与交接

List every file created with one-sentence summary. Then:

Your triage system is ready. Run the inbox-triage skill to process your inbox. First runs need oversight — system learns from your edits and overrides.

Remind: re-run this setup anytime business/pricing/priorities change.

Run

scripts/kb_validator.py --workspace ${WORKSPACE}

to confirm the 7-file contract is satisfied before final handoff.

列出已创建的所有文件并附上一句话说明。然后：

你的分类系统已准备就绪。运行inbox-triage技能即可处理你的收件箱。首次运行需要监督——系统会从你的编辑和手动调整中学习。

提醒：当业务/定价/优先级发生变化时，可重新运行本设置技能。

在最终交接前，运行

scripts/kb_validator.py --workspace ${WORKSPACE}

确认7个文件的约定已满足。

Privacy Boundary

隐私边界

Never persist passwords, full account numbers, SSNs, or other sensitive credentials in knowledge base files. If the user volunteers such info during the interview, acknowledge it but don't store it; the relevant KB file gets

[stored separately by user]

in its place.

绝不在知识库文件中存储密码、完整账号、社保号或其他敏感凭证。如果用户在访谈中提供此类信息，需确认收到但不存储；相关知识库文件中对应位置将标记为

[由用户单独存储]

。

Re-Run Behavior

重新运行行为

Re-running on an existing setup:

Detect
```
${WORKSPACE}/Email/
```
For each existing file, ask per-file: replace / merge / skip
Walk only the sections whose files the user chose to update
Skip sections whose files the user kept

在已有设置上重新运行时：

检测
```
${WORKSPACE}/Email/
```
路径
针对每个现有文件，询问用户：替换 / 合并 / 跳过
仅处理用户选择更新的文件对应的章节
跳过用户选择保留的文件对应的章节

Error Handling

错误处理

Situation	Behavior
Workspace inaccessible	Stop. Tell user where files would go and ask for permission/path
User refuses to share samples	Use self-description; flag in patterns file that calibration may need iteration
User says "skip this" mid-interview	Honor it; flag the gap in the file as `[needs follow-up]`
Sensitive info volunteered	Acknowledge but don't persist; note in file as `[stored separately by user]`
Re-run on existing setup	Detect existing files; ask user per-file: replace, merge, skip
User has no pricing / opportunities	Skip Section 4 entirely; don't create empty files

场景	处理方式
工作区无法访问	停止操作。告知用户文件的预期存储路径，并请求权限/正确路径
用户拒绝提供样本	使用用户自我描述的信息；在模式文件中标记校准可能需要迭代优化
用户中途说“跳过这个”	执行跳过操作；在文件中标记该缺口为 `[需后续补充]`
用户提供敏感信息	确认收到但不存储；在文件中标记为 `[由用户单独存储]`
在已有设置上重新运行	检测现有文件；针对每个文件询问用户：替换、合并、跳过
用户无定价/机会类邮件	完全跳过章节4；不创建空文件

Portability

可移植性

Claude Code CLI: Native — writes markdown files directly to filesystem.
Claude.ai web: Works with project files / artifacts. Document the alternate path: generate files as artifacts, instruct user to save to their workspace, or use connected file system if available.

Claude Code CLI： 原生支持——直接将markdown文件写入文件系统。
Claude.ai网页版： 可配合项目文件/工件使用。需说明替代路径：生成文件作为工件，指导用户保存到自己的工作区，或使用可用的连接文件系统。

Tooling

工具集

Script	Role
`scripts/kb_validator.py`	Validates the 7-file KB output (required files present, conditional files only if their sections ran, headers + structure correct).
`scripts/section_progress_tracker.py`	JSON-backed walk state at `~/.inbox_setup_sessions/<session>.json` . Tracks active section, answered questions, committed files.
`scripts/voice_sample_analyzer.py`	Extracts voice patterns from pasted sent-email samples — opening phrases, sign-offs, length distribution, register markers.

脚本	作用
`scripts/kb_validator.py`	验证7个文件的知识库输出（必填文件是否存在，可选文件仅在对应章节运行时生成，标题+结构是否正确）。
`scripts/section_progress_tracker.py`	基于JSON的流程状态存储在 `~/.inbox_setup_sessions/<session>.json` 。跟踪当前章节、已回答问题、已提交文件。
`scripts/voice_sample_analyzer.py`	从粘贴的已发送邮件样本中提取语气模式——开场白、签名、长度分布、正式程度标记。

References

参考资料

```
references/kb_file_contract.md
```
— the canonical 7-file contract (write perspective; mirror lives in
```
inbox-triage/references/
```
)
```
references/grill_me_section_walk.md
```
— 8-section discipline, skip-logic, commit-per-section
```
references/voice_calibration.md
```
— sample-based voice extraction theory + anti-patterns

```
references/kb_file_contract.md
```
— 标准7文件约定（编写视角；镜像文件位于
```
inbox-triage/references/
```
）
```
references/grill_me_section_walk.md
```
— 8章节准则、跳过逻辑、逐章提交规则
```
references/voice_calibration.md
```
— 基于样本的语气提取理论 + 反模式

Anti-Patterns To Reject

需避免的反模式

Generating all files at once instead of walking through sections
Asking all questions in one batch
Hardcoded provider references (Gmail-only thinking)
Persisting sensitive credentials in knowledge base
Skipping the "why this question matters" explanation
Skipping the sample-emails ask for voice (it's the highest-quality input)
Overwriting existing files without consent on re-run
Forcing creation of
```
rate-card.md
```
or
```
evaluation-framework.md
```
when they don't apply

Version: 1.0.0 Source spec:

megaprompts/06-inbox-setup-megaprompt.md

Build pattern: Path B (direct conversion). Paired with

inbox-triage

一次性生成所有文件而非逐章完成
批量提出所有问题
硬编码特定服务商引用（仅考虑Gmail的思维）
在知识库中存储敏感凭证
跳过“问题重要性说明”环节
跳过请求邮件样本以校准语气（这是最高质量的输入）
重新运行时未经同意覆盖现有文件
强制生成
```
rate-card.md
```
或
```
evaluation-framework.md
```
文件（当不适用时）

版本： 1.0.0 源规范：

megaprompts/06-inbox-setup-megaprompt.md

构建模式： Path B（直接转换）。与

inbox-triage

配套使用。