DTC Daily Ops Router独立站每日经营与竞对雷达

1. One router, deterministic execution and a review queue一个总入口、确定性执行与待审核队列

The natural-language skill is only the entry and routing contract. Scheduling, run locks, retries, hashing, schema validation, baseline pointers and file output belong in a deterministic runner. Platform-specific access stays inside connectors, and every real external write remains outside the daily collection job.

自然语言 Skill 只负责说明入口、路由和完成标准。定时、任务锁、重试、哈希、数据校验、历史基线和文件落盘，应由确定性的 Runner 执行。不同平台的访问逻辑放在各自连接器里，所有真实外部写入都不属于每日采集任务。

QoderWork CN schedule / command
  -> dtc-daily-ops-router
  -> deterministic daily runner
  -> tenant + seat policy / credit guard
  -> SellerSprite + owned + competitor connectors
  -> SignalEvent + AuditEvent evidence ledgers
  -> ProductCandidate auto-selection
  -> MultimodalOutreachPack per creator
  -> DingTalk selection brief / Feishu outreach queue
  -> credit ledger + delivery receipt + read-back

The product is not “more scraping.” The product is a daily, evidence-linked decision record that makes missing coverage visible.这个系统的产品价值不是“多抓一些数据”，而是每天形成一份证据可追溯、数据缺口也清楚可见的经营判断记录。

2. Eight modules with separate responsibilities八个职责清楚的模块

3. Eight gates that every daily run must pass每日运行必须经过的八个关卡

4. Public competitor signals and owned metrics are different products竞品公开信号与自有经营数据是两类不同数据

The source contract distinguishes owned_authorized, competitor_official_public, public_observation and inferred. A number never moves between these scopes without retaining its original definition.

数据契约明确区分 owned_authorized、competitor_official_public、public_observation 与 inferred。任何数字跨表使用时，都必须保留它原来的来源和定义。

Commerce truth rule: Shopify is the transaction ledger for owned orders, refunds and inventory. GA4 and each advertising platform keep their own attribution basis and maturity state; attributed conversions are not added together as store orders.经营事实规则：自有订单、退款和库存以 Shopify 交易记录为主账。GA4 与各广告平台保留各自的归因口径和数据成熟度，平台归因转化不能相加后当作店铺真实订单。

5. Five operating contracts, one access policy and two governance ledgers五类业务契约、一份权限策略与两本治理账

observed evidence
  -> explicit interpretation
  -> proposed action
  -> pending_human_review
  -> approved operator execution
  -> read-back verification

6. No-manual product selection and evidence-led creator activation无人手工选品与基于证据的达人多模态建联

The current operating route uses QoderWork CN as the orchestrator, SellerSprite as an authorized product, keyword and review evidence source, DingTalk CLI as the internal selection-delivery surface, and Feishu CLI as the batch creator-work queue. “No manual selection” means the daily run does not rely on a person browsing products and picking favorites; administrators own the policy and hard thresholds, while the runner makes the candidate decision deterministically.

当前运营链路由 QoderWork CN 负责编排，卖家精灵提供已授权范围内的商品、关键词与评论证据，钉钉 CLI 承接选品结果的内部交付，飞书 CLI 管理红人批量建联任务。“无人手工选品”指每日运行不再依赖运营逐个浏览商品、凭感觉挑选；管理员负责制定规则与硬门槛，Runner 按同一套标准自动产生选品结论。

QoderWork CN
  -> SellerSprite evidence snapshot
  -> ProductCandidate hard gates + ranking
  -> AUTO_SELECTED / REJECTED_HARD_GATE / NEEDS_FRESH_DATA
  -> DingTalk CLI selection brief

Creator evidence + Product Truth Card
  -> MultimodalOutreachPack
  -> Feishu CLI batch work queue
  -> approved external channel
  -> delivery / reply / follow-up read-back

Automation boundary: there is no manual SKU picking inside the daily selection run, but procurement, samples, supplier outreach, Listing publication and advertising spend remain separate approved actions. Creator research and multimodal package generation can run in batch; outbound contact requires an approved roster, lawful contact basis, channel policy, rate limits and suppression handling. Tool access and connector methods must be verified per deployment.自动化边界：每日选品运行内部不再人工挑 SKU，但采购、寄样、供应商外联、Listing 发布和广告花费仍是独立审批动作。达人研究与多模态合作包可以批量生成；对外建联必须基于已批准名单、合法联系依据、渠道规则、频率限制和排除机制。QoderWork CN、卖家精灵、钉钉与飞书 CLI 的具体访问方式和权限范围，需要在每次实施时真实核验。

ChatGPT referral and GEO loop: validated ChatGPT sessions and orders become demand evidence for query coverage and product selection; Product Truth then keeps the PDP, structured data, feeds and creator packs aligned. See the detailed ChatGPT Commerce GEO method for attribution states, crawl controls, feed freshness, experiments and conversion-quality measurement.ChatGPT 来单与 GEO 闭环：已验证的 ChatGPT 会话与订单，作为查询覆盖和选品的需求证据；Product Truth 再让 PDP、结构化数据、Feed 与达人多模态合作包保持一致。订单归因状态、抓取权限、Feed 新鲜度、实验与转化质量的详细方法，见 ChatGPT 电商 GEO 方法论。

7. Enterprise teams need a control plane, not shared credentials企业团队需要权限控制面，而不是共用店铺凭证

Enterprise access is evaluated per tenant, acting seat, assigned store, connector, action and validity period. Effective access is the narrowest intersection of role, store assignment, connector scope, approval policy, credit budget and time window—not whatever a logged-in browser happens to expose.

企业版权限不能只看“账号是否已经登录”，而要同时限定企业、操作席位、店铺、数据源、可执行动作、credits 额度与有效期。一个席位最终能做什么，取决于角色、店铺分配、连接器权限、审批规则、额度和有效期的最小交集，不能继承浏览器中碰巧存在的更大权限。

Tenant Admin connects store
  -> server-side credential reference
  -> seat receives scoped AccessGrant
  -> tenant + store + role + action + credit check
  -> approval when required
  -> AuditEvent + CreditLedgerEntry
  -> read-back verification or explicit revoke state

Enterprise status boundary: these are implementation requirements, not a claim that seat enforcement, complete audit coverage, ZiNiao or other managed-browser security, credit allocation or automatic offboarding is already deployed. This system cannot guarantee the security of a third-party browser. Audit coverage includes only activity this system observes or initiates; direct platform activity depends on each platform's own logs. Credit limits govern this system's credits, not advertising spend or third-party fees. Revocation is complete only after every connected system confirms it.企业版状态边界：以上是实施时必须达到的控制标准，不代表席位强制管控、完整审计、紫鸟等受管浏览器安全、额度分配或自动离职撤权已经上线；本系统也不能为第三方浏览器的安全性作保证。审计只能覆盖本系统观察到或发起的动作，绕开本系统的直接平台操作仍需依赖对应平台日志；credits 上限只约束本系统额度，不等于限制广告花费或第三方费用；只有所有连接系统都回读确认后，撤权才算完成。

8. The daily brief should take five minutes to read每日简报应在五分钟内读完

1. Owned-store red lights: page, checkout, inventory, tracking or connector failures that need attention first.自有站红灯：需要优先处理的页面、结账、库存、埋点或连接器问题。
2. Top external movements: the most relevant storefront, social, media and public-ad changes.外部重点变化：与当前业务最相关的竞品网站、社媒、媒体和公开广告动作。
3. Owned performance context: store-truth outcomes and platform metrics with attribution and maturity labels.自有表现背景：店铺真实交易结果，以及标明归因口径与成熟度的平台数据。
4. Review and search gaps: new recurring customer language connected to an owned search term, PDP or Listing hypothesis—not an automatic rewrite.评论与搜索缺口：把最新高频用户表达对应到自己的搜索词、PDP 或 Listing 优化假设，但不自动改写线上内容。
5. At most three actions: fix, test or keep watching—with owner, evidence and acceptance metric.最多三个动作：今天该修什么、测试什么或继续观察什么，并写清负责人、依据与验收指标。
6. Team-control exceptions: role or seat changes, expiring grants, blocked scope attempts, privileged operations, credit use against assigned caps and pending revocations.团队管控异常：角色或席位变更、即将到期的授权、越权尝试、重要操作、credits 相对配额的使用情况，以及尚未完成的撤权。
7. Data boundaries: sources that were blocked, stale, unsupported or not configured.数据边界：今天哪些来源受限、过期、不支持或尚未配置。

If successful coverage is zero, the report becomes an access-limited operating alert. It must not recycle historical signals into a new competitor conclusion.如果本次成功采集为零，日报只能输出访问受限告警；不得把历史信号重新包装成今天的新竞品结论。

9. Read-only collection first; execution requires approval先只读采集，真实执行必须经过审批

• Automatically allowed: permitted reading, snapshots, hashing, normalization, comparison, calculations, local reports and alerts to a pre-approved destination—only within the acting seat's tenant, store and source scopes.可以自动完成：合规读取、快照、哈希、规范化、变化比较、计算、本地报告，以及发送到预先批准目的地的告警，但不得超出当前席位所属企业、店铺和数据源范围。
• Human approval required: changes to storefronts, prices, inventory, content, advertising budgets, bids, targeting, campaign state, outreach or publishing. Operator, approver and read-back outcome enter the audit trail.必须人工批准：修改网站、价格、库存、内容、广告预算、竞价、受众、活动状态，以及对外联系或发布；操作者、审批人和回验结果都要进入审计日志。
• No credential sharing: seats cannot view, export or reuse another seat's password, token, cookie or browser session. Possession of a browser profile does not grant store authority.不共享凭证：子席位不能查看、导出或复用其他席位的密码、令牌、Cookie 或浏览器会话；拿到浏览器环境不等于获得店铺权限。
• No hidden credit spend: paid work is charged to an approved seat, store or project cap. Reaching the limit stops the paid step or requests administrator approval; it never triggers a silent purchase.不隐形消耗 credits：付费任务必须计入已批准的席位、店铺或项目配额；达到上限后停止付费步骤或请求管理员批准，不得静默加购。
• No blind outreach or identity fabrication: batch creator work must deduplicate contacts, respect rate limits and suppression lists, and preserve review before send. Multimodal personalization may adapt a truthful SKU story to a creator's public audience context; it cannot clone a creator's face or voice, claim a past partnership or invent product use.不盲发、不伪造身份：红人批量建联必须去重、限频、遵守停止联系名单，并在发送前保留审核。多模态定制可以按达人公开受众语境改写真实 SKU 叙事，但不得克隆达人脸部或声音、伪称既往合作，也不得虚构使用经历。
• No access-control bypass: no login-wall, CAPTCHA, private-account, robots or platform-rate-limit circumvention.不绕过访问控制：不绕登录墙、验证码、私密账号、robots 规则或平台限流。
• No competitor result invention: ad duration, likes or creative repetition do not prove spend, sales, conversion, profitability or winning creative.不编造竞品成绩：投放时长、点赞量或素材重复使用，不能证明花费、销量、转化、盈利或“爆款”。
• Current status: this page is a reviewed design specification. It does not claim that every listed API connector, scheduled job or delivery integration is already deployed.当前状态：本页是已经整理完成的系统设计规范，不声称其中每个 API 连接器、定时任务或交付集成都已经部署。

Primary platform references主要平台依据

• YouTube Data API — Channels
• Meta — Instagram Business Discovery
• Meta Ad Library
• TikTok Commercial Content API
• Google Ads Transparency Center
• Shopify Admin GraphQL — Orders
• GA4 — Reporting data expectations
• Google Search Console — Performance data