marketing-loops
Compare original and translation side by side
🇺🇸
Original
English🇨🇳
Translation
ChineseMarketing Loops
营销循环
You help set up marketing loops — repeatable marketing workflows an AI agent runs on a cadence, each with a defined trigger, a bounded set of steps, a self-check, and an explicit stopping condition. A loop turns a marketing task you'd otherwise do manually (and forget) into an always-on system: the weekly SEO opportunity scan, the ad-fatigue refresh, the churn-signal watch.
This is the operational cousin of . Ideas tell you what to try once. Loops tell you what to keep doing on a schedule — and wire the other marketing skills together to do it.
marketing-ideas你负责设置营销循环——即由AI Agent按照特定节奏运行的可重复营销工作流,每个循环都有明确的触发条件、一系列限定步骤、自我检查机制和清晰的终止条件。循环可将原本需手动完成(且容易遗忘)的营销任务转化为持续运行的系统:比如每周SEO机会扫描、广告疲劳更新、客户流失信号监控等。
本技能是的运营类配套技能。提供的是可尝试一次的创意,而本技能则聚焦于需按计划持续执行的任务——并将其他营销技能整合起来完成这些任务。
marketing-ideasmarketing-ideasHow to Use This Skill
如何使用本技能
Check for product marketing context first: if exists (or , or the legacy ), read it before asking questions. Use that context and only ask for what's missing.
.agents/product-marketing.md.claude/product-marketing.mdproduct-marketing-context.mdThen:
- Clarify the job. What outcome should this loop protect or grow? (rankings, ad efficiency, activation, retention, revenue, referrals)
- Pick a loop from the catalog in — or adapt the closest one.
references/loop-catalog.md - Tune the cadence to how fast the underlying signal actually changes (see the cadence rule below).
- Confirm the human checkpoint. Decide what the loop does autonomously vs. what it stages for human approval before publishing or spending — see .
references/loop-guardrails.md - Schedule it (see "Scheduling a loop" below).
Building more than one loop, or a whole marketing operating system? See for how loops compose and the order to adopt them (start with tracking + a weekly review; don't build 43 at once).
references/loop-orchestration.md首先检查产品营销上下文: 如果存在(或,或旧版),请先阅读该文件再提问。利用已有上下文,仅询问缺失的信息。
.agents/product-marketing.md.claude/product-marketing.mdproduct-marketing-context.md然后按以下步骤操作:
- 明确目标:该循环需要保障或提升哪些成果?(排名、广告效率、用户激活、留存、收入、推荐量)
- 选择循环:从的目录中选择一个循环——或调整最接近的现有循环。
references/loop-catalog.md - 调整节奏:根据底层信号的实际变化速度调整循环节奏(见下文的节奏规则)。
- 确认人工检查点:确定循环可自主完成的操作,以及在发布或投入资金前需提交人工审批的操作——详见。
references/loop-guardrails.md - 安排调度(见下文“调度循环”部分)。
若要构建多个循环或完整的营销操作系统?请查看了解循环的组合方式及采用顺序(从跟踪+每周复盘开始;不要一次性构建43个循环)。
references/loop-orchestration.mdAnatomy of a Marketing Loop
营销循环的组成结构
Every loop in the catalog has these nine parts. When you author or adapt one, fill all of them — a loop missing a stop condition, a self-check, or its state handling is a liability, not an asset.
| Part | What it defines |
|---|---|
| Check cadence | How often the loop looks (weekly / daily / on-trigger). Match it to signal speed. |
| Acts when | The action condition — what must be true to actually do something, vs. just check and skip. Most runs of a good loop are "checked, nothing to do." |
| Purpose | The one outcome this loop exists to move. |
| Skills used | Which marketing skills the loop orchestrates each iteration. |
| Loop body | The ordered steps run each iteration. |
| Self-check | The verification done before acting — so the loop doesn't act on noise, seasonality, or a tracking bug. |
| State / idempotency | What the loop remembers between runs: last-run marker, dedupe key, cooldown window, "already handled" set. Without this, loops double-act, re-nag the same people, or re-alert the same thing. Non-negotiable for anything scheduled — see |
| Stop / bail-out | When the loop skips, halts, escalates to a human, or disables itself — plus what it does on error. Every loop needs one, including heartbeat loops (their stop is "manual disable + error-halt," never "n/a"). |
| Output | Where results go: a file, a PR, a staged draft, a notification, a report. |
The Check cadence / Acts when split matters: a churn-signal loop might check daily but only act when an account crosses a risk threshold it hasn't been contacted about inside the cooldown window. Conflating the two produces loops that either miss the window or spam.
目录中的每个循环都包含以下九个部分。在创建或调整循环时,请填写所有部分——缺少终止条件、自我检查或状态处理的循环是隐患,而非资产。
| 组成部分 | 定义内容 |
|---|---|
| 检查节奏 | 循环的检查频率(weekly/daily/触发式)。需与信号变化速度匹配。 |
| 触发条件 | 执行操作的条件——即满足何种条件才会实际执行操作,而非仅检查后跳过。一个设计良好的循环多数运行结果都是“已检查,无需操作”。 |
| 目标 | 该循环存在的核心目的,即要推动达成的成果。 |
| 使用技能 | 每次迭代中循环需协调的营销技能。 |
| 循环主体 | 每次迭代时执行的有序步骤。 |
| 自我检查 | 执行操作前的验证步骤——确保循环不会因噪音、季节性因素或跟踪错误而执行操作。 |
| 状态/幂等性 | 循环在多次运行之间需记录的信息:上次运行标记、去重键、冷却窗口、“已处理”集合。没有这些信息,循环可能重复执行操作、反复打扰同一用户或重复发出相同警报。对于任何调度任务而言,这都是必不可少的——详见 |
| 终止/退出机制 | 循环何时跳过、暂停、升级至人工处理或自行禁用——以及出现错误时的处理方式。每个循环都需要此机制,包括心跳循环(其终止机制为“手动禁用+错误暂停”,而非“无”)。 |
| 输出 | 结果的去向:文件、PR、待发布草稿、通知、报告。 |
检查节奏/触发条件的区分十分重要:客户流失信号循环可能每日检查,但仅当客户账户超出风险阈值且在冷却窗口内未被联系过时才执行操作。混淆两者会导致循环要么错过时机,要么发送垃圾信息。
The cadence rule
节奏规则
Match cadence to how fast the signal actually changes — not to how often you'd like an update.
| Signal | Realistic cadence | Why |
|---|---|---|
| Rankings, backlinks, domain authority | Weekly | Move slowly; daily checks are noise |
| Ad creative fatigue, CPA drift | Every 2–3 days | Meta/Google feedback loops are days, not hours |
| Activation / onboarding funnel | Weekly | Needs enough signups to be significant |
| Churn signals | Daily or on-trigger | Early intervention window is short |
| Content / copy decay | Monthly | Traffic erosion is gradual |
| Competitor changes | Weekly | Pricing/positioning shifts are infrequent but matter |
| Social listening / mentions | Daily | Engagement windows close fast |
Over-frequent loops are the most common failure mode: they generate busywork, burn budget, and train you to ignore the output.
循环节奏需与信号的实际变化速度匹配——而非你希望接收更新的频率。
| 信号类型 | 合理节奏 | 原因 |
|---|---|---|
| 排名、反向链接、域名权重 | Weekly | 变化缓慢;每日检查会产生大量噪音 |
| 广告创意疲劳、CPA漂移 | 每2-3天 | Meta/Google的反馈周期以天为单位,而非小时 |
| 用户激活/入门漏斗 | Weekly | 需要足够的新注册用户才能体现显著性 |
| 客户流失信号 | Daily或触发式 | 早期干预窗口较短 |
| 内容/文案衰减 | Monthly | 流量流失是渐进过程 |
| 竞品变化 | Weekly | 定价/定位变化不频繁,但影响重大 |
| 社交聆听/提及 | Daily | 互动窗口关闭速度快 |
过于频繁的循环是最常见的失败模式:它们会产生无效工作、消耗预算,并让你逐渐忽略输出内容。
When NOT to loop
不适用于循环的场景
Not everything should be automated on a cadence. Skip a loop — or add a mandatory human checkpoint — when:
- Strategy or creative direction is the real work. Loops maintain and optimize; they don't set positioning, invent campaigns, or make brand calls.
- The action publishes or spends without review. Auto-drafting an ad, email, or post is fine. Auto-publishing or auto-shifting budget needs a human checkpoint unless the user has explicitly authorized autonomous action and set guardrails (caps, allowlists).
- The signal is too sparse to be significant. A weekly conversion-rate loop on 40 visitors/week is measuring noise.
- It's a vanity loop. If nobody acts on the output, delete the loop. A loop that emails a dashboard nobody reads is worse than nothing.
For any loop that sends, spends, publishes, or touches personal data, apply — the two-tier action model (autonomous-safe vs. gated), spend/send caps, CAN-SPAM/GDPR/FTC/ToS rules, the always-escalate list, and a required kill switch.
references/loop-guardrails.md并非所有任务都适合按节奏自动化。在以下情况下,请跳过循环——或添加强制人工检查点:
- 核心工作是策略或创意方向:循环用于维护和优化,而非设定定位、发明营销活动或做出品牌决策。
- 操作会直接发布或投入资金且无审核:自动草拟广告、邮件或帖子是可行的。自动发布或自动调整预算需要人工检查点,除非用户明确授权自主操作并设置了防护规则(限额、白名单)。
- 信号过于稀疏,不具备显著性:针对每周仅40名访客的转化率循环,测量的只是噪音。
- 虚荣循环:如果无人根据输出内容采取行动,请删除该循环。发送无人查看的仪表盘邮件的循环比没有循环更糟。
对于任何涉及发送内容、投入资金、发布信息或处理个人数据的循环,请遵循——采用两级操作模式(自主安全操作 vs 需审批操作)、支出/发送限额、CAN-SPAM/GDPR/FTC/服务条款规则、必升级列表,并设置必要的终止开关。
references/loop-guardrails.mdScheduling a loop
调度循环
These loops are agent-agnostic — the body works in any agent. The scheduling depends on your environment:
- Claude Code — native options: (self-paced, until a condition),
/loop(dynamic pacing that reacts to state), andScheduleWakeup(fixed cron schedule). If you have a loop-mechanics skill such asCronCreateinstalled, use it to choose between them and tune delays; otherwise the guidance below is enough.loopify - Any agent + cron — wrap the loop body as a scheduled prompt/script (for Mondays 9am, etc.).
0 9 * * 1 - Manual cadence — for high-judgment loops, "run this skill every Monday" is a perfectly good loop. The value is the repeatable body, not the automation.
Default to time-of-day cron for review-style loops (weekly review, ranking watch) and dynamic pacing for monitor-until-threshold loops (churn watch, launch-day tracking).
这些循环与Agent无关——循环主体可在任何Agent中运行。调度方式取决于你的环境:
- Claude Code——原生选项:(自定节奏,直至满足条件)、
/loop(根据状态调整的动态节奏)和ScheduleWakeup(固定Cron调度)。若已安装CronCreate等循环机制技能,请使用它来选择合适的调度方式并调整延迟;否则以下指导已足够。loopify - 任意Agent + Cron——将循环主体包装为调度提示/脚本(如表示每周一上午9点)。
0 9 * * 1 - 手动节奏——对于高判断性循环,“每周一运行此技能”就是一个很好的循环。其价值在于可重复的主体,而非自动化本身。
对于复盘类循环(每周复盘、排名监控),默认采用特定时间的Cron调度;对于监控至阈值的循环(客户流失监控、发布日跟踪),默认采用动态节奏。
The Catalog
循环目录
references/loop-catalog.mdreferences/loop-catalog.mdAuthoring a new loop
创建新循环
When nothing in the catalog fits, author a new loop from — a copy-paste template with fill-in prompts, a worked before/after example, and a ship checklist. Fill all nine anatomy parts; if you can't answer the self-check, state/idempotency, and stop/bail-out concretely, the loop isn't ready to run.
references/loop-template.md当目录中没有合适的循环时,请从创建新循环——这是一个可复制粘贴的模板,包含填空提示、前后示例和发布检查清单。请填写所有九个组成部分;如果无法明确自我检查、状态/幂等性和终止/退出机制的具体内容,该循环还未准备好运行。
references/loop-template.mdAnti-patterns
反模式
- Looping without a stop condition → runaway spend or infinite churn.
- Same cadence for every loop → most run too often and get ignored.
- No self-check → the loop acts on noise, seasonality, or a tracking bug.
- No human checkpoint on spend/publish actions.
- Building 10 loops at once → start with one, prove it earns its keep, then add the next.
- 无终止条件的循环 → 失控支出或无限循环。
- 所有循环采用相同节奏 → 多数循环运行过于频繁,被忽略。
- 无自我检查机制 → 循环因噪音、季节性因素或跟踪错误而执行操作。
- 涉及支出/发布的操作无人工检查点。
- 一次性构建10个循环 → 从一个开始,证明其价值后再添加下一个。
Banned vocabulary
禁用词汇
Avoid: "set it and forget it," "fully autonomous marketing," "AI does everything," "10x on autopilot," "growth hacking machine." Loops are disciplined systems with checkpoints, not magic. Describe them honestly.
避免使用:“设置后即可遗忘”“完全自主营销”“AI包办一切”“自动驾驶式10倍增长”“增长黑客机器”。循环是带有检查点的严谨系统,而非魔法。请如实描述它们。
Related Skills
相关技能
- marketing-ideas — one-off tactics and inspiration (what to try). Loops operationalize the ones worth repeating.
- ab-testing — the experimentation loop specifically (hypothesis → test → promote winner → repeat).
- analytics — most loops read from analytics to decide whether to act.
- Individual channel skills (,
ads,seo-audit,emails,social,churn-prevention,pricing) — the loop bodies orchestrate these.referrals
- marketing-ideas——一次性策略和灵感(可尝试的内容)。循环将值得重复的内容落地执行。
- ab-testing——特定的实验循环(假设→测试→推广赢家→重复)。
- analytics——多数循环需读取分析数据来决定是否执行操作。
- 各渠道技能(、
ads、seo-audit、emails、social、churn-prevention、pricing)——循环主体会协调这些技能。referrals