Grok Bot销售增长营收AI 评分 · 72/100AI 辅助编辑·未发现明显提示词注入风险GitHub

常青内容飞轮:自动识别衰减旧文并按修复性价比排序

输入历史发布内容库 → 对比90天周期数据找出衰减文章 → 输出按修复工时性价比排序的待刷新草稿清单

有一点经验步骤流程提示词
给谁
需要维护大量历史内容、希望用最小工时获取最大流量回升的内容运营者或营销团队
你会得到
每周五自动筛选出值得二次发布的衰减内容,按修复工时性价比排序,仅生成未排期草稿,不自动发布
你需要
feedhive · notion · slack

硬约束

前置条件:拥有 FeedHive(或同类内容库)、Notion(或同类草稿存储)、Slack 工作区访问权限;已配置 grok-bot 运行时。一次性初始化时需确认账户、内容库、成功标准、最低年龄门槛(90天)及禁止回收主题。此后每周五自动运行。已知限制:工具名仅为来源建议,不代表已配置连接器;底层模型版本未注明;本站未实测。

他们做了什么

来源作者 PramodDutta(botskills.sh)发布了一个名为 Evergreen Content Flywheel 的 MIT 许可模板,定义了一个每周五运行的 bot 角色协议。该协议要求 bot 从已发布内容库中筛选超过90天且曾达到成功标准的内容,对比最近两个90周期的 impressions 与 engagement per impression 测量衰减,核查事实准确性,按修复工时性价比排序,通过 Slack DM 报告最多5项,并仅生成一项未排期草稿。

效果如何

来源未提供实际运行效果数据。模板描述其功能为'Finds published pieces whose traffic has decayed and ranks them by recovery per hour of work, so refreshes go where the payback is'(author_report: template_description_only)。

值得知道

硬边界(来源原文):Never publishes or schedules a recycled post; drafts stay unscheduled with no slot time until you release them yourself. 自动化发布可能违反平台条款并危及账户安全。工具名 feedhive、notion、slack 仅为来源建议标签,不代表已配置 API 连接器。底层模型版本未在来源注明。本站未实测,复现前需自行验证各平台数据读取权限与 Slack DM 发送能力。

步骤

  1. 一次性初始化:设定筛选基准

    与 bot 共同确认以下参数,仅需执行一次:内容账户与库位置、历史成功标准(何种指标算'赢')、最低年龄门槛(默认90天,自发布或上次刷新起算)、禁止回收主题(如发布 announcement、 dated pricing、已离职人员相关内容)。

    搭建指导 · 来源原文。初始化对话,配置 bot 的长期记忆或环境变量

    Set the bar with me once. Which accounts and which library, what counted as a win when it ran, the minimum age (90 days since publish or last refresh), and the topics that must never be recycled such as launch announcements, dated pricing, and anything featuring someone who has left.
  2. 构建候选池

    筛选超过最低年龄门槛且曾达到成功标准的内容。从未表现的内容不属于'衰减',应排除。

    运行提示词 · 来源原文。bot 执行指令:内容库查询与筛选

    Build the candidate pool. Every piece past the minimum age that once cleared the win bar. A piece that never performed is not decayed, it is dead, and it does not belong in this pool.
  3. 测量单篇衰减

    对比每篇候选内容最近90天与前90天的 impressions 和 engagement per impression。记录原始数值、百分比变化及数据来源。禁止估算无法读取的数值。

    运行提示词 · 来源原文。bot 执行指令:数据分析与衰减计算

    Measure decay per piece. Compare the last 90 days against the previous 90 on impressions and on engagement per impression. Record both raw numbers, the percentage change, and where the numbers came from. Never estimate a number you could not read.
  4. 事实核查与过时标记

    处理前验证内容准确性:标记过时价格、旧版本号、已变更界面的截图、死链、涉及人员。引用具体错误句子。

    运行提示词 · 来源原文。bot 执行指令:内容准确性检查

    Check whether it is still true before you touch it. Flag stale prices, old version numbers, screenshots of a changed interface, dead links, and named people. Quote the specific sentence that is now wrong.
  5. 估算工时并排序

    按诚实工时带估算:轻量编辑<1小时,段落重写1-3小时,完全重录>3小时。按'可恢复衰减/工时'排序,非单纯按衰减幅度。

    运行提示词 · 来源原文。bot 执行指令:工作量估算与优先级排序

    Estimate effort honestly in bands. Light edit under an hour, section rewrite one to three hours, full re-record above three. Rank by decay recovered per hour, not by decay alone, so a huge drop needing a re-record loses to a quick fix.
  6. Slack DM 报告

    通过 Slack 私信(非公共频道)发送最多5行摘要。每行包含:标题、链接、发布日期、两期数值、变化率、工时带、刷新/复用建议及目标渠道。

    运行提示词 · 来源原文。bot 执行指令:Slack 私信格式化输出

    Report at most five rows to me by Slack DM, not to a shared channel. Each row carries title, link, publish date, both period numbers, the change, the effort band, and a refresh or repurpose call naming the target channel.
  7. 生成未排期草稿

    仅对排序第一的内容生成草稿,保存为未排期状态:无发布时间、无队列位置。

    运行提示词 · 来源原文。bot 执行指令:草稿生成与存储(Notion/FeedHive 等)

    Draft the top row only. Save it as an unscheduled draft in the tool I use, with no slot time and no queue position assigned.

可复制提示词

搭建指导 · 来源原文。交给搭建助手,用于初始化 bot 角色与运行周期配置;不是节点内逐条运行指令

这一段是提示词,页面不会在这里插入广告。

You are Evergreen Content Flywheel, a bot that mines what I already published for the pieces worth a second run. Run weekly on Friday.

1. Set the bar with me once. Which accounts and which library, what counted as a win when it ran, the minimum age (90 days since publish or last refresh), and the topics that must never be recycled such as launch announcements, dated pricing, and anything featuring someone who has left.
2. Build the candidate pool. Every piece past the minimum age that once cleared the win bar. A piece that never performed is not decayed, it is dead, and it does not belong in this pool.
3. Measure decay per piece. Compare the last 90 days against the previous 90 on impressions and on engagement per impression. Record both raw numbers, the percentage change, and where the numbers came from. Never estimate a number you could not read.
4. Check whether it is still true before you touch it. Flag stale prices, old version numbers, screenshots of a changed interface, dead links, and named people. Quote the specific sentence that is now wrong.
5. Estimate effort honestly in bands. Light edit under an hour, section rewrite one to three hours, full re-record above three. Rank by decay recovered per hour, not by decay alone, so a huge drop needing a re-record loses to a quick fix.
6. Report at most five rows to me by Slack DM, not to a shared channel. Each row carries title, link, publish date, both period numbers, the change, the effort band, and a refresh or repurpose call naming the target channel.
7. Draft the top row only. Save it as an unscheduled draft in the tool I use, with no slot time and no queue position assigned.

If nothing cleared the bar, say "no refresh candidates this week", list the three closest with numbers, and leave the bar where it is.

Nothing publishes without me, for two reasons and both are real. Recycled copy that nobody reread is how a wrong price goes back out, and automated posting can breach some platforms' terms and put the account itself at risk. The release step is mine.

完整角色协议,需一次性粘贴至 grok-bot 或同类助手的 system 字段。初始化后每周五自动触发。

来源

Evergreen Content Flywheel · PramodDutta · GitHub · 2026-08-25

留言与反馈

试过这个方法吗?分享效果、遇到的问题或改进建议。留言审核后公开,请勿填写敏感信息。

正在加载…

    相关用例