content-pipeline
Skill0 starsChanged 2 months agoMITView on GitHub
内容文案量产流水线——字段化输入 + 参数化生成 + 多级校验器 + 回退机制，把"写作"变成"审核"，保证违禁词零容忍与一次可用率。当用户要"批量产文案/脚本/模板内容"时使用。
17 other projects use a version of this.
Adopted by
Most recently taken up by
- Kianzzz/Zhouxing-skill-publictheir own version, first seen Nov 8, 2026
- LazyIsEfficient/agentic-ostheir own version, first seen Oct 22, 2026
- claude-world/claude-world-studiotheir own version, first seen Oct 22, 2026
- Aravind7262/content-pipelinetheir own version, first seen Oct 20, 2026
- runxhq/runxtheir own version, first seen Oct 13, 2026
- pobsteta/aigoratheir own version, first seen Oct 2, 2026
Other versions17 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 17
- OrangeViolin/content-pipeline★ 217same name
- fivetaku/content-pipeline★ 100same name
- runxhq/runx★ 97same name
- claude-world/claude-world-studio★ 71same name
- coopersimson96/ai-content-system★ 17same name
- LazyIsEfficient/agentic-os★ 17same name
- zad111ak-ai/hermes-agent-skills★ 7same name
- Kianzzz/Zhouxing-skill-public★ 4same name
- PingPingE/ai-content-agents★ 2same name
- rami-maalouf/skills★ 2same name
7 more not listed
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository10 other files it gives its agents.
- llms.txtllms.txt
- cost-quoteSkill
- doc-reviewSkill
- fde-discoverySkill
- kb-buildSkill
- recon-chainSkill
- record-linkSkill
- semantic-layerSkill
- state-reminderSkill
- timeline-checkSkill
The file
Files
Content Pipeline · 内容量产流水线
对应案例：NO.15（短视频脚本，直接 AI 写可用率 0%→流水线 100%）、
NO.12（鞋服电商素材）。
参考实现：cases/15-content-pipeline/（违禁词零出现、日交付 400 条）。
何时使用
- 高峰期日产数百条文案，人工写作是产能瓶颈
- 直接让 AI 写"AI 味"重、有违禁词风险、商户/品牌间差异照顾不到
流程
- Know-how 字段化：把优秀运营的判断拆成业务字段（客群/菜品/卖点/活动/ 语气/钩子），先结构化再谈生成——"写出一篇文案"和"稳定量产可用脚本" 是两回事。
- 参数化生成：钩子×细节×卖点×CTA 组合生成，语气随字段参数变化； 每条文案引用不同模板组合，避免同对象撞模板。
- 校验器链（对生成与人工稿同一口径，保证公平）： 长度区间 → 违禁词（广告法绝对化用语，零容忍）→ 核心卖点覆盖 → 结构完整 → 同对象查重（n-gram 相似度）。
- 回退机制：未过校验 → 换模板重写一次 → 仍未过 → 人工队列； 人工只审抽检 + 回退件，角色从"写"退到"审"。
- 反馈调优：平台数据（留存/转化）与"味道不对"类主观反馈，定期回填为 校验规则与参数——把语感变成可执行标准。
验收
- 流水线输出违禁词出现次数 = 0（红线）
- 一次可用率 ≥ 95%，人工回退率 ≤ 5%
- 同对象内容无高度重复；用同一校验器对比"直接 AI 写"基线的可用率提升
边界
- 品牌调性、是否发布由人工终审
- 校验词表与卖点口径需品牌方确认后固化为配置
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.