x-post-gate
Skill3 starsChanged 3 months agoMITView on GitHub
X(Twitter) 发帖前「不发原则」自检门。把一条推文草稿过两道闸:①发帖前四问·一票否决(四个都不占 → 别发)②不发清单(命中黑名单 → 不发或打回改)。给出「发 / 打回改 / 不发」三档裁决 + 逐条依据 + 可执行的改法。定位在 x-hotspot-radar 出稿之后、x-post 发布之前的闸门。清单唯一真相是自媒体运营看板的 SELF_CHECK。 触发方式:/x-post-gate、「这条该发吗」「这条能发吗」「不发清单检测」「过一下发帖门」「发帖自检」「用我的不发原则检测」。 Pre-publish gate for X drafts against Charles's "don't-post" principle. Runs two checks: four-question veto (if none apply → don't post) and a blacklist. Returns a POST / REWORK / DROP verdict with per-item reasons and fixes. Sits between x-hotspot-radar (draft) and x-post (publish). Trigger: /x-post-gate, "should I post this", "run the post gate", "post checklist".
1 other project uses a version of this, 1 of them edited.
Adopted by
Most recently taken up by
- anneheartrecord/x-operation-skillsedited, first seen Jul 13, 2026
Other versions1 project uses a version of this.
Word for word · 0
None found.
Edited · 1
- anneheartrecord/x-operation-skills★ 423% same
Wrote their own version · 0
None found.
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 repository18 other files it gives its agents.
- agent-mbtiSkill
- de-ai-flavorSkill
- extract-memorySkill
- duanyongping-perspectiveSkill
- tashanzhishiSkill
- github-recruiterSkill
- graphifySkill
- convert-lakebookSkill
- offer-radarSkill
- resume-tuningSkill
- spoolSkill
- mbti-analysisSkill
- generate-weekly-reportSkill
- weread-digestSkill
- x-account-auditSkill
- x-content-reviewSkill
- x-hotspot-radarSkill
- x-postSkill
The file
Files
X 发帖前「不发原则」自检门
在把一条推文交给 x-post 发布之前,先过这道门。目的不是拦一切,而是拦住发了也白发、甚至稀释账号定位的内容。宁可少发一条,不发一条没有判断、跟主线无关的流水。
清单的唯一真相:~/Documents/knowledge-base/40-dashboards/自媒体运营看板.html 里的 SELF_CHECK 对象(搜 const SELF_CHECK)。本 skill 是它的可执行副本,两边内容必须一致——若在看板改了四问或不发清单,同步改本文件;反之亦然。
输入
一条推文草稿(文件路径或直接粘贴的正文)。默认从 ~/Documents/knowledge-base/30-outputs/tweets/ 里的草稿取。
两道闸(顺序执行,任一判「不发」即停)
闸一:不发清单(黑名单,命中即打回或不发)
逐条核对草稿是否属于下面任一类。命中就不能直接发:
| # | 不发项 | 判定要点 | 处置 |
| 1 | 模型新闻评论(无一手实测) | 只是转述/点评某模型发布、跑分、更新,自己没上手实测 | 打回:补一手实测数据/截图再发,否则不发 |
| 2 | 纯工具搬运 | 只是「发现个好工具,链接给你」,没有自己的用法/判断 | 打回:加自己的使用场景 + 判断 |
| 3 | 配图流水账 | 晒图/晒生活/晒结果,无观点无信息增量 | 不发 |
| 4 | MBTI / 星座 | 命理、人格标签类娱乐内容 | 不发(硬拒) |
| 5 | 纯转发 | 只是转发他人内容,无自己的增量观点 | 不发 |
| 6 | 没有判断的资讯 | 只报「发生了什么」,不给「我怎么看」 | 打回:补判断 |
| 7 | 纯吐槽 | 只有情绪锐评,没落到理由/边界/动作 | 打回:锐评转判断(给理由 / 给边界 / 给动作) |
| 8 | 闲聊 / 体验卡 / 纯链接短推 | 无信息量的日常闲聊、体验卡、只甩个链接 | 不发 |
「打回改」和「不发」的区别:打回类是内容有底子但缺关键要素(实测/判断/用法),补上就能发;不发类是这类内容本身不该出现在这个账号。
闸二:发帖前四问 · 一票否决(四个都不占 → 别发)
过了闸一,再问这四个问题。只要一个都不占,就别发(反过来:至少命中一个才有资格发,命中越多越该发):
- 服务三条主线之一吗?(AI 落地 / 技术人的钱 / 大厂之外的路)
- 能让合适的人更理解我吗?(增加辨识度、露出真实的人)
- 露出判断了吗?(有没有自己的观点/取舍,而不只是信息搬运)
- 能把人带到下一步吗?(引发关注、收藏、私信、点进主页的动机)
裁决输出(固定格式)
跑完两道闸,输出:
裁决:发 / 打回改 / 不发
闸一·不发清单:通过 / 命中第 N 条「XX」
闸二·四问:命中 [1/2/3/4 哪几条],共 N 条
1 主线:命中(哪条主线)/ 不占
2 理解我:命中 / 不占
3 露出判断:命中 / 不占
4 带到下一步:命中 / 不占
理由:一句话说清为什么是这个档
改法(仅打回改时给):具体缺什么、怎么补裁决规则:
- 闸一命中「不发」类 → 不发。
- 闸一命中「打回改」类 → 打回改(先不发)。
- 闸一通过,闸二四问全不占 → 不发(跟这个账号无关)。
- 闸一通过,闸二至少命中一问 → 发。
边界
- 本门只判「该不该发」,不判「文案好不好」。文风打磨走写作系统,开头优化走
dbs-hook,标题走xhs-title,去 AI 味走de-ai-flavor。 - 裁决「发」≠ 自动发布。发布永远是用户手动动作,或用户明确说发之后才走
x-post(先 dry-run 预览费用再确认)。 - 本门不改草稿正文,只给裁决和改法建议。
与工具包其它 skill 的衔接
x-hotspot-radar(出稿)→ x-post-gate(该不该发) → x-post(发布)。
复盘侧:发过的帖用 x-content-review 出周报/月报,A 档扩系列、C 档停选题,反过来影响以后什么该发。
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.

