post
Skill12 starsChanged 6 days agoMITView on GitHub
把实测数据或经验写成社媒帖:核数、按平台语言写文案、出数据图、排期发布并回查
18 other projects use a version of this.
Adopted by
Most recently taken up by
- flung-official/flung-claude-plugintheir own version, first seen Nov 8, 2026
- dcbruck/claude-skillstheir own version, first seen Oct 20, 2026
- Lzdevmendes/motion-studiotheir own version, first seen Oct 15, 2026
- ayrshare/ayrshare-social-media-api-claude-plugintheir own version, first seen Oct 13, 2026
- devinat1/skillstheir own version, first seen Oct 6, 2026
- YoniChechik/claude-code-configtheir own version, first seen Sep 18, 2026
Other versions18 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 18
- danium/lateral-thinking★ 311same name
- N1arko/redaktura-skills★ 130same name
- analystacademy/claude-skills★ 35same name
- ayrshare/ayrshare-social-media-api-claude-plugin★ 19same name
- imMamdouhaboammar/linkedin-animated-infographics★ 14same name
- Epistates/sparX★ 3same name
- robertnowell/marketing-pipeline★ 2same name
- dcbruck/claude-skills★ 1same name
- devinat1/skills★ 1same name
- giacomoguidotto/skills★ 1same name
8 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 repository28 other files it gives its agents.
- AGENTS.mdAGENTS.md
- gpt-imageSkill
- promoSkill
- videoSkill
- cuepadSkill
- architecture-auditSkill
- better-testSkill
- project-setupSkill
- prototypeSkill
- prSkill
- shipSkill
- write-swiftSkill
- ui-craftSkill
- ui-picksSkill
- better-browser-useSkill
- better-computer-useSkill
- herdrSkill
- sshSkill
- researchSkill
- session-dataSkill
- web-searchSkill
- fan-outSkill
- grillingSkill
- hillclimbSkill
- retroSkill
- eli5Skill
- writing-for-agentsSkill
- writing-for-humansSkill
The file
Files
Post
写法是具体的人在分享自己的发现,数字是证据。形态按用户要发的样子定:短帖、回复大帖、长帖或长文;用户没说发哪种语言就先问,只写那一种。
- 核数:先写一句话结论,这一帖只证明它;与结论无关的实验不进帖。把要用的每个数字写进事实清单文件,逐个从原始数据复算,写明来源与单位(轮次还是 PR、中位还是均值、样本数)。没有原始记录支撑的说法删掉。完成:清单文件路径交给用户,清单里每个数字都有来源,帖子和图里没有清单外的数字。
- 写文案:读对应平台、语言与形态的参考;没有对应参考时先做一轮原文调研(该平台该形态近期高互动帖的逐字原文,至少 5 个账号,按 fan-out 中档一个账号一个子代理),调研结论写成新的参考文件再动笔。动笔按 writing-for-humans 写。完成:逐条对过参考里的禁用清单,且每个限定词(样本、范围)都保留在正文或首条回复里。
- 出图:写 spec,跑
scripts/chart.py spec.json out.png [--size WxH](spec 格式见--help),以退出码为准,非零就没有新图。每张图一个结论,标题就是那个结论;配色版式避开 ui-craft「其他模板痕迹」,chart.py已用白底。完成:每张 PNG 文字不溢出,数字与事实清单一致。 - 发布:按参考里的节奏排期。用
better-browser-use的--login车道发帖,发完用平台接口或页面回查正文、图片数与回复对象。完成:每条帖子都回查过,链接交给用户。
参考
| 平台 · 语言 | 文件 |
| X · English · 短帖与回复 | references/x-en.md |
踩坑
- X 网页会把帖子自动翻译成中文;取原文走
https://api.fxtwitter.com/<user>/status/<id>(含 views、likes、replies、followers)。 - X 发帖流程(
--login车道):打开x.com/compose/post,点[data-testid=tweetTextarea_0]后用keyboard inserttext输入正文(多行原样保留),upload 'input[data-testid=fileInput]' <png>,发帖按钮是[data-testid=tweetButton];回复在帖子页用同一个输入框,按钮是[data-testid=tweetButtonInline]。超过 280 字符的长帖要认证账号(api.fxtwitter.com/<user>的verification.verified)。 - X 发帖框上传图片期间「回复/发帖」按钮是禁用的,等它恢复可点再点。
- X 个人主页有缓存,刚发的帖子可能不显示;回查用
x.com/search?q=from:<user>&f=live。独立帖可用发帖框的定时按钮(scheduleOption)排期,确认后发送按钮变成「安排表」且不再是tweetButton,在compose/post/unsent/scheduled回查;回复不能定时。 - 打开自己的帖子常弹「尝试推广这个帖子」遮住回复框,先点「以后再说」。
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.

