x-post
Skill4 starsChanged 4 months agoMITView on GitHub
通过 X 官方 API 发布推文(按量计费:纯文字 $0.015/条,含链接 $0.20/条)。带确认门槛:先 dry-run 预览内容和预估费用,用户明确确认后才真正发布;支持回复指定帖子、发多条 thread。 触发方式:/x-post、「把这条发到X」「发布这条推文」「用API发帖」。 Post tweets via the official X API (pay-per-use). Dry-run preview with cost estimate first; publishes only after explicit user confirmation. Supports replies and threads. Trigger: /x-post, "post this to X", "publish this tweet".
- Reads credentials
17 other projects use a version of this.
Adopted by
Most recently taken up by
- terryso/ego-skillstheir own version, first seen Nov 8, 2026
- schroneko/skillstheir own version, first seen Oct 29, 2026
- hanzhangzzz/agent-skills-zhtheir own version, first seen Oct 29, 2026
- belzoralolbtw/x-agent-skilltheir own version, first seen Oct 25, 2026
- swayamdhawan/x-agenttheir own version, first seen Oct 20, 2026
- razbakov/skillstheir own version, first seen Oct 17, 2026
Used with
Projects with it also use x-dm, x-human and 6 more.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
JakeschincariolSkillx-dm
Write X DMs that get answered - the first message, the two follow-ups - and triage the user's DM inbox and message requests. Use when the user says "DM this person", "cold DM", "outreach on X", "how do I follow up", "what do I say to this DM", "go through my message requests", or is reaching out to someone specific on X.
Also in 3 projects that use this
JakeschincariolSkillx-human
Strip the machine fingerprint out of any draft - em dashes, AI slop words, invisible watermark characters, thread boilerplate - and score it against a five-check detection panel before it goes out. Use whenever text needs to sound human, when the user says humanize, "does this sound like AI", "remove the em dashes", "de-slop this", "this sounds like ChatGPT", or before any post, thread, reply or DM from this pack is shown to the user.
Also in 3 projects that use this
lleqsnoomSkillx-plan
Plan before coding — research the project and the web first, ask short plain questions until the user is sure, propose three approaches with trade-offs, then write a layered spec (contract, invariant, test) as a graph-driven scenario with guards and a memory file; gate on user approval
Also in 3 projects that use this
lxyang20131208-starSkillx-audit
Audit a draft X (Twitter) post or thread against the open-source X algorithm BEFORE publishing. Use when the user shares a tweet draft and wants feedback, asks "will this do well on X / Twitter", "review my post", "is this good to post", or wants to improve reach before posting. Returns a PASS / FLAG / BLOCK verdict per dimension plus a concrete rewrite.
Also in 3 projects that use this
lxyang20131208-starSkillx-reply
Build a reply-based growth strategy for a new or small X (Twitter) account, and draft high-quality replies. Use when the user has few followers, asks "how do I grow on X from zero", "my account is new", "who should I reply to", "help me write a reply to this tweet", or wants a cold-start plan. Returns an anchor-account strategy and concrete reply drafts.
Also in 3 projects that use this
- +1 more from Jakeschincariol
- +2 more from lxyang20131208-star
Other versions17 projects use a version of this.
Word for word · 1
- anneheartrecord/charles-skill★ 3100% same
Edited · 0
None found.
Wrote their own version · 16
- publora/skills★ 68same name
- terryso/ego-skills★ 34same name
- rameerez/claude-code-startup-skills★ 30same name
- SpaceZephyr/allSkills★ 14same name
- win4r/x-post-skill★ 12same name
- tonydzi/second-brain-starter-kit★ 6same name
- Jakeschincariol/x-agent-skill★ 4same name
- razbakov/skills★ 4same name
- dqtx760/skills-manage★ 2same name
- t2y-kage/agent-skills★ 2same name
6 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 repository5 other files it gives its agents.
- x-account-auditSkill
- x-content-reviewSkill
- x-hotspot-radarSkill
- x-post-gateSkill
- x-scheduleSkill
The file
Files
X 发帖(官方 API)
把定稿内容通过官方 API 发到 X。核心原则:发布是不可逆的对外动作,永远先预览、后确认、再发布。
前置条件
官方 API 的 OAuth 凭证,四个环境变量(developer.x.com → 项目 → Keys and tokens,Access Token 需勾选 Read and write;按惯例存 ~/.config/secrets/api-keys.env):
export X_API_KEY="..."
export X_API_SECRET="..."
export X_ACCESS_TOKEN="..."
export X_ACCESS_TOKEN_SECRET="..."依赖:pip3 install tweepy。计费为预充值信用点、按请求扣费、无订阅。
先自检再用:python3 <skill目录>/scripts/post_tweet.py --check 验证凭证(缺变量/权限不足/过期会 FAIL 并给提示,不发帖)。⚠️ 发帖写路径尚未在真实凭证下端到端验证过(需用户配好凭证后自测一次首发);dry-run 预览与拆分逻辑已测。
工作流程(硬性顺序,不可跳步)
第 1 步:dry-run 预览
python3 <skill目录>/scripts/post_tweet.py --text "帖子内容"输出内容、字数、预估费用。把预览结果原样给用户看,特别是:
- 含链接的帖单价 $0.20,是纯文字($0.015)的 13 倍(X 刻意抑制外链)。检测到链接必须显式提醒,并建议备选:链接放到自回复里(主帖纯文字 $0.015 + 回复含链接 $0.20,总价不变但主帖曝光不受外链抑制)。
- 超过 280 字符会发布失败,预览时先检查(中文按 2 字符计)。
第 2 步:等用户明确确认
**只有用户明确说「发」「确认发布」「就这条」等肯定指令才进入第 3 步。**以下情况一律不发:用户只是让你「生成/改一下/看看」;内容还是草稿阶段;用户没有对本次预览的具体内容表态。修改内容后必须重新 dry-run,不能拿旧确认发新内容。
第 3 步:发布
python3 <skill目录>/scripts/post_tweet.py --text "帖子内容" --yes发 thread(长文自动拆分)
长文一条发不下时,用同仓 split_thread.py 拆:按句界切成 ≤270 加权长度(中文算 2),把所有链接归拢到末条自回复,这样整个 thread 只有末条付 $0.20,正文各条 $0.015。
python3 <仓库>/x-post/scripts/split_thread.py --file draft.md --number > thread-plan.json
python3 <skill目录>/scripts/post_tweet.py --thread-file thread-plan.json # dry-run 预览
python3 <skill目录>/scripts/post_tweet.py --thread-file thread-plan.json --yes # 确认后顺序发注意:链接被抽到末条后,正文里原本「仓库在 <链接>」这类句子会留空档,拆分前把这类句子改成不依赖内联链接的说法(如「仓库和链接放在末条」)。dry-run 会显示每条正文、加权长度、预估总价,让用户确认整个 thread 再发。
第 4 步:回报结果
把返回的帖子 URL 给用户;发布记录(时间、内容、费用)追加到用户运营目录的发布日志(若有)。
判断规则(硬口径)
- 没有 dry-run 过的内容绝不发布。
- 一次确认只对应一次发布;批量发 thread 需要用户对整个 thread 文案确认过。
- 发布失败(限流/凭证过期)时原样报错,不重试超过 1 次,不静默吞错。
- 费用敏感:单次会话累计发帖费用预估超过 $1 时,汇总提醒用户。
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.

