Skip to main content

x-plan

Plan the user's week on X - what to post, when to post it, and who to engage with. Use when the user says "plan my week", "what should I post", "content calendar", "posting schedule", "I have nothing to post about", or wants a weekly mix of posts, threads and replies and a list of accounts to engage.

来源信息

仓库
Jakeschincariol/x-agent-skill
最近来源活动
2026年9月29日 04:04
检测到的 SKILL.md 语言
英语
星标
0
分支
0

安装方式

默认使用会先检查来源的 Prompt;你也可以切换为直接命令,或下载本地副本。

检查来源文件

决定是否安装前,请先阅读 SKILL.md,以及 SkillsMP 当前展示的配套文件。

文件资源管理器
2 个文件

正在显示 SKILL.md

SKILL.md
来源说明 · 只读预览
name
x-plan
description
Plan the user's week on X - what to post, when to post it, and who to engage with. Use when the user says "plan my week", "what should I post", "content calendar", "posting schedule", "I have nothing to post about", or wants a weekly mix of posts, threads and replies and a list of accounts to engage.
# x-plan The control room. Everything else in this pack executes; this decides what gets executed. Run it once a week, on the same day. One tool lives in this folder: ```bash python3 weights.py # what X's ranker rewards and punishes, live from X's own code ``` ## Input Read these if they exist: `~/.claude/x/voice.md`, `log.md` (what was posted, with which formula), `swipe.md` (what is working in the niche, from `/x-viral`) and the last `/x-audit` result. The plan should not repeat a theme from the last fortnight, and it should lean on what the user's own evidence says works. If they do not exist, ask four things and write them down: 1. What the user sells, and to whom. 2. The three or four topics they want to be known for. 3. What actually happened this week: a number, a client, a mistake, a thing they built, an argument. This is where posts come from. 4. Twenty accounts in their niche, from much bigger to about their size. ## What to post X moves faster than other platforms and rewards presence, but volume is not the lever people think it is. A working default for a solo account: | format | per week | job | | --- | --- | --- | | **Post** | 5-7 | one idea, one to three lines. The workhorse. `/x-post` | | **Thread** | 1-2 | the week's best ideas, with steps. `/x-thread` | | **Quote** | 1-2 | your take on the week's news in the niche | | **Poll** | 0-1 | only when the answers are next week's post | | **Video / image** | 1 | a screen recording or a chart beats a stock image | | **Replies** | 10-30 a day | on other people's posts. `/x-comment`. This is the growth | Two limits worth knowing: X caps unverified accounts at 50 original posts and 200 replies a day. Nobody should get near either. For each slot give the topic, the specific angle drawn from what actually happened this week, and the hook formula number from `../x-post/hooks.json`. Not a topic, an angle. "AI" is not a plan. "The proposal I lost because the draft had an em dash in it" is a post. ## What X actually rewards Run `python3 weights.py` and read the output to the user in one paragraph. The shape to plan around: replies, quotes and shares are weighted far above likes, a reply between two accounts that follow each other gets extra, and mutes, "not interested" and reports are weighted heavily against you. The file's own comments say these apply to predicted probabilities, not counts, so do not turn them into "a reply = 10 likes". Two practical consequences: - **Plan for replies, not likes.** A post that asks for a reply honestly (a specific question, a claim people will argue with) beats a post built for applause. - **Engagement pods do nothing.** X's code comments say engagement only counts toward ranking when the post was served in the viewer's home timeline; sending people to the post from a group chat has no ranking impact. ## When to post When the user's audience is awake and scrolling, in the audience's timezone: weekday mornings and lunch are the working default for a professional audience. Say this plainly as well: **the hour matters far less than the first line.** If the user is tuning posting times before their hooks work, they are polishing the wrong thing. The better timing lever is the hour after posting: be there to reply. ## Who to engage with A list of 10 for the week, split: - **5 reach**: bigger accounts whose posts the user can genuinely add to. Turn on their post notifications and reply in the first 15 minutes. - **3 peers**: same size, same niche. They reply back, and replies between mutuals are the ones X boosts. - **2 buyers**: people who could buy. Reply to their posts for weeks before any DM, and never pitch in a reply. ## Output ``` WEEK OF SEP 28 MON 9:00 THREAD #16 Thread Promise - the 40 viral posts I read, what they shared TUE 8:30 POST #9 Time Anchor - proposals, 5 hours to 20 minutes WED 12:00 POLL - - "which do you pay for" (answers = Friday's post) THU 9:00 THREAD #2 Number Reveal - 90 days of daily posting, what moved the numbers FRI 5:00 VIDEO #15 The Launch - 40-second screen recording of the new tool SAT 10:00 POST #21 The One-Liner - (from Wednesday's poll result) SUN 7:00 QUOTE - - the week's biggest niche news, your take DAILY 20 replies before posting, not after. List below. ENGAGE (5 reach / 3 peers / 2 buyers) ... Say "write Tuesday" and I will draft it. ``` Write the plan to `~/.claude/x/plan.md` so the other skills can read it. Nothing is scheduled or posted anywhere. This is a plan, and the user runs it.
在 GitHub 查看