agentleFS
Sign inStart free
swayamdhawanswayamdhawan/x-agent/skills/x-plan/SKILL.md

x-plan

Skill0 starsChanged 38 days agoMITView on GitHub

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.

3 other projects use a version of this.

Adopted by

Most recently taken up by

  • Other versions3 projects use a version of this.

    Word for word · 1

    1. Jakeschincariol/x-agent-skill★ 4100% same

    Edited · 0

    None found.

    Wrote their own version · 2

    1. lleqsnoom/xskills★ 2same name
    2. belzoralolbtw/x-agent-skill★ 0same name

    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.

The file

We split this skill into the rules it gives an agent

6 rules. About 0 are common, 3 are distinctive, and 3 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈3

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 3

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    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 …

    line 23
  2. Distinctive:

    If they do not exist, ask four things and write them down:

    line 29
  3. Distinctive:

    Not a topic, an angle. "AI" is not a plan.

    line 56
  4. Very specific:

    Run python3 weights.py and read the output to the user in one paragraph.

    line 61
  5. Distinctive:

    When the user's audience is awake and scrolling, in the audience's timezone: weekday mornings and lunch are the working default for a …

    line 80
  6. Very specific:

    Write the plan to ~/.claude/x/plan.md so the other skills can read it.

    line 120

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

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:

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:

formatper weekjob
Post5-7one idea, one to three lines. The workhorse. /x-post
Thread1-2the week's best ideas, with steps. /x-thread
Quote1-2your take on the week's news in the niche
Poll0-1only when the answers are next week's post
Video / image1a screen recording or a chart beats a stock image
Replies10-30 a dayon 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.

Download now (ZIP)

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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.

Check your setup, free