agentleFS
gladosAagmangladosAagman/x-agent-skill/skills/x-engage/SKILL.md

x-engage

Skill1 starsChanged 5 days agoMITView on GitHub

Keep the user's X reply round honest - log who they replied to, catch drift onto the same three accounts, track the reach / peer / buyer mix from the weekly plan, and surface the accounts on their list they have gone quiet on. Use when the user says "who should I reply to today", "log this reply", "who have I been replying to", "am I neglecting anyone", or runs their daily engagement round.

2 other projects use a version of this.

Adopted by

Most recently taken up by

  • Other versions2 projects use a version of this.

    Word for word · 0

    None found.

    Edited · 0

    None found.

    Wrote their own version · 2

    1. dancolta/x-engage★ 18same name
    2. jared833/claude-code-hooks★ 2same 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 repository14 other files it gives its agents.

The file

We split this skill into the rules it gives an agent

2 rules. About 0 are common, 2 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Never reply, like, follow or DM on the user's behalf, and never drive a browser to do it.

    line 63
  2. Distinctive:

    Never log a reply the user did not make.

    line 66

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 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-engage

For a small account on X, replies under bigger accounts are most of the growth. /x-plan sets the list: 5 reach, 3 peers, 2 buyers. Without a record two things happen. The round collapses onto the three accounts that reply back, which everyone reading those threads can see. And the buyers, the accounts the user meant to warm up for weeks before a DM, get dropped.

One tool lives in this folder and it runs:

python3 targets.py add @sarahbuilds --tier reach --note "added our churn number"
python3 targets.py report                     # the last 7 days
python3 targets.py due --roster roster.txt    # who on the list has gone quiet

The ledger is a CSV at ~/.claude/x/engage.csv. It validates handles (letters, digits, underscore, 15 at most), it never opens X and it never posts.

The roster

The ten from /x-plan, in ~/.claude/x/roster.txt, one per line, handle,tier:

@sarahbuilds,reach
@devon_k,peer
@dana_ops,buyer

The daily round

  1. targets.py due --roster ~/.claude/x/roster.txt. Most overdue first.
  2. The user pastes those accounts' latest posts. /x-comment drafts the replies, in batch mode.
  3. The user posts each reply by hand, early, then logs it with targets.py add.

The weekly read

targets.py report --days 7: count per account, the share the top three took, and the tier mix against 50 / 30 / 20. It warns when three accounts took over half the round, and when a tier fell below half its target.

Replies between accounts that follow each other get a boost in X's published ranker (python3 ../x-plan/weights.py), which is why the peer tier matters. Peers who never reply back after two weeks get replaced in next week's /x-plan.

Never

  • Never reply, like, follow or DM on the user's behalf, and never drive a browser to do it. X's automation rules prohibit automated replies, likes and bulk follows.
  • Never log a reply the user did not make.

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.