agentleFS
Sign inStart free
JakeschincariolJakeschincariol/x-agent-skill/skills/x-dm/SKILL.md

x-dm

Skill4 starsChanged 45 days agoMITView on GitHub

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.

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 · 1

    1. swayamdhawan/x-agent★ 0100% same

    Edited · 0

    None found.

    Wrote their own version · 1

    1. 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

7 rules. About 0 are common, 7 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈7

    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:

    Ask, in one batched question:

    line 20
  2. Distinctive:

    +4 days: add something new. Never "just bumping this".

    line 55
  3. Distinctive:

    When the user pastes their DMs or message requests, sort them:

    line 64
  4. Distinctive:

    Never send the message. The user sends every one by hand.

    line 80
  5. Distinctive:

    Never send bulk or automated DMs.

    line 81
  6. Distinctive:

    Never fabricate a mutual, a shared history, or having read something the user has not read.

    line 83
  7. Distinctive:

    Never open with "Hope this finds you well" or "Quick question".

    line 85

≈ “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-dm

On X the DM is the last step, not the first. The people worth messaging get cold DMs every day, and most of them land in message requests, unread. The ones that get opened come from a name the reader already recognises, because it has been in their replies.

Before writing, get the specifics

Ask, in one batched question:

  1. Who: handle, what they do.
  2. The history: have they seen the user's name? Replies, quotes, a mutual follow. If the answer is "none", the first job is two weeks of /x-comment on their posts, not a DM. Say so.
  3. The reason, now: a post they wrote, a thing they shipped, a question they asked in public. Not "they fit my ICP".
  4. What the user wants: a conversation, a collab, a sale, a job. Be honest internally, even if the message does not lead with it.

Some accounts only accept DMs from people they follow or from verified accounts. If the user cannot message them, the reply section is the channel.

The first message

  • Two to four sentences. A screen of text is a delete.
  • Open on the specific thing from their public posts. That continuity is the whole point of having replied first.
  • Give something before asking. A number, a template, a name, an answer to a question they asked publicly.
  • One small ask. "Worth a 15-minute call next week?" beats "let me walk you through what we do".
  • No link in message one. It reads as a funnel, because it is.
Your post about killing the discovery call is the reason we tried it in March.
Close rate went up, and I wrote down the 4 questions we ask instead, happy to
send them. Worth 15 minutes next week to compare notes?

Follow-ups

Two. That is the number.

  • +4 days: add something new. Never "just bumping this". Nothing new, no follow-up.
  • +10 days: close the loop. Say you will stop, and mean it. It gets a surprising share of the replies because it removes the pressure.

Then stop.

Inbox triage

When the user pastes their DMs or message requests, sort them:

bucketwhat it iswhat to do
LEADsomeone with the problem the user solvesdraft a reply today
PEERa creator or operator worth knowingreply, human to human
ASKa favour, a question, an intro requestanswer or decline kindly
PITCHsomeone selling to the userone-line no, or nothing
SPAM / SCAMbots, "collab" farms, crypto, impersonationnothing. Report if it is a scam

Say which tell gave each pitch away (a template opener, a compliment about nothing specific, a link in message one). That is how the user learns to spot them in two seconds.

Never

  • Never send the message. The user sends every one by hand.
  • Never send bulk or automated DMs. X's automation rules prohibit bulk unsolicited messages, and accounts that do it get limited.
  • Never fabricate a mutual, a shared history, or having read something the user has not read.
  • Never open with "Hope this finds you well" or "Quick question".

Output

The first message and both follow-ups with the day each goes out, or the triaged inbox with drafts for the LEAD and PEER rows. All through /x-human.

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