agentleFS
belzoralolbtwbelzoralolbtw/x-agent-skill/skills/x-dm/SKILL.md

x-dm

Skill0 starsChanged 35 days agoMITView on GitHub

Write X (Twitter) direct messages that get replies, for outreach, warm intros, partnerships, and follow-ups. Use when the user wants to DM someone, cold outreach on X, a pitch, an intro message, or help getting a reply. Produces a short, specific, humanized message and a follow-up, with the reasons most DMs get ignored.

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. Jakeschincariol/x-agent-skill★ 4same name
    2. swayamdhawan/x-agent★ 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 repository9 other files it gives its agents.

The file

We split this skill into the rules it gives an agent

5 rules. About 0 are common, 4 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈4

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

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

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

    Read the voice profile (templates/voice.md), or infer the voice from three of the user's own posts.

    line 19
  2. Distinctive:

    Ask who the message is going to and what the sender actually wants.

    line 21
  3. Distinctive:

    Ask what the sender already knows about the recipient: a post they read, a project they saw.

    line 23
  4. Distinctive:

    Never chase more than once.

    line 57
  5. Distinctive:

    Do not write messages that pretend to be personal when they are mass-sent, and do not help impersonate someone or misrepresent what the …

    line 72

≈ “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

A DM on X is read in a crowded inbox by someone who gets pitched constantly. The bar is not "polite", it is "obviously written for me by a real person, and asks for almost nothing".

Before you write

  1. Read the voice profile (templates/voice.md), or infer the voice from three of the user's own posts.
  2. Ask who the message is going to and what the sender actually wants. "Talk to them" is not a goal. "Get 15 minutes" or "ask one question" is.
  3. Ask what the sender already knows about the recipient: a post they read, a project they saw. If the answer is nothing, that is the first fix, not the message.

The shape of a DM that gets a reply

Line 1   proof you know them: their specific post, project, or result. One line.
Line 2   who you are, in their terms, and why them.
Line 3   one small, specific ask. A question, or a low-cost next step.

Three or four lines. No paragraph. No attachment. No life story. The smaller the ask, the higher the reply rate. "Can I ask you one question about X" beats "can I pick your brain" every time.

Rules

  • No pitch in the first message unless the recipient explicitly welcomes pitches. The first message earns the right to a second.
  • No link. Links in a cold DM read as spam and can get the account flagged.
  • Be specific or be ignored. "I love your content" is deleted. "Your post on cold email subject lines changed how I write line 1" gets answered.
  • Send after engagement, not instead of it. A reply to their post, then a DM a day later, works far better than a cold DM out of nowhere.
  • No flattery openers, no "hope you're doing well", no "I'll keep this short". Cut every warm-up line.

The loop

1. Write the message in the shape above, under 500 characters, ending on one specific ask. Give one version, not three; the choice is theirs, not yours. 2. Write one follow-up for a week later, short, that adds something new (a thought, a relevant link in the second message only if they replied once). Never chase more than once. 3. Humanize both (x-human). Cold DMs are where template tells are most obvious.

Failure modes

  • A message that would read identically if sent to anyone else in the niche.
  • "Hey, love your work, I built something that could help you." Instant delete.
  • Asking for a call as the first ask. Offer a question, then let it grow.
  • A follow-up that repeats the first message. If you have nothing to add, wait.
  • Sending to fifty accounts at once with the same text. X and the recipients both notice.

When not to act

Do not write messages that pretend to be personal when they are mass-sent, and do not help impersonate someone or misrepresent what the sender does. If the sender cannot name one specific thing about the recipient, write that line first, or send nothing.

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.