x-dm
/x-dm
Pisze pierwszą wiadomość prywatną na X do founderów lub freelancerów oraz dwa follow-upy, bez wysyłania.
- Autor
- muhammadhassan03 ↗
- Repozytorium
- x-agent-skill ↗
- Licencja
- MIT
- Ostatnia zmiana repozytorium
- 24.10.2026
Ocena i bezpieczeństwo
- Pliki w paczce
- 1
- Skrypty
- 0
- Komentarze HTML
- 0
- Adresy URL w SKILL.md
- 0
Brak sygnałów. Repozytorium zmienione 24.10.2026, bez odwołań do wycofanych modeli i API.
MIT, otwarta: można używać i zmieniać, z zachowaniem informacji o autorze.
Co robi i kiedy
Pisze pierwszą wiadomość prywatną na X do founderów lub freelancerów oraz dwa follow-upy, bez wysyłania.
Wyzwalacze z opisu
Oryginalny opis (EN)
Draft founder and freelancer outreach DMs for X: one first message and two follow-ups, then stop. Use when the user says "write a DM to", "cold outreach", "how do I follow up", "message this founder", or is reaching out to a specific person. One-to-one, hand-sent, never bulk. Never sends.
Jak działa
- How this stays within X's automation rules (not a guarantee)
- Before you write
- The sequence
- Checks before showing
- Output
- Approval gate
Podgląd SKILL.md
---
name: x-dm
description: >-
Draft founder and freelancer outreach DMs for X: one first message and two
follow-ups, then stop. Use when the user says "write a DM to", "cold outreach",
"how do I follow up", "message this founder", or is reaching out to a specific
person. One-to-one, hand-sent, never bulk. Never sends.
---
# x-dm
For a freelancer or founder reaching out to a specific person they have a real
reason to contact. Three messages at most per person. Then stop.
No tool of its own. Run each message through `/x-human`, and count with
`../x-post/xcount.py` if the user wants it short.
## How this stays within X's automation rules (not a guarantee)
X's automation rules forbid unsolicited DMs in bulk or automated form, and ask
people to be thoughtful about contact frequency. So:
- **One person at a time, written for that person, sent by hand.**
- **No templates with merge fields.** If the message would work with another name
swapped in, it is not ready.
- **Never a list.** Do not generate messages for a batch of accounts. If the user
pastes twenty profiles, pick the one or two with a real reason and say why the
rest are not worth a DM.
- Note that someone being able to receive your DM does not mean they want it.
## Before you write
1. Read `~/.claude/x/voice.md`.
2. Ask: who is this, what did you see of theirs (a specific post, a pricing page, a
launch), what do you offer, what is the smallest next step. If the user has no
specific observation, there is nothing to write yet. Say so.
3. **No invented proof.** A number, client or result the user did not give becomes
`{{your number}}`, flagged.
## The sequence
**Message 1: the first message.** Four parts, under about 450 weighted characters:
the specific thing you noticed, why it made you write, the one-line offer, a
question that costs one word to answer ("worth a quick look?"). No pitch deck, no
calendar link in the first message, no "I hope this finds you well".
**Message 2: follow-up, 4 to 7 days later.** Add one new, useful thing: a fix, a
data point, a short example. Not "just bumping this".
**Message 3: last one, 7 to 10 days later.** Shorter. Give an easy exit ("no worries
if the timing is off") and leave the door open. Then **stop**. No fourth message,
ever. No new account, no other channel to get around the silence.
Spacing is a suggestion. The user decides when to send.
## Checks before showing
- [ ] References something only this person has posted or built
- [ ] One ask, answerable in a word
- [ ] No links in message 1
- [ ] No flattery with nothing behind it
- [ ] No claim the user did not give
- [ ] Passed `/x-human`
## Output
Three fenced blocks, labelled 1, 2 and 3, each with the suggested day offset and a
line saying what would change the plan (a reply, a "no", a read receipt that
changes nothing). Remind the user to send them by hand and to stop at three.
## Approval gate
1. Show the finished text in one fenced block, ready to copy. If there is a link,
show it in a second block titled FIRST REPLY.
2. End the message with: Reply yes to log it.
3. On "yes", append one line to `~/.claude/x/log.md` (or the handle's folder):
date, skill, first line. That is all "yes" does.
4. Never post, like, follow, reply, DM or scroll. You write; the human posts, by
hand, on x.com.
Wersje
W bazie nie ma innych skilli o nazwie x-dm.
Migawka bazy z 28.10.2026 · wersja paczki 3318f78ea45e (skrót SHA-256 całej paczki)
Pobrania w ostatnich 30 dniach: 0 · ranking
Zgłoś problem z tym skillem: szkodliwa treść, błędny opis albo prośba autora o usunięcie.
Podobne skille
- 100li-dm
Pisze notatki do zaproszeń i follow-upy w wiadomościach na LinkedIn: 200-znakowe zaproszenie, pierwszą wiadomość i dwa follow-upy. - 100ig-dm
Pisze wiadomości prywatne na Instagramie, na które ludzie odpowiadają: dostarczenie słowa kluczowego, pierwszą wiadomość do osoby zaangażowanej, propozycję współpracy i dwa follow-upy. - 100ig-dm
Pisze wiadomości prywatne na Instagramie, na które ktoś odpowie: dostarczenie słowa kluczowego, pierwszą wiadomość do zaangażowanej osoby, propozycję współpracy i dwa follow-upy. - 100ig-dm
Pisze wiadomości prywatne na Instagramie: dostarczenie słowa kluczowego z automatyzacją komentarz-DM przez PostZen, pierwszą wiadomość do zaangażowanej osoby, propozycję współpracy i dwa follow-upy. - 90write-outreach
Tworzy outreach oparty na sygnałach i obsługę odpowiedzi: zimne maile, wiadomości partnerskie i sprzedażowe, DM na LinkedIn, oferty, follow-upy, dostarczalność i zgodność z przepisami. - 100follow-up-radar
Skanuje folder plików markdown z outreachem lub CRM w poszukiwaniu zaległych follow-upów i przygotowuje szkice wiadomości od najstarszych, bez wysyłania czegokolwiek.