agentleFS
JakeschincariolJakeschincariol/closer-skill/follow-up/SKILL.md

follow-up

Skill33 starsChanged 11 days agoMITView on GitHub

Follow-Up. Keeps following up until a call is booked, then stops. Every morning it reads closer/pipeline.json and says who is due a follow-up today, who replied and is waiting on you, who booked, and who is stopped and why. Drafts each follow-up (a bump, then something useful, then a polite last note), waits for your yes, logs it, and stops at the first "no", the moment a call is booked, after 3 follow-ups or 30 days. Use when the user says "follow up", "who do I need to follow up with", "they haven't replied", "chase", "nudge", "bump this", "they replied", or every morning.

23 other projects use a version of this, 1 of them edited.

Adopted by

Most recently taken up by

Used with

Projects with it also use call-prep and mock-interview.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • AnthropicSkill

    call-prep

    Prepare for a customer or prospect call using Common Room signals. Triggers on 'prep me for my call with [company]', 'prepare for a meeting with [company]', 'what should I know before talking to [company]', or any call preparation request.

    Also in 3 projects that use this

  • aslavchevSkill

    mock-interview

    Simulate a real job interview for any role. Use when user says "mock interview", "interview me", "interview prep", "practice interview", or wants to rehearse for a specific company or position. Adapts rounds and questions to the role — technical, managerial, creative, or any other.

    Also in 3 projects that use this

The file

We split this skill into the rules it gives an agent

9 rules. 0 are common, 8 are distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 19 edited versions we read keep these.

  • 8

    Distinctive

    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. Distinctive:

    At most 3 follow-ups: after the opening, and the third one says it is the last.

    line 39
  2. Distinctive:

    Follow-up 1 is two days after the opening, follow-up 2 two days after that, follow-up 3 four days after that.

    line 46
  3. Very specific:

    Run /record-keeper sync first so replies are on the board.

    line 57
  4. Distinctive:

    Never sends, and never records a message that did not go out.

    line 79
  5. Distinctive:

    Never follows up after a no, after a booking, after 3 follow-ups or after 30 days.

    line 80
  6. Distinctive:

    Never uses guilt, fake urgency, a fake "Re:" or a made-up reason to write.

    line 81
  7. Distinctive:

    Stop at the first "no" or any sign of disinterest.

    line 88
  8. Distinctive:

    Every email keeps the opt-out line from the opening thread.

    line 89
  9. Distinctive:

    Never invent a number, a result, a client, a review or a deadline.

    line 90

“Common” is measured: kept by at least 6 in 10 of the 19 edited versions of this file we could read. “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

follow-up

Most deals are lost to silence, not to "no". This skill makes sure nobody is forgotten and nobody is pestered. It drafts; it never sends by itself.

${CLAUDE_SKILL_DIR} below is this skill's folder (where this SKILL.md lives).

python3 "${CLAUDE_SKILL_DIR}/followup.py" due --today 2026-10-21
python3 "${CLAUDE_SKILL_DIR}/followup.py" draft --contact dana-harbor-lane --today 2026-10-21
python3 "${CLAUDE_SKILL_DIR}/followup.py" draft --contact dana-harbor-lane --today 2026-10-23 \
    --hook "here's a 1-minute mockup of what online booking could look like for Harbor Lane."
python3 "${CLAUDE_SKILL_DIR}/followup.py" record --contact dana-harbor-lane --text-file /tmp/f.txt \
    --approval "yes" --at 2026-10-21T09:00
python3 "${CLAUDE_SKILL_DIR}/followup.py" reply --contact dana-harbor-lane \
    --text "Sorry, crazy week! Thursday at 2 works." --at 2026-10-27T11:48
python3 "${CLAUDE_SKILL_DIR}/followup.py" stop --contact <id> --said "Please remove me from your list."

The rules (per person, across every channel)

  1. Stop at the first "no" or any sign of disinterest ("not interested", "no thanks", "we're all set", "please remove me"). An unsubscribe goes on the suppression list, and no skill emails them again.
  2. Stop the moment a call is booked. That is the job. /scheduler and /sales-coach take over.
  3. A reply is your turn. Answering them is a conversation, never a "follow-up".
  4. At most 3 follow-ups after the opening, and the third one says it is the last.
  5. Nothing after 30 days from the opening without a reply. /win-back may try once, much later.

draft refuses to draft and record refuses to log anything that breaks a rule.

The cadence

Follow-up 1 is two days after the opening, follow-up 2 two days after that, follow-up 3 four days after that. A date on a weekend moves to Monday. The reel's thread: Mon Oct 19 (opening), Wed Oct 21, Fri Oct 23, Tue Oct 27.

  1. Follow-up 1, the bump. One line: "just bumping this up in case it got buried."
  2. Follow-up 2, give something. A mockup, a number, a short idea for them. --hook is that one new, true, specific thing. Without a hook there is no follow-up 2.
  3. Follow-up 3, the last note. Offer a day for a call and say it is the last email. Either answer is fine.

Steps, every morning

  1. Run /record-keeper sync first so replies are on the board.
  2. followup.py due. Read it to the user grouped as it prints: DUE NOW, YOUR TURN, WAITING, BOOKED, STOPPED.
  3. For each DUE NOW, followup.py draft. Fill every [fill: ...]. Show it: "Send this follow-up to Dana? Reply yes or no." One message per question.
  4. On a yes: a Gmail draft in the same thread from the user's account, which the user sends (or sent through the Gmail connector right after that yes). Then followup.py record --approval "<their yes, word for word>".
  5. For each YOUR TURN: when they gave a time, hand it to /scheduler (slots.py parse), confirm with the confirm-time template, and book. When they said no, followup.py reply with their words: it stops everything and marks the deal lost.

A scheduled morning run may list and draft. It never sends: nobody is there to say yes.

Example from the reel

Dana Ortiz never answered the opening. Follow-up 1 on Wed Oct 21: "just bumping this up in case it got buried." Follow-up 2 on Fri Oct 23: the 1-minute mockup. Follow-up 3 on Tue Oct 27: "should I close the loop on this, or is Thursday good for a quick call?" At 11:48 AM she replied, "Sorry, crazy week! Thursday at 2 works." reply moved her to YOUR TURN; the call was booked, and from then on she got no more follow-ups. (Illustrative: Dana and Harbor Lane Dental are fictional.)

What it never does

  • Never sends, and never records a message that did not go out.
  • Never follows up after a no, after a booking, after 3 follow-ups or after 30 days.
  • Never uses guilt, fake urgency, a fake "Re:" or a made-up reason to write.

Consent and truth

  • Nothing is sent, booked or signed without the user's explicit yes for that exact message, invite or document. Claude drafts, the user says "yes", then it goes out from the user's own accounts. One yes per message. Never "yes to all".
  • Stop at the first "no" or any sign of disinterest. A request to stop is honoured forever, across every skill.
  • Every email keeps the opt-out line from the opening thread. Opt-outs are honoured forever.
  • Never invent a number, a result, a client, a review or a deadline.

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.