agentleFS
Sign inStart free
JakeschincariolJakeschincariol/closer-skill/win-back/SKILL.md

win-back

Skill33 starsChanged 11 days agoMITView on GitHub

Win-Back. Brings back the deals that went quiet. Finds lost deals worth one more try (bad timing, budget, still thinking, no decision) once enough time has passed or on the date they asked you to come back, plus open deals that went silent after every follow-up, and writes one short, honest check-in from the reason it was lost. One win-back per deal, never to anyone who said no or unsubscribed. Use when the user says "win back", "revive old deals", "follow up on lost deals", "who went quiet", "re-engage", "dead leads", or once a week.

1 other project uses a version of this.

Adopted by

Most recently taken up by

  • Other versions1 project uses a version of this.

    Word for word · 0

    None found.

    Edited · 0

    None found.

    Wrote their own version · 1

    1. Castan-AI/founder-commands★ 1same 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

10 rules. About 0 are common, 8 are distinctive, and 2 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈8

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 2

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Lost to someone else: not before 180 days, and only a friendly "how's it going".

    line 31
  2. Very specific:

    Open but silent: no activity for 30 days after /follow-up used all 3 follow-ups.

    line 32
  3. Distinctive:

    Ask: "Send this to Tom at Lakeline Roofing?

    line 42
  4. Very specific:

    If they reply, it is a conversation: /follow-up reply, then /scheduler.

    line 45
  5. Distinctive:

    Never emails anyone who said no, unsubscribed or is do-not-contact.

    line 57
  6. Distinctive:

    Never sends a second win-back after an unanswered first one.

    line 58
  7. Distinctive:

    Never invents a reason to write ("just saw your post", "my colleague mentioned you") that is not true.

    line 59
  8. Distinctive:

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

    line 66
  9. Distinctive:

    Every email is honest about who is writing and keeps a plain way to opt out.

    line 67
  10. Distinctive:

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

    line 68

≈ “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

win-back

"Not now" is not "no". The Win-Back skill remembers who said not now and comes back once, at the right time, with a reason to talk. It never chases anyone who said no.

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

python3 "${CLAUDE_SKILL_DIR}/winback.py" list --today 2026-10-29
python3 "${CLAUDE_SKILL_DIR}/winback.py" draft --deal lakeline-website --today 2026-10-29
python3 "${CLAUDE_SKILL_DIR}/winback.py" record --deal lakeline-website --text-file /tmp/w.txt \
    --approval "yes" --at 2026-10-29T10:00

Who it tries, and when

  • Lost for timing, budget, "let me think" or no decision: 60 days after it was lost, or on the deal's own revisit date if they named one ("ask again in the fall": set revisit on the deal).
  • Lost to someone else: not before 180 days, and only a friendly "how's it going".
  • Open but silent: no activity for 30 days after /follow-up used all 3 follow-ups.
  • Never: anyone who said no, unsubscribed or is do-not-contact. Never twice: one win-back per deal, and if there is no reply, that is the end. Another try only after they write back, and 90 days later.

Steps, once a week

  1. winback.py list. Read the READY ones to the user with why, biggest first. Mention LATER ones with their date.
  2. For each the user wants, winback.py draft. Make it more specific with one true, new thing if you have one (a new plan, a result for a similar business). Keep it under 60 words, and keep the easy out: "If not, no problem at all, just say so and I'll leave it."
  3. Ask: "Send this to Tom at Lakeline Roofing? Reply yes or no."
  4. On a yes: a Gmail draft from the user's account, which the user sends (or sent through the Gmail connector right after that yes). Then winback.py record --approval "<their yes>". The deal opens again.
  5. If they reply, it is a conversation: /follow-up reply, then /scheduler.

Example

Tom Becker at Lakeline Roofing liked the idea in July but said it was roofing season: "ask again in the fall." Lost on Aug 10 for timing. On Oct 29 list shows READY, and the draft reads: "Hi Tom, when we spoke you said the timing wasn't right until the fall. Is now any better for website + reviews widget? If not, no problem at all, just say so and I'll leave it." Elena Ruiz at Mesa Verde Med Spa asked to be removed, so she shows as NEVER. (Illustrative: both businesses are fictional.)

What it never does

  • Never emails anyone who said no, unsubscribed or is do-not-contact.
  • Never sends a second win-back after an unanswered first one.
  • Never invents a reason to write ("just saw your post", "my colleague mentioned you") that is not true.

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 is honest about who is writing and keeps a plain way to opt out. 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.

Check your setup, free