agentleFS
itinovo-crmitinovo-crm/claude-plugin/skills/follow-up-open-quotes/SKILL.md

follow-up-open-quotes

Skill1 starsChanged 22 days agoMITView on GitHub

Find the quotes in itinovo still waiting for an answer — sent and not answered, opened, with a change request, expired, or drafts left unsent — and propose the next step for each — a follow-up task with a short draft message, a new version, or the lead marked lost with its reason. Use when the user asks which quotes are waiting, whom to call back, or to tidy up the pipeline.

The file

We split this skill into the rules it gives an agent

3 rules. About 0 are common, 3 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈3

    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:

    Never send anything to the client: the draft message is for the user, who sends it from the itinovo app.

    line 37
  2. Distinctive:

    Never mark a lead lost without the user's yes for that lead.

    line 38
  3. Distinctive:

    Never add a second follow-up where one is already open.

    line 39

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 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

Following up the quotes waiting for an answer

Steps

  1. Read what is waiting: get_overview (view: follow_ups, scope: quotes) gives the leads itinovo itself suggests following up, with how long they have been still. Then list_quotes with status: sent, viewed, changes_requested and expired, one call each, reading every page: each quote comes with the day it was sent and the day the client opened it.
  2. Read only what decides the next step: get_quote (include: ["messages"]) for the client's last message, get_lead (include: ["tasks"]) for a follow-up already planned.
  3. Sort them:
    • a change request → a new version, as the revise-a-sent-quote skill does;
    • opened, no answer → a follow-up now;
    • sent, never opened → a follow-up by phone: the email may not have reached the client;
    • expired → a follow-up with a new version, or the lead lost;
    • a draft never sent, or a trip whose dates have passed → the user finishes and sends it from the app, or the lead is lost;
    • a follow-up task already open → leave it, and say so.
  4. Show a short table — client, trip, sent on, days waiting, opened or not, proposed step — and wait for the user to choose.
  5. Do what the user chose:
    • a follow-up with save_task (leadId, title, dueDate, priority), with a short draft message in the client's language in description, for the user to send from itinovo or to say on the phone;
    • a lead lost with set_lead_state (action: lost, leadId, reason, note, closeTasks: true), one lead at a time, each after the user's yes. The reason is the client's: too_expensive, dates_not_flexible, chose_competitor, changed_plans, no_response (only when the client never answered) or other with a note. action: reactivate brings a lead back.
  6. Report what was planned, what was marked lost and what is left to the user.

Rules

  • Never send anything to the client: the draft message is for the user, who sends it from the itinovo app.
  • Never mark a lead lost without the user's yes for that lead.
  • Never add a second follow-up where one is already open.

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.