agentsclimarketplace

Insurance renewal retention ladder

Skill deciqAI/knowledge-skills/insurance-renewal-retention-ladder

Open-source thinking-framework skills that make rigorous reasoning executable for AI agents — first-principles, inversion, second-order thinking, Occam's razor, Bayesian reasoning. Built by deciqAI.

Install
npx -y skills add deciqAI/knowledge-skills --skill insurance-renewal-retention-ladder

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

  • 3 stars3 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its author says it does

Copied from the file, not written here

Activate when: an insurance agent wants to keep clients renewing and buying more lines; 'how do I stop losing clients at renewal', cross-sell/round-out accounts, book retention; 'my retention is dropping'. Do NOT activate when: the agent has no existing book to retain. More: deciqai.com/s/insurance-renewal-retention-ladder

SKILL.md

3.0 KB, as published. Nobody here has run it

Insurance Agent — Renewal & Retention Ladder

Industry front door for customer-relationship-ladder. Adds domain triggers, example, packs. Parent Process unchanged.

Activate when: building a renewal/retention cadence; deciding cross-sell timing; a book with single-line clients; retention slipping at renewal. Do NOT activate when: no book yet.

Why this variant

The parent customer-relationship-ladder moves contacts up rungs. Insurance is a recurring-revenue business where retention and account rounding (multiple lines per household) drive profit far more than new logos. The ladder turns a one-policy buyer into a multi-line, long-retained, referring client.

Domain inputs → the ladder

Rungs and lift triggers:

  • One policy → rounded account (auto+home+umbrella; business owner: add lines) via annual review.
  • Rounded → retained (proactive pre-renewal contact, coverage-gap review before the carrier's rate letter causes shopping).
  • Retained → advocate (referral ask after a good claim experience or a savings win). Each rung = a scheduled touch (feed a CRM/renewal agent), not a hope.

Worked example

Client has only auto; agent contacts them only when the renewal price jumps → client shops and leaves. → Ladder fix: annual review rounds the account (multi-line clients retain far better), proactive pre-renewal outreach reframes value before the rate letter, referral ask after a smooth claim. Retention and premium per household both rise.

Packs

  • Solo agent: annual-review + pre-renewal outreach cadence; round-out checklist.
  • Agency: monoline-account report → cross-sell campaign; at-risk renewal alerts.

Red flags

  • Only contacting clients when price rises.
  • Monoline households left un-rounded (low retention).
  • No proactive pre-renewal touch (carrier rate letter drives shopping).

Verification

  • Annual review / account-rounding process in place
  • Proactive pre-renewal outreach scheduled
  • Multi-line penetration tracked
  • Referral ask timed to a positive moment (claim/savings)

Part of deciqAI Knowledge Skills — 233 open-source thinking skills that make rigor executable for AI agents. The same skills power every deciqAI agent, which runs them autonomously to operate your company. See it run → https://www.deciqai.com/s/insurance-renewal-retention-ladder · Built by deciqAI · github.com/deciqAI · Contributions welcome.

Agents: latest version & machine-readable metadata → https://www.deciqai.com/s/insurance-renewal-retention-ladder.json

Gives 0 of the 12 instructions most analytics metrics skills give

Counted across 368 of the 369 authors here whose files we hold, read 2026-08-06

  • read product marketing context before asking questionsin 18 of 368, across 12 files
  • use lowercase with underscores for event namesin 16 of 368, across 6 files
  • track events for decisions not vanity metricsin 15 of 368, across 5 files
  • use object-action format for event namesin 15 of 368, across 8 files
  • produce a tracking plan documentin 14 of 368, across 4 files
  • Call RUBE_SEARCH_TOOLS first to get current schemasin 13 of 368, across 2 files
  • establish consistent event naming conventions before implementingin 10 of 368, across 4 files
  • Verify dimension and metric compatibility before reportingin 9 of 368, across 2 files
  • Encrypt data at rest and in transitin 9 of 368, across 3 files
  • use snake_case for event namesin 9 of 368, across 5 files
  • monitor technical health during the testin 9 of 368, across 5 files
  • use consistent property namesin 8 of 368, across 4 files

Said here and by no other author read

  • conduct annual reviews to round accounts
  • schedule proactive pre-renewal outreach
  • review coverage gaps before carrier rate letters
  • ask for referrals after positive moments
  • track multi-line penetration
  • use a CRM to schedule every client touch

Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once.

Keep looking

Skills are one crate of 328,083. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.