churn-signals

churn-signals is an Account health & churn prevention skill for AI agents, published by kortix-ai in the suna repository on GitHub. Skillspace rates churn-signals D (68/100) and it passed the safety scan; a judge model has also reviewed it.

Scoring rules for daily churn-risk detection — usage decline, support friction, billing/payment risk, and renewal proximity — plus how to combine them into a ranked at-risk list with a reason and a suggested next step per account.

Grade
D
Quality
68 / 100
Safety
Passed
GitHub stars
20,201

Placed #1 of 6 in the judged category final for Account health & churn prevention.

This rating describes the version of the repository we crawled; it may have changed since, so go by its current files.

Our review

Architecture
100 / 100
Maturity
Basic: a single SKILL.md
Security scan
No issues found
License
Not declared. Check the repository before reusing it.

Judge review

Placed #1 of 6 in the judged category final for Account health & churn prevention.

  • Trigger8888
  • Instructions9393
  • Specificity9292
  • Safety9696
  • Disclosure8585
  • Maintenance8888
A tight daily-cron runbook that combines four read-only signals into one ranked risk table with explicit guardrails: read-only always, a single Slack post, no memory between runs, and a human who decides.

Not checked yet

  • Category is a classifier prediction; no model has read this skill yet
  • No blind task eval yet
  • Scope (portable / vendor / repo-internal) not assessed; only the top of each category is read for scope
  • Sibling files (scripts, references) not fetched; security scan covers SKILL.md only

Skillspace indexes and rates this skill; it does not host or endorse it. Run third-party skills at your own risk.