posthog-pre-cancellation-behavior
posthog-pre-cancellation-behavior is an Account health & churn prevention skill for AI agents, published by PostHog in the posthog.com repository on GitHub. Skillspace rates posthog-pre-cancellation-behavior D (59/100) and it passed the safety scan; the rating is based on static analysis only.
Find the shared product-usage warning pattern before churn: pull cancellation dates from Stripe or Chargebee and examine the roughly 30 days of activity before each one, saved as a reusable PostHog insight. Use this whenever someone wants an early-warning churn signal from behavior, asks what churning customers do (or stop doing) before they leave, how usage or activity changes before cancellation, or the usage drop that precedes churn. Triggers on phrasings like 'what do customers do before they cancel', 'pre-cancellation behavior', 'churn warning signs', 'how does usage change before churn', or 'leading indicators of churn'. Boundary: this is behavioral/usage-based churn prediction with no support data. If the question is specifically about SUPPORT TICKETS or Zendesk/Intercom predicting churn, use posthog-support-tickets-churn. It sets up the Stripe/Chargebee source if needed and builds the insight end-to-end.
- Grade
- D
- Quality
- 59 / 100
- Safety
- Passed
- GitHub stars
- 1,138
Unproven: rated by static analysis only, not yet compared head-to-head.
Our two independent classifiers differ on this skill's category, so treat the placement as provisional.
This rating describes the version of the repository we crawled; it may have changed since, so go by its current files.
Our review
- Architecture
- 84 / 100
- Maturity
- Basic: a single SKILL.md
- Security scan
- No issues found
- License
- Not declared. Check the repository before reusing it.
Not checked yet
- Category is a classifier prediction; no model has read this skill yet
- Not judged on the rubric yet (not a contender in its category)
- 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.