hummbl-io/agent-skills/churn-analysis

Claude Code and agent skill by hummbl-io/agent-skills

Trust tier 3
  • community
Source check pending

Checking that the SKILL.md file is still in the repository.

Analyze client churn signals including engagement drops, support spikes, and renewal risk scoring

Install

npx vskill@latest install hummbl-io/agent-skills/churn-analysis

SKILL.md

The same SKILL.md was published earlier as hummbl-io/agent-skills/churn-analysis.

Churn Analysis

Detect early warning signs of client churn by analyzing engagement frequency, support interaction patterns, and renewal timeline proximity. Produces a risk score per client with actionable recommendations to improve retention.

When to Use

  • Quarterly review of client health across the portfolio
  • Before a renewal conversation to understand risk level
  • When engagement frequency with a client drops noticeably
  • After a support escalation to assess broader relationship health

Execution

  1. Parse $ARGUMENTS for client filter (default: all), lookback period (default: 90d), and signal types.
  2. Gather engagement data from available sources:
  • CRM interactions (_state/crm/ or Google Sheets via [crm])
  • Email/meeting frequency (calendar, sent emails)
  • Bus messages and deliverable history
  • Invoice and payment patterns (_state/billing/)
  1. For each client, compute signal scores:
  • Engagement: Compare current-period interaction frequency to baseline. Flag drops > 30%.
  • Support: Count support requests, escalations, and unresolved issues. Flag volume spikes > 2x.
  • Renewal: Days until contract end, renewal discussion status, competitor mentions.
  1. Calculate composite churn risk score (0-100, where 100 = highest risk).
  2. Classify each client: GREEN (0-30), YELLOW (31-60), RED (61-100).
  3. Generate specific retention recommendations per at-risk client.

Output Format

Churn Analysis | period | client_filter
## Portfolio Summary
- Clients analyzed: N
- GREEN: N | YELLOW: N | RED: N
## Risk Scores
| Client | Risk Score | Trend | Top Signal | Days to Renewal |
|--------|-----------|-------|------------|-----------------|
| {name} | {0-100} | {up/down/stable} | {signal} | {N or N/A} |
## At-Risk Details
### {Client Name} -- {YELLOW|RED}
- Engagement: {trend description with data}
- Support: {volume and severity}
- Renewal: {timeline and status}
- Recommendation: {specific action}
Next action: {suggestion or "No further action needed"}

Skill Chains

After this skill...Consider...
Identifying at-risk clients[engagement-tracker] for detailed interaction history
Finding upcoming renewals[renewal-check] to draft renewal proposals
Drafting retention outreach[follow-up] to send targeted communication

Security

  • Security scanPassed, 90 of 100Pattern checks on the skill's files.
  • Model reviewPassed

Quality evaluation

  • Task evaluationNot runNo evaluation yet. Run one in Skill Studio.

Source

Popularity

7-day trend score
5

Not refreshed yet.

Works with

Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.

  • Claude Code
  • Cursor
  • GitHub Copilot
  • Windsurf
  • Codex
  • Gemini CLI
  • Cline
  • Amp
  • Roo Code
  • Goose
  • Continue
  • Kilo Code
  • Junie
  • Trae
  • OpenHands
  • Qwen Code
  • AI Agent
  • Tabnine Chat
  • Sourcegraph Cody
  • Amazon Q
  • Firebase Genkit
  • Sweep
  • Devin
  • Phind
  • Mentat
  • Claude Desktop
  • Aider
  • GPT Pilot
  • Plandex
  • bolt.new
  • v0
  • Replit Agent
  • Anse
  • TypingMind
  • BetterChatGPT
  • LibreChat
  • Warp AI
  • Pieces
  • Fig AI
Embed badge
vskill VERIFIED badge
[![vskill VERIFIED](https://verified-skill.com/api/v1/skills/hummbl-io/agent-skills/churn-analysis/badge)](https://verified-skill.com/skills/hummbl-io/agent-skills/churn-analysis)

Something wrong with this skill or its page? Tell us.