Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add guia-matthieu/clawfu-skills --skill churn-predictiongit clone --depth 1 https://github.com/guia-matthieu/clawfu-skillsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/guia-matthieu/clawfu-skills/churn-prediction)<a href="https://agentmods.dev/skills/guia-matthieu/clawfu-skills/churn-prediction"><img src="https://agentmods.dev/badge/skills/guia-matthieu/clawfu-skills/churn-prediction/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/guia-matthieu/clawfu-skills/churn-prediction"><img src="https://agentmods.dev/badge/skills/guia-matthieu/clawfu-skills/churn-prediction.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00023 | $0.03331 |
| Opus 5 | $0.00012 | $0.01665 |
| Sonnet 5 | $0.00005 | $0.00666 |
| Haiku 4.5 | $0.00002 | $0.00333 |
Grade A, and why
churn-prediction scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 459 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Churn Prediction
Detect early warning signals of customer churn through systematic analysis of usage patterns, support interactions, and relationship health.
When to Use This Skill
- Monthly/quarterly churn risk reviews
- Prioritizing CSM intervention
- Building early warning systems
- Post-mortem analysis on lost customers
- Executive churn reporting
Methodology Foundation
Based on Lincoln Murphy's Churn Analysis and ProfitWell Retention Research, analyzing:
- Product engagement decay
- Support sentiment trends
- Payment behavior changes
- Relationship deterioration
- Competitive signals
What Claude Does vs What You Decide
| Claude Does | You Decide |
|---|---|
| Identifies risk signals | Save vs. let go decisions |
| Calculates risk scores | Resource allocation |
| Suggests interventions | Discount/concession offers |
| Prioritizes at-risk accounts | Executive escalation timing |
| Analyzes churn patterns | Retention strategy changes |
What This Skill Does
- Signal detection - Identify behavioral indicators of churn risk
- Risk scoring - Calculate churn probability
- Root cause analysis - Why are they likely to leave?
- Intervention planning - What actions could save them?
- Pattern recognition - Learn from past churned accounts
How to Use
Assess churn risk for this customer:
Account: [Company Name]
Contract: $[ARR], Renewal: [Date]
Tenure: [Months]
Usage Signals:
- Login frequency: [trend]
- Feature adoption: [% and trend]
- Active users: [current vs licensed]
- Key feature usage: [specific metrics]
Support Signals:
- Recent tickets: [count and nature]
- CSAT trend: [improving/stable/declining]
- Escalations: [any open or recent]
- Sentiment: [last few interactions]
Relationship Signals:
- Champion status: [engaged/disengaged/left]
- Exec sponsor: [status]
- NPS response: [score and comments]
- QBR attendance: [pattern]
Financial Signals:
- Payment status: [current/late]
- Contract discussions: [any mentions of changes]
- Competitor mentions: [any signals]
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 9d ago First seen · 459 lines · 23 tokens per session scan A 1581ba470ba8
churn-prediction is a skill published in the GitHub repository guia-matthieu/clawfu-skills (149 stars, last pushed 5mo ago), licensed MIT. It adds 23 tokens to every session and 3,331 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
after-action-report
Run a structured after-action review (postmortem, retrospective) on a launch, incident, or completed project to capture timeline, root cause analysis, contributing factors, and actionable lessons. Use this skill whenever the user wants to run a postmortem, retrospective, AAR, or after-action review on any past event.…
azure-devops
Manage Azure DevOps projects, work items, repos, PRs, pipelines, wikis, test plans, security alerts, variable groups, environments/approvals, branch policies, and attachments. Use when user asks to: manage sprints, create/update work items, list repos, create PRs, run pipelines, search code, manage wiki pages, check…
ads-performance-analytics
How to read paid media dashboards without fooling yourself. Attribution models, platform reporting quirks, multi-platform reconciliation, ROAS vs LTV horizon traps, statistical noise in performance metrics, incrementality testing, and the failure modes that produce expensive lessons. Triggers on read paid media…
okr-design
OKR design as actually shipped, not as conference-talk theory. Outcome statements that drive decisions, key results that measure the right thing, scoring discipline, mid-quarter recalibration, and the difference between sandbagged OKRs (always 100%) and aspirational OKRs (always 30%) and stretch OKRs (genuine ambition…
paid-media-strategy
A discipline for running paid media that does not light money on fire. Hypothesis writing for paid spend, channel selection, budget allocation, audience targeting, bid strategy, campaign types, what NOT to spend on, attribution reality, and the failure modes that produce expensive lessons. Triggers on paid media…
onboard
Sets up ai-toolkit in a project: symlinks, CLAUDE.md, intent interview. Triggers: onboard, setup project, install ai-toolkit, migrate project.