compounding-roi-hawk

Evaluates incident prevention and lifecycle handoffs using compounding ROI metrics and fail-closed gates.

1|Updated Aug 27, 2025
One-click install
npx skills add https://github.com/IgorGanapolsky/Random-Timer --skill compounding-roi-hawk-igorganapolsky
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: compounding-roi-hawk
Source: https://github.com/IgorGanapolsky/Random-Timer/tree/main/.claude/skills/compounding-roi-hawk
Command: npx skills add https://github.com/IgorGanapolsky/Random-Timer --skill compounding-roi-hawk-igorganapolsky

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) components.

What problem does it solve? Teams ship AI-generated code faster but lack shared intelligence across the incident lifecycle, so the same failures recur and recovery work never compounds into prevention. This Skill applies PlayerZero-style compounding ROI methods—shared lifecycle graphs, prevention recipes, and hawk metrics—without buying any SaaS product. ## Core Features & Use Cases - Lifecycle handoff validation: Uses evaluate_lifecycle_handoff to require a shared context id across stages (sre, quality, review, planning) or fail closed. - Hawk metrics evaluation: Uses evaluate_hawk_metrics to rank work by WQTU, paywall attempt-to-success rate, incident recurrence, and escape rate instead of PR velocity. - Prevention recipes: Uses evaluate_prevention_recipe to encode every resolved incident as a pattern plus an executable gate, so recovery without a gate is rejected. - Use Case: After resolving a paywall incident where paywall_view events had zero purchase_attempt, run the compounding ROI script with the incident context id, recurrence metrics, and a gate command; the claim of compounding ROI is allowed only when every JSON check returns ok and the process exits 0. ## Quick Start Ask the assistant to evaluate whether your resolved incident qualifies as compounding ROI by running the compounding_roi script with your source stage, target stages, context id, metrics, pattern, and gate.

Frequently Asked Questions about compounding-roi-hawk

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I measure compounding ROI from incident resolution?

Run the compounding_roi script with your source stage, target stages, context id, and metrics such as WQTU, paywall attempt success, and incident recurrence. The claim is allowed only when every JSON check returns ok and the process exits 0.

What are hawk metrics versus mouse metrics?

Hawk metrics track prevention outcomes: WQTU, paywall attempt-to-success rate, incident recurrence, and escape rate. Mouse metrics track raw velocity like faster PRs, which this Skill explicitly deprioritizes when ranking work.

Does this require a PlayerZero subscription or paid RCA platform?

No. The Skill explicitly forbids subscribing to PlayerZero or adding paid RCA platforms. It reuses the methods—shared lifecycle graphs, prevention recipes, and hawk metrics—on your own code, telemetry, deploys, and resolution history.

Why does the compounding ROI check exit with code 2?

Exit code 2 means incomplete controls: missing evidence, a missing context id, or a resolved incident without an executable gate. Missing evidence is treated as failure, not approval, because the Skill fails closed.

When should I not use this approach?

Avoid it when you only need session-only memory or one-off fixes, since the method requires a persistent graph that survives the chat. It is also unsuitable if your goal is velocity dashboards rather than prevention and recurrence reduction.