Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Tech debt assessment that identifies, classifies, and prioritizes maintainability problems — helping teams build a refactoring roadmap — drawing on twelve classic engineering books. Triggers when: user asks about tech debt, refactoring priorities, what to clean up first, or asks "why...
.claude/skills/sickn33-brooks-debt/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-02 | ✗→✓ | ▲ Improved | 204% | 0% |
| case-04 | ✗→✓ | ▲ Improved | -3% | 0% |
| case-05 | ✗→✓ | ▲ Improved | 49% | 0% |
| case-08 | ✗→✓ | ▲ Improved | 161% | 0% |
| case-10 | ✗→✓ | ▲ Improved | 10% | 0% |
Use this skill when you need tech debt assessment that identifies, classifies, and prioritizes maintainability problems — helping teams build a refactoring roadmap — drawing on twelve classic engineering books. Triggers when: user asks about tech debt, refactoring priorities, what to clean up first, or asks "why...
../_shared/common.md for the Iron Law, Project Config, Report Template, and Health Score rules../_shared/source-coverage.md for book-level coverage, exceptions, and tradeoffs../_shared/decay-risks.md for symptom definitions and source attributionsdebt-guide.md in this directory for the debt classification frameworkIf the user has not described the codebase or pointed to specific areas: apply Auto Scope Detection from ../_shared/common.md to determine the assessment scope before proceeding.
Mode line in report: Tech Debt Assessment
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-06 | fail→fail | 8,077 | 6,081 | -25% | 1 | 1 | 0% | 1,546 | 1,390 | -10% | 0 | 0 | — |
case-01 | fail→fail | 7,942 | 6,967 | -12% | 1 | 1 | 0% | 1,325 | 1,499 | +13% | 0 | 0 | — |
case-02 | fail→pass | 5,525 | 14,607 | +164% | 1 | 1 | 0% | 987 | 3,001 | +204% | 0 | 0 | — |
case-03 | fail→fail | 8,271 | 11,697 | +41% | 1 | 1 | 0% | 1,365 | 2,371 | +74% | 0 | 0 | — |
case-04 | fail→pass | 12,289 | 10,242 | -17% | 1 | 1 | 0% | 2,204 | 2,130 | -3% | 0 | 0 | — |
case-05 | fail→pass | 19,201 | 26,322 | +37% | 1 | 1 | 0% | 3,706 | 5,517 | +49% | 0 | 0 | — |
case-07 | fail→fail | 8,727 | 8,932 | +2% | 1 | 1 | 0% | 1,496 | 1,819 | +22% | 0 | 0 | — |
case-08 | fail→pass | 8,243 | 18,908 | +129% | 1 | 1 | 0% | 1,383 | 3,612 | +161% | 0 | 0 | — |
case-09 | fail→fail | 16,423 | 13,193 | -20% | 1 | 1 | 0% | 2,877 | 2,634 | -8% | 0 | 0 | — |
case-10 | fail→pass | 14,603 | 15,538 | +6% | 1 | 1 | 0% | 2,686 | 2,947 | +10% | 0 | 0 | — |
case-11 | pass→pass | 18,849 | 28,530 | +51% | 1 | 1 | 0% | 3,325 | 5,979 | +80% | 0 | 0 | — |
case-12 | fail→fail | 15,510 | 8,362 | -46% | 1 | 1 | 0% | 2,909 | 1,858 | -36% | 0 | 0 | — |
case-13 | fail→fail | 8,851 | 8,002 | -10% | 1 | 1 | 0% | 1,543 | 1,794 | +16% | 0 | 0 | — |
case-14 | fail→pass | 9,994 | 21,376 | +114% | 1 | 1 | 0% | 1,909 | 4,377 | +129% | 0 | 0 | — |
case-15 | fail→pass | 14,553 | 27,512 | +89% | 1 | 1 | 0% | 2,461 | 5,236 | +113% | 0 | 0 | — |
case-16 | fail→fail | 9,187 | 7,055 | -23% | 1 | 1 | 0% | 1,446 | 1,641 | +13% | 0 | 0 | — |
case-17 | fail→fail | 11,705 | 4,399 | -62% | 1 | 1 | 0% | 1,899 | 616 | -68% | 0 | 0 | — |
case-18 | pass→pass | 9,617 | 14,757 | +53% | 1 | 1 | 0% | 2,246 | 3,046 | +36% | 0 | 0 | — |
case-19 | pass→pass | 15,934 | 17,375 | +9% | 1 | 1 | 0% | 3,129 | 4,064 | +30% | 0 | 0 | — |
case-20 | pass→pass | 8,406 | 7,418 | -12% | 1 | 1 | 0% | 1,507 | 1,737 | +15% | 0 | 0 | — |
case-21 | pass→pass | 6,513 | 4,133 | -37% | 1 | 1 | 0% | 1,243 | 1,285 | +3% | 0 | 0 | — |
case-22 | pass→pass | 16,698 | 17,101 | +2% | 1 | 1 | 0% | 3,781 | 4,049 | +7% | 0 | 0 | — |
DecimalAI ran this skill against gemini-3.6-flash twice over the same eval suite — once with the skill loaded and once without — and compared the two runs case by case. 22 cases were attempted, and 21 counted toward the lift figure. The other 1 produced results that are not comparable between the two arms, so they are excluded from the headline rather than averaged into it. The headline lift of +32 percentage points is the difference between those two pass rates over the 21 comparable cases. 3 cases got worse with the skill loaded, and they are included in that figure.
Without the skill loaded, the model failed this case. With it loaded, the same prompt on the same model passed. This is one improved case from the latest verified run; every case, including any that regressed, is in the table above.
Other measured skills in the registry, with their headline benchmark lift.