Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Facilitates conversational discovery to create Architectural Decision Records (ADRs) for non-functional requirements using the ISO/IEC 25010:2023 quality model. Use when the user wants to document quality attributes, NFR decisions, security/performance/scalability architecture, or design systems with measurable quality criteria. This should trigger for requests such as Create ADR for Non-functional requirements; Document Non-functional requirements; Capture Non-functional requirements; Generate
.claude/skills/jabrena-032-architecture-adr-non-functional-requirements/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-02 | ✗→✓ | ▲ Improved | -1% | 0% |
| case-05 | ✗→✓ | ▲ Improved | 113% | 0% |
| case-07 | ✗→✓ | ▲ Improved | 6% | 0% |
| case-15 | ✗→✓ | ▲ Improved | 28% | 0% |
| case-16 | ✗→✓ | ▲ Improved | -43% | 0% |
Guide stakeholders through a structured conversation to uncover and document architectural decisions for quality attributes using the ISO/IEC 25010:2023 quality model. This is an interactive SKILL. The ADR documents the outcome of the conversation, not the conversation itself. Act as an architecture consultant: challenge-first, consultative, adaptive. Use only the current conversation and repository files explicitly available in the current session.
What is covered in this Skill?
Use challenge-first, consultative discovery in small batches, build on answers, tailor to NFR category. Only create ADR after thorough conversation and user confirmation.
date command before starting to get accurate timestamps for the ADRUse the local shell date command before discovery and use it for ADR timestamps.
Load references/032-architecture-adr-non-functional-requirements.md from this skill and begin with the challenge-first ISO 25010:2023 quality characteristics framing.
Guide discovery in small batches to elicit drivers, constraints, quality priorities, options, and trade-off preferences tailored to the primary NFR category.
Step constraints:
Only after user confirms proceed, create the ADR including measurable Quality Metrics and Success Criteria.
For detailed guidance, examples, and constraints, see references/032-architecture-adr-non-functional-requirements.md.
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-22 | pass→pass | 6,011 | 6,784 | +13% | 1 | 1 | 0% | 1,112 | 1,755 | +58% | 0 | 0 | — |
case-01 | fail→fail | 26,327 | 10,376 | -61% | 1 | 1 | 0% | 3,655 | 964 | -74% | 0 | 0 | — |
case-02 | fail→pass | 13,580 | 8,958 | -34% | 1 | 1 | 0% | 1,986 | 1,971 | -1% | 0 | 0 | — |
case-03 | fail→fail | 25,950 | 6,437 | -75% | 1 | 1 | 0% | 3,776 | 984 | -74% | 0 | 0 | — |
case-04 | pass→pass | 14,167 | 10,131 | -28% | 1 | 1 | 0% | 2,289 | 2,296 | +0% | 0 | 0 | — |
case-05 | fail→pass | 9,998 | 20,462 | +105% | 1 | 1 | 0% | 1,487 | 3,164 | +113% | 0 | 0 | — |
case-06 | fail→fail | 5,871 | 5,135 | -13% | 1 | 1 | 0% | 813 | 1,454 | +79% | 0 | 0 | — |
case-07 | fail→pass | 16,504 | 12,635 | -23% | 1 | 1 | 0% | 2,462 | 2,615 | +6% | 0 | 0 | — |
case-08 | pass→fail | 6,441 | 8,393 | +30% | 1 | 1 | 0% | 959 | 1,246 | +30% | 0 | 0 | — |
case-09 | pass→pass | 16,561 | 13,796 | -17% | 1 | 1 | 0% | 2,490 | 2,298 | -8% | 0 | 0 | — |
case-10 | pass→fail | 6,375 | 7,643 | +20% | 1 | 1 | 0% | 1,005 | 1,115 | +11% | 0 | 0 | — |
case-11 | pass→fail | 6,986 | 6,297 | -10% | 1 | 1 | 0% | 1,138 | 1,091 | -4% | 0 | 0 | — |
case-12 | pass→fail | 4,191 | 5,290 | +26% | 1 | 1 | 0% | 703 | 853 | +21% | 0 | 0 | — |
case-13 | pass→pass | 4,640 | 11,722 | +153% | 1 | 1 | 0% | 743 | 2,218 | +199% | 0 | 0 | — |
case-14 | pass→fail | 7,851 | 7,034 | -10% | 1 | 1 | 0% | 1,351 | 1,148 | -15% | 0 | 0 | — |
case-15 | fail→pass | 9,498 | 10,425 | +10% | 1 | 1 | 0% | 1,372 | 1,756 | +28% | 0 | 0 | — |
case-16 | fail→pass | 10,788 | 2,014 | -81% | 1 | 1 | 0% | 1,630 | 936 | -43% | 0 | 0 | — |
case-17 | pass→fail | 3,562 | 7,800 | +119% | 1 | 1 | 0% | 446 | 1,066 | +139% | 0 | 0 | — |
case-18 | fail→pass | 18,431 | 19,652 | +7% | 1 | 1 | 0% | 2,727 | 3,640 | +33% | 0 | 0 | — |
case-19 | pass→fail | 19,262 | 12,162 | -37% | 1 | 1 | 0% | 2,784 | 2,596 | -7% | 0 | 0 | — |
case-20 | pass→fail | 10,432 | 10,727 | +3% | 1 | 1 | 0% | 1,802 | 1,138 | -37% | 0 | 0 | — |
case-21 | pass→fail | 19,953 | 19,884 | -0% | 1 | 1 | 0% | 3,059 | 2,951 | -4% | 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 13 counted toward the lift figure. The other 9 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 -14 percentage points is the difference between those two pass rates over the 13 comparable cases. 9 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.