Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Turn an approved PRD or implementation goal into SRS/FRS technical requirements (How), architecture, contracts, and verification decisions.
.claude/skills/hoangnguyen0403-design-solution/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-11 | ✗→✓ | ▲ Improved | -20% | 0% |
| case-14 | ✗→✓ | ▲ Improved | -26% | 0% |
| case-17 | ✗→✓ | ▲ Improved | 4% | 0% |
| case-19 | ✗→✓ | ▲ Improved | 7% | 0% |
| case-21 | ✗→✓ | ▲ Improved | 5% | 0% |
> !IMPORTANT] > Turn an approved PRD or implementation goal into SRS/FRS technical requirements (How), architecture, contracts, and verification decisions.
Optional args: slug=<feature>, ticket=<id/url>, mode=interactive|autonomous|channel, channel=<id>, auto_continue=true|false, profile=business|hybrid|technical.
When the user asks to perform this workflow, execute the following steps:
Goal: Produce a build-ready technical design with explicit boundaries, contracts, risks, and tests.
common-software-requirements, PRD or ticket, implementation plan, matched framework skills, architecture docs, and trace source BRD-OBJ-* -> REQ-* -> AC-*.container diagram plus one sequence per complex flow via common-architecture-diagramming (evidence cites the SRS or system-design doc, metric from NFR thresholds).docs/srs/srs-[slug].md when file writes are allowed.docs/srs/srs-walkthrough.md.implementation-readiness or dev-fix.slug, SRS path, requirement trace, architecture decisions, diagram paths, contracts, data/migration plan, NFR thresholds, verification matrix, ADR, outcome report, next workflow.md# Technical Design (SRS/FRS): [Name] ## Context ## Requirement Trace (BRD -> PRD -> SRS) ## Architecture & RACI ## Diagrams (Container / Sequence) ## Functional Flows (FRS) ## Parallel Readiness (Mocks/Schemes) ## Requirement Cards ## Contracts (API/Events) ## Data And Migration ## NFR Thresholds & Measurement ## Security And Privacy ## Failure Mode Analysis (FMA) ## Verification Plan & Evidence Matrix ## ADR ## Outcome Report feature_status: design_ready | blocked requirement_trace: BRD-OBJ-* -> REQ-* -> AC-* -> SRS-* completed_evidence: []; missing_evidence: []; decision_needed: []; recommended_next_workflow: implementation-readiness ## Next Workflow implementation-readiness | dev-fix ## Cost Report Call `get_session_cost(workflow="design-solution")` before final handoff.
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→fail | 31,450 | 33,276 | +6% | 1 | 1 | 0% | 6,232 | 7,142 | +15% | 0 | 0 | — |
case-02 | fail→fail | 30,843 | 31,538 | +2% | 1 | 1 | 0% | 6,219 | 7,129 | +15% | 0 | 0 | — |
case-03 | fail→fail | 32,672 | 31,693 | -3% | 1 | 1 | 0% | 6,216 | 7,126 | +15% | 0 | 0 | — |
case-04 | pass→fail | 18,088 | 34,690 | +92% | 1 | 1 | 0% | 2,985 | 6,443 | +116% | 0 | 0 | — |
case-05 | pass→fail | 5,456 | 23,939 | +339% | 1 | 1 | 0% | 988 | 4,509 | +356% | 0 | 0 | — |
case-06 | pass→fail | 13,303 | 17,268 | +30% | 1 | 1 | 0% | 2,928 | 4,246 | +45% | 0 | 0 | — |
case-07 | pass→pass | 17,218 | 12,122 | -30% | 1 | 1 | 0% | 2,939 | 3,038 | +3% | 0 | 0 | — |
case-08 | pass→pass | 16,959 | 14,324 | -16% | 1 | 1 | 0% | 2,953 | 3,450 | +17% | 0 | 0 | — |
case-09 | pass→pass | 5,995 | 2,913 | -51% | 1 | 1 | 0% | 939 | 1,380 | +47% | 0 | 0 | — |
case-10 | fail→fail | 17,078 | 11,061 | -35% | 1 | 1 | 0% | 2,953 | 2,832 | -4% | 0 | 0 | — |
case-11 | fail→pass | 7,801 | 2,652 | -66% | 1 | 1 | 0% | 1,588 | 1,278 | -20% | 0 | 0 | — |
case-12 | pass→pass | 8,507 | 2,352 | -72% | 1 | 1 | 0% | 1,427 | 1,245 | -13% | 0 | 0 | — |
case-13 | pass→pass | 11,650 | 7,141 | -39% | 1 | 1 | 0% | 1,993 | 2,215 | +11% | 0 | 0 | — |
case-14 | fail→pass | 11,964 | 2,809 | -77% | 1 | 1 | 0% | 1,842 | 1,358 | -26% | 0 | 0 | — |
case-15 | fail→fail | 6,870 | 1,353 | -80% | 1 | 1 | 0% | 1,102 | 1,087 | -1% | 0 | 0 | — |
case-16 | pass→pass | 9,302 | 1,677 | -82% | 1 | 1 | 0% | 1,586 | 1,129 | -29% | 0 | 0 | — |
case-17 | fail→pass | 12,671 | 9,032 | -29% | 1 | 1 | 0% | 2,357 | 2,460 | +4% | 0 | 0 | — |
case-18 | pass→pass | 19,085 | 14,694 | -23% | 1 | 1 | 0% | 3,106 | 3,177 | +2% | 0 | 0 | — |
case-19 | fail→pass | 14,590 | 12,096 | -17% | 1 | 1 | 0% | 2,589 | 2,761 | +7% | 0 | 0 | — |
case-20 | fail→fail | 15,516 | 9,298 | -40% | 1 | 1 | 0% | 2,518 | 2,250 | -11% | 0 | 0 | — |
case-21 | fail→pass | 16,688 | 13,413 | -20% | 1 | 1 | 0% | 2,831 | 2,971 | +5% | 0 | 0 | — |
case-22 | fail→pass | 8,996 | 2,612 | -71% | 1 | 1 | 0% | 1,373 | 1,336 | -3% | 0 | 0 | — |
case-23 | pass→pass | 14,294 | 11,222 | -21% | 1 | 1 | 0% | 2,370 | 2,697 | +14% | 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. 23 cases were attempted. The headline lift of +13 percentage points is the difference between those two pass rates over the 23 comparable cases. 4 cases got worse with the skill loaded, and they are included in that figure.
The publisher has shipped newer versions since this run, so these numbers describe v1, not the version currently listed.
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.