Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Identify patent coverage gaps — feature cross-matrix blank areas revealing unprotected technology combinations. Budget: 150 patent families, 10 claim parses, 60 web searches.
.claude/skills/yogsoth-ai-white-space-analysis/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-04 | ✗→✓ | ▲ Improved | 40% | 0% |
| case-05 | ✗→✓ | ▲ Improved | 85% | 0% |
| case-07 | ✗→✓ | ▲ Improved | -8% | 0% |
| case-14 | ✗→✓ | ▲ Improved | -4% | 0% |
| case-18 | ✗→✓ | ▲ Improved | 51% | 0% |
Identifies gaps in patent coverage by constructing feature cross-matrices and finding blank areas where no patents exist. Reveals opportunities for new filings.
Map the patent coverage landscape as a multi-dimensional feature matrix and identify unprotected technology combinations — areas where innovation is possible without infringing existing IP.
| Metric | Target | |--------|--------| | Patent families analyzed | 150 | | Claim parses | 10 | | Web searches completed | 60 |
| Metric | Target | Current | % | |--------|--------|---------|---| | Patent families analyzed | 150 | 0 | 0% | | Claim parses completed | 10 | 0 | 0% | | Web searches completed | 60 | 0 | 0% | | Feature dimensions defined | — | 0 | — | | White spaces identified | — | 0 | — |
HARD-GATE: Cannot exit iteration loop until 80% of patent families (120) and web searches (48) budget met.
| Tactic | When to Use | |--------|-------------| | patent-family-tracing | Fill coverage map by tracing families in each matrix cell | | classification-navigation | Define feature dimensions from IPC/CPC hierarchy | | claim-decomposition | Extract feature elements from key patents to define matrix axes |
| SOP | Role in This Strategy | |-----|----------------------| | patent-query-formulation | Generate queries for each feature combination | | patent-categorization | Assign patents to matrix cells | | white-space-mapping | Construct cross-matrix and identify blanks | | claim-parsing | Extract features from key patents for axis definition | | trend-analysis | Identify which white spaces are trending toward filling | | saturation-detection | Confirm matrix coverage is complete | | patent-synthesis | Produce white space opportunity report |
claim-decomposition on key patents to identify feature dimensionswhite-space-mappingpatent-query-formulationpatent-family-tracing to ensure complete cell coveragepatent-categorizationtrend-analysis to assess which gaps are closingmarkdown# White Space Analysis: [Technology Domain] ## Feature Dimensions [Axis definitions with rationale] ## Coverage Matrix [Cross-matrix with patent counts per cell, blanks highlighted] ## Identified White Spaces (ranked by opportunity) | Rank | Feature Combination | Adjacent Patents | Trend | Opportunity Score | |------|--------------------|--------------------|-------|-------------------| ## Opportunity Assessment [For each top white space: technical feasibility, market potential, filing risk] ## Recommendations [Prioritized list of filing opportunities]
<!-- BEGIN available-tables (generated) -->
Optional, no fixed order; the final leaf is always a sop.
| Tactic | When to use | | --- | --- | | classification-navigation | IPC/CPC hierarchy drill-down and lateral expansion for patent discovery | | knowledge-acquisition-claim-decomposition | Independent/dependent claim parsing, element extraction, and feature mapping to technical domains | | patent-family-tracing | Forward/backward patent citation and priority tracing until saturation |
Optional, no fixed order; the final leaf is always a sop.
| SOP | When to use | | --- | --- | | claim-parsing | Patent claim syntax parsing — independent/dependent relationships and element extraction | | knowledge-acquisition-saturation-detection | Determine when additional searching yields diminishing returns. Analyzes the latest expansion batch against existing corpus to judge continue/near-saturation/saturated. Used by snowball and systematic-survey. | | patent-categorization | Classify patents by tech subdomain, application scenario, and value chain position | | patent-query-formulation | Construct keyword + IPC/CPC + assignee combination search strategies for patent databases | | patent-synthesis | Produce final structured patent intelligence report from all analysis results | | trend-analysis | Patent filing volume time-series, technology lifecycle stage, and S-curve analysis | | white-space-mapping | Feature cross-matrix construction and blank area identification for patent opportunity mapping |
<!-- END available-tables (generated) -->
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→fail | 49,050 | 56,879 | +16% | 1 | 1 | 0% | 8,278 | 10,110 | +22% | 0 | 0 | — |
case-02 | fail→fail | 55,316 | 19,187 | -65% | 1 | 1 | 0% | 8,285 | 1,744 | -79% | 0 | 0 | — |
case-03 | fail→fail | 46,678 | 9,388 | -80% | 1 | 1 | 0% | 8,277 | 2,298 | -72% | 0 | 0 | — |
case-04 | fail→pass | 14,675 | 16,179 | +10% | 1 | 1 | 0% | 2,185 | 3,055 | +40% | 0 | 0 | — |
case-05 | fail→pass | 28,752 | 36,356 | +26% | 1 | 1 | 0% | 3,919 | 7,247 | +85% | 0 | 0 | — |
case-06 | pass→fail | 16,504 | 3,408 | -79% | 1 | 1 | 0% | 1,848 | 1,651 | -11% | 0 | 0 | — |
case-07 | fail→pass | 23,439 | 14,513 | -38% | 1 | 1 | 0% | 2,817 | 2,605 | -8% | 0 | 0 | — |
case-08 | pass→pass | 15,979 | 24,185 | +51% | 1 | 1 | 0% | 2,569 | 4,149 | +62% | 0 | 0 | — |
case-20 | pass→pass | 13,853 | 11,533 | -17% | 1 | 1 | 0% | 2,044 | 2,173 | +6% | 0 | 0 | — |
case-09 | pass→pass | 17,706 | 4,992 | -72% | 1 | 1 | 0% | 1,935 | 1,924 | -1% | 0 | 0 | — |
case-10 | pass→pass | 25,679 | 30,492 | +19% | 1 | 1 | 0% | 3,582 | 5,504 | +54% | 0 | 0 | — |
case-11 | pass→pass | 21,808 | 21,442 | -2% | 1 | 1 | 0% | 3,046 | 3,513 | +15% | 0 | 0 | — |
case-12 | pass→fail | 28,539 | 39,227 | +37% | 1 | 1 | 0% | 4,046 | 6,970 | +72% | 0 | 0 | — |
case-13 | pass→fail | 22,695 | 21,510 | -5% | 1 | 1 | 0% | 2,767 | 3,771 | +36% | 0 | 0 | — |
case-14 | fail→pass | 19,127 | 10,638 | -44% | 1 | 1 | 0% | 2,960 | 2,833 | -4% | 0 | 0 | — |
case-15 | fail→fail | 48,656 | 48,479 | -0% | 1 | 1 | 0% | 7,637 | 9,317 | +22% | 0 | 0 | — |
case-16 | fail→fail | 15,399 | 86,282 | +460% | 1 | 1 | 0% | 1,609 | 9,319 | +479% | 0 | 0 | — |
case-17 | fail→fail | 49,413 | 54,784 | +11% | 1 | 1 | 0% | 8,240 | 9,294 | +13% | 0 | 0 | — |
case-18 | fail→pass | 26,860 | 8,814 | -67% | 1 | 1 | 0% | 1,110 | 1,672 | +51% | 0 | 0 | — |
case-19 | fail→pass | 21,634 | 4,141 | -81% | 1 | 1 | 0% | 2,967 | 1,872 | -37% | 0 | 0 | — |
case-21 | fail→fail | 26,366 | 57,105 | +117% | 1 | 1 | 0% | 3,084 | 9,282 | +201% | 0 | 0 | — |
case-22 | fail→fail | 24,200 | 23,539 | -3% | 1 | 1 | 0% | 2,690 | 4,146 | +54% | 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 20 counted toward the lift figure. The other 2 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 +10 percentage points is the difference between those two pass rates over the 20 comparable cases. 5 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.