Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Process user-provided patent figures and generate formal drawing descriptions. Use when user says "附图处理", "figure description", "附图说明", "drawings description", or wants to describe patent figures with reference numerals.
.claude/skills/wanshuiyin-figure-description/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-09 | ✗→✓ | ▲ Improved | 4% | 0% |
| case-11 | ✗→✓ | ▲ Improved | 100% | 0% |
| case-16 | ✗→✓ | ▲ Improved | -17% | 0% |
| case-20 | ✗→✓ | ▲ Improved | 66% | 0% |
| case-21 | ✗→✓ | ▲ Improved | 137% | 0% |
Process patent figures and generate drawing descriptions based on: $ARGUMENTS
Unlike /paper-figure which generates data plots, this skill processes user-provided technical diagrams and assigns reference numerals.
FIGURE_DIR = "patent/figures/" — Output directory for figure descriptionsREFERENCE_NUMERAL_PREFIX = 100 — Starting numeral for first figure's componentsNUMERAL_SERIES = 100 — Each figure uses a separate 100-series (Fig 1: 100-199, Fig 2: 200-299, etc.)patent/INVENTION_DISCLOSURE.md — for understanding what components to identifypatent/CLAIMS.md — for mapping numerals to claim elementspatent/figures/, figures/, root directory[MISSING: description needed]For each figure found:
For each figure, assign numerals using the series convention:
| Figure | Numeral Range | |--------|-------------| | FIG. 1 | 100-199 | | FIG. 2 | 200-299 | | FIG. 3 | 300-399 |
For each identified component:
Write formal drawing descriptions (附图说明):
For CN jurisdiction (Chinese):
图1是[发明名称]的系统结构示意图;
图2是[发明名称]的方法流程图;
图3是[具体组件]的详细结构示意图;For US/EP jurisdiction (English):
FIG. 1 is a block diagram illustrating the system architecture according to one embodiment;
FIG. 2 is a flowchart illustrating the method steps according to one embodiment;
FIG. 3 is a detailed view of the processing module of FIG. 1;Create a complete mapping:
markdown## Reference Numeral Index | Numeral | Component Name | Figure(s) | Claim Element | |---------|---------------|-----------|---------------| | 100 | System | FIG. 1 | Claim X preamble | | 102 | Processor | FIG. 1 | Claim X, element 1 | | 104 | Memory | FIG. 1 | Claim X, element 2 | | 106 | Communication bus | FIG. 1 | Claim X, element 3 | | 200 | Method | FIG. 2 | Claim 1 preamble | | 202 | Receiving step | FIG. 2 | Claim 1, step 1 | | 204 | Processing step | FIG. 2 | Claim 1, step 2 |
Verify that every claim element has at least one reference numeral:
| Claim Element | Figure | Numeral | Status | |---------------|--------|---------|--------| | element] | which fig] | numeral] | Covered / MISSING] |
If any claim element has no corresponding figure or numeral, flag it:
[MISSING FIGURE: Need a diagram showing {element description}][MISSING NUMERAL: Component {name} in figure {X} needs a numeral]Write patent/figures/figure_descriptions.md:
markdown## Figure Descriptions ### FIG. 1 — [Description] [Formal one-paragraph description with all reference numerals] ### FIG. 2 — [Description] [Formal one-paragraph description with all reference numerals] ...
Write patent/figures/numeral_index.md:
markdown## Reference Numeral Index [Complete table of all numerals, components, figures, and claim mappings]
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→fail | 13,510 | 3,216 | -76% | 1 | 1 | 0% | 2,425 | 1,456 | -40% | 0 | 0 | — |
case-02 | fail→fail | 10,675 | 3,501 | -67% | 1 | 1 | 0% | 1,857 | 1,438 | -23% | 0 | 0 | — |
case-03 | fail→fail | 18,727 | 3,727 | -80% | 1 | 1 | 0% | 3,678 | 1,635 | -56% | 0 | 0 | — |
case-04 | pass→pass | 12,765 | 23,067 | +81% | 1 | 1 | 0% | 2,175 | 5,302 | +144% | 0 | 0 | — |
case-05 | pass→fail | 19,757 | 26,420 | +34% | 1 | 1 | 0% | 4,016 | 6,329 | +58% | 0 | 0 | — |
case-06 | pass→fail | 18,962 | 3,755 | -80% | 1 | 1 | 0% | 3,054 | 1,468 | -52% | 0 | 0 | — |
case-07 | pass→pass | 11,962 | 9,798 | -18% | 1 | 1 | 0% | 2,147 | 2,482 | +16% | 0 | 0 | — |
case-08 | pass→pass | 9,831 | 4,179 | -57% | 1 | 1 | 0% | 1,739 | 1,921 | +10% | 0 | 0 | — |
case-09 | fail→pass | 12,116 | 5,121 | -58% | 1 | 1 | 0% | 1,949 | 2,036 | +4% | 0 | 0 | — |
case-10 | pass→pass | 13,996 | 10,156 | -27% | 1 | 1 | 0% | 2,217 | 2,502 | +13% | 0 | 0 | — |
case-11 | fail→pass | 7,903 | 8,340 | +6% | 1 | 1 | 0% | 1,354 | 2,714 | +100% | 0 | 0 | — |
case-12 | pass→pass | 10,307 | 3,901 | -62% | 1 | 1 | 0% | 1,634 | 1,835 | +12% | 0 | 0 | — |
case-13 | fail→fail | 10,942 | 3,152 | -71% | 1 | 1 | 0% | 1,855 | 1,829 | -1% | 0 | 0 | — |
case-14 | fail→fail | 7,793 | 2,046 | -74% | 1 | 1 | 0% | 1,186 | 1,539 | +30% | 0 | 0 | — |
case-15 | pass→pass | 7,612 | 2,958 | -61% | 1 | 1 | 0% | 1,412 | 1,781 | +26% | 0 | 0 | — |
case-16 | fail→pass | 11,067 | 2,455 | -78% | 1 | 1 | 0% | 1,973 | 1,630 | -17% | 0 | 0 | — |
case-17 | pass→pass | 7,573 | 2,688 | -65% | 1 | 1 | 0% | 1,412 | 1,666 | +18% | 0 | 0 | — |
case-18 | pass→pass | 11,159 | 3,189 | -71% | 1 | 1 | 0% | 1,923 | 1,875 | -2% | 0 | 0 | — |
case-19 | pass→pass | 11,270 | 7,233 | -36% | 1 | 1 | 0% | 2,016 | 2,599 | +29% | 0 | 0 | — |
case-20 | fail→pass | 6,502 | 3,085 | -53% | 1 | 1 | 0% | 1,018 | 1,691 | +66% | 0 | 0 | — |
case-21 | fail→pass | 5,453 | 4,081 | -25% | 1 | 1 | 0% | 815 | 1,935 | +137% | 0 | 0 | — |
case-22 | fail→pass | 22,371 | 5,409 | -76% | 1 | 1 | 0% | 2,288 | 2,244 | -2% | 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 18 counted toward the lift figure. The other 4 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 +18 percentage points is the difference between those two pass rates over the 18 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.