Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Search the web for current information using the web_search tool
.claude/skills/dicklesworthstone-minimax-web-search/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-09 | ✗→✓ | ▲ Improved | 76% | 0% |
| case-11 | ✗→✓ | ▲ Improved | -7% | 0% |
| case-12 | ✗→✓ | ▲ Improved | -61% | 0% |
| case-13 | ✗→✓ | ▲ Improved | -55% | 0% |
| case-19 | ✗→✓ | ▲ Improved | -29% | 0% |
Use this skill when you need to find current, real-time, or authoritative information that may have changed since my knowledge cutoff.
Call the web_search tool directly with a query:
web_search({ query: "your search query" })Use web_search when:
Do NOT use web_search when:
read toolweb_search({
query: "your search query here"
})Endpoint: POST {api_host}/v1/coding_plan/search
Request Body:
json{ "q": "your search query" }
Response Format:
json{ "organic": [ { "title": "Result Title", "link": "https://example.com", "snippet": "Brief description...", "date": "2025-01-15" } ], "related_searches": [ {"query": "related query 1"}, {"query": "related query 2"} ], "base_resp": { "status_code": 0, "status_msg": "success" } }
Results include:
You can use the suggestions to refine your search or ask the user which direction they'd like to explore.
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→fail | 17,745 | 5,002 | -72% | 1 | 1 | 0% | 3,054 | 1,011 | -67% | 0 | 0 | — |
case-02 | fail→fail | 6,955 | 5,553 | -20% | 1 | 1 | 0% | 387 | 1,047 | +171% | 0 | 0 | — |
case-03 | fail→fail | 5,338 | 4,321 | -19% | 1 | 1 | 0% | 271 | 951 | +251% | 0 | 0 | — |
case-04 | pass→pass | 10,409 | 10,584 | +2% | 1 | 1 | 0% | 2,001 | 2,672 | +34% | 0 | 0 | — |
case-05 | pass→pass | 2,601 | 2,868 | +10% | 1 | 1 | 0% | 410 | 1,187 | +190% | 0 | 0 | — |
case-06 | pass→pass | 12,499 | 14,941 | +20% | 1 | 1 | 0% | 2,203 | 3,207 | +46% | 0 | 0 | — |
case-07 | fail→fail | 2,185 | 2,266 | +4% | 1 | 1 | 0% | 308 | 1,162 | +277% | 0 | 0 | — |
case-08 | fail→fail | 5,683 | 4,449 | -22% | 1 | 1 | 0% | 887 | 1,430 | +61% | 0 | 0 | — |
case-09 | fail→pass | 4,161 | 2,373 | -43% | 1 | 1 | 0% | 679 | 1,196 | +76% | 0 | 0 | — |
case-10 | fail→fail | 4,745 | 5,012 | +6% | 1 | 1 | 0% | 230 | 974 | +323% | 0 | 0 | — |
case-11 | fail→pass | 7,165 | 2,133 | -70% | 1 | 1 | 0% | 1,134 | 1,050 | -7% | 0 | 0 | — |
case-12 | fail→pass | 17,688 | 2,512 | -86% | 1 | 1 | 0% | 3,147 | 1,221 | -61% | 0 | 0 | — |
case-13 | fail→pass | 14,206 | 2,208 | -84% | 1 | 1 | 0% | 2,456 | 1,104 | -55% | 0 | 0 | — |
case-14 | pass→pass | 10,404 | 2,807 | -73% | 1 | 1 | 0% | 1,781 | 1,234 | -31% | 0 | 0 | — |
case-15 | pass→pass | 19,865 | 2,090 | -89% | 1 | 1 | 0% | 3,391 | 1,022 | -70% | 0 | 0 | — |
case-16 | pass→fail | 4,346 | 6,942 | +60% | 1 | 1 | 0% | 603 | 1,222 | +103% | 0 | 0 | — |
case-17 | pass→pass | 2,413 | 2,526 | +5% | 1 | 1 | 0% | 346 | 1,231 | +256% | 0 | 0 | — |
case-18 | pass→pass | 6,708 | 2,439 | -64% | 1 | 1 | 0% | 1,210 | 1,093 | -10% | 0 | 0 | — |
case-19 | fail→pass | 8,827 | 2,128 | -76% | 1 | 1 | 0% | 1,505 | 1,076 | -29% | 0 | 0 | — |
case-20 | pass→fail | 6,404 | 8,381 | +31% | 1 | 1 | 0% | 939 | 1,280 | +36% | 0 | 0 | — |
case-21 | fail→fail | 7,501 | 3,823 | -49% | 1 | 1 | 0% | 448 | 898 | +100% | 0 | 0 | — |
case-22 | pass→pass | 5,769 | 2,730 | -53% | 1 | 1 | 0% | 821 | 1,147 | +40% | 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 15 counted toward the lift figure. The other 7 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 15 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.