Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Broad landscape mapping strategy — quickly understand what exists in a field. Prioritizes breadth over depth with high paper-overview volume and minimal deep reading. Use when entering a new field or needing orientation before committing to deeper investigation.
.claude/skills/yogsoth-ai-scoping-survey/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-02 | ✗→✓ | ▲ Improved | -73% | 0% |
| case-05 | ✗→✓ | ▲ Improved | 103% | 0% |
| case-06 | ✗→✓ | ▲ Improved | 4% | 0% |
| case-08 | ✗→✓ | ▲ Improved | -15% | 0% |
| case-15 | ✗→✓ | ▲ Improved | 18% | 0% |
Purpose: Broad and shallow — map the landscape of a field quickly. Understand what exists, who's working on what, and where the boundaries are.
When to use: User is entering a new field, needs orientation before committing to deeper investigation.
| Base SOP | Target | ±10% Range | |----------|--------|------------| | web-search | 100 results | 90–110 | | web-research | 10 pages | 9–11 | | paper-overview | 100 papers | 90–110 | | paper-search | 20 papers | 18–22 | | paper-research | 0 | 0 |
CC may deviate within ±10% with documented reasoning. If the field is genuinely small (fewer papers exist), document and proceed.
Print this table before each major iteration decision:
| SOP | Target | Current | % Complete |
|----------------|--------|---------|------------|
| web-search | 100 | ??? | ???% |
| web-research | 10 | ??? | ???% |
| paper-overview | 100 | ??? | ???% |
| paper-search | 20 | ??? | ???% |Do not exit the strategy until all rows reach ≥90%.
None mandatory — CC composes directly from SOPs.
Import (strict protocol execution):
web-search → web-browsing/skills/web-search/SKILL.mdweb-research → web-browsing/skills/web-research/SKILL.mdpaper-overview → literature-engine/skills/literature-overview/SKILL.mdpaper-search → literature-engine/skills/literature-search/SKILL.mdSubagent (optional, CC decides):
categorize-papers — cluster papers by theme/method/timelinetaxonomy-mapping — construct hierarchical field mapgap-identification — find what the literature hasn't addressedsurvey-synthesis — produce final structured outputField Landscape Map containing:
<!-- BEGIN available-tables (generated) -->
Optional, no fixed order; the final leaf is always a sop.
| SOP | When to use | | --- | --- | | categorize-papers | Cluster papers by theme, method, or timeline. Produces natural groupings from a paper collection. Used by scoping-survey and narrative-review. | | knowledge-acquisition-gap-identification | Identify what the literature has NOT addressed — missing methods, untested combinations, unexplored applications, contradictions without resolution. Used by all strategies. | | knowledge-acquisition-paper-overview | Abstract-level paper scanning for broad coverage. Import of literature-engine/literature-overview skill. Abstract-level only — no methodology conclusions from abstracts. | | knowledge-acquisition-paper-search | AI-summarized paper reading for intermediate depth. Import of literature-engine/literature-search skill. Must call get_paper_content for every analyzed paper. | | knowledge-acquisition-web-research | Full-page web reading for non-academic perspectives — blogs, tech reports, product pages, industry analysis. Import of web-browsing/web-research skill. Must fetch full page via apify for every analyzed page. | | knowledge-acquisition-web-search | Quick web scanning for landscape understanding. Import of web-browsing/web-search skill. Snippets only — no conclusions from snippets alone. | | survey-synthesis | Final synthesis step — weave all gathered evidence (reading notes, extracted data, categorizations) into a coherent structured output appropriate to the strategy type. Used by all 5 strategies as the final step. | | taxonomy-mapping | Construct a hierarchical field map from paper collection — multi-level taxonomy with parent/child relationships, paper counts per node, and maturity indicators. Used by scoping-survey. |
<!-- 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 | 51,456 | 15,672 | -70% | 1 | 1 | 0% | 7,066 | 2,723 | -61% | 0 | 0 | — |
case-02 | fail→pass | 51,369 | 12,655 | -75% | 1 | 1 | 0% | 8,288 | 2,246 | -73% | 0 | 0 | — |
case-03 | fail→fail | 47,957 | 13,420 | -72% | 1 | 1 | 0% | 6,788 | 1,904 | -72% | 0 | 0 | — |
case-04 | fail→fail | 47,951 | 13,575 | -72% | 1 | 1 | 0% | 7,432 | 3,376 | -55% | 0 | 0 | — |
case-05 | fail→pass | 29,100 | 47,657 | +64% | 1 | 1 | 0% | 3,972 | 8,050 | +103% | 0 | 0 | — |
case-06 | fail→pass | 75,813 | 51,926 | -32% | 1 | 1 | 0% | 8,237 | 8,555 | +4% | 0 | 0 | — |
case-07 | fail→fail | 39,224 | 12,645 | -68% | 1 | 1 | 0% | 6,075 | 3,285 | -46% | 0 | 0 | — |
case-08 | fail→pass | 16,623 | 10,906 | -34% | 1 | 1 | 0% | 2,720 | 2,319 | -15% | 0 | 0 | — |
case-09 | fail→fail | 20,676 | 45,523 | +120% | 1 | 1 | 0% | 2,668 | 9,310 | +249% | 0 | 0 | — |
case-10 | fail→fail | 26,912 | 20,224 | -25% | 1 | 1 | 0% | 3,603 | 3,660 | +2% | 0 | 0 | — |
case-11 | fail→fail | 16,730 | 53,905 | +222% | 1 | 1 | 0% | 1,660 | 9,008 | +443% | 0 | 0 | — |
case-12 | pass→fail | 52,628 | 22,989 | -56% | 1 | 1 | 0% | 8,245 | 4,005 | -51% | 0 | 0 | — |
case-13 | pass→fail | 43,391 | 47,012 | +8% | 1 | 1 | 0% | 8,250 | 9,331 | +13% | 0 | 0 | — |
case-14 | pass→pass | 51,844 | 51,761 | -0% | 1 | 1 | 0% | 8,239 | 9,320 | +13% | 0 | 0 | — |
case-15 | fail→pass | 15,729 | 10,452 | -34% | 1 | 1 | 0% | 1,795 | 2,110 | +18% | 0 | 0 | — |
case-16 | pass→pass | 21,534 | 2,907 | -87% | 1 | 1 | 0% | 2,773 | 1,591 | -43% | 0 | 0 | — |
case-17 | fail→fail | 9,542 | 54,143 | +467% | 1 | 1 | 0% | 1,568 | 9,325 | +495% | 0 | 0 | — |
case-18 | fail→pass | 25,577 | 16,320 | -36% | 1 | 1 | 0% | 3,369 | 2,759 | -18% | 0 | 0 | — |
case-19 | fail→pass | 38,002 | 26,665 | -30% | 1 | 1 | 0% | 3,266 | 4,665 | +43% | 0 | 0 | — |
case-20 | pass→pass | 23,445 | 17,554 | -25% | 1 | 1 | 0% | 2,712 | 3,018 | +11% | 0 | 0 | — |
case-21 | pass→pass | 17,116 | 8,811 | -49% | 1 | 1 | 0% | 2,737 | 1,664 | -39% | 0 | 0 | — |
case-22 | pass→fail | 18,428 | 7,014 | -62% | 1 | 1 | 0% | 2,199 | 1,400 | -36% | 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. The headline lift of +18 percentage points is the difference between those two pass rates over the 22 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.