Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Exhaustive PRISMA-style literature survey — comprehensive coverage of all related work on a specific question. Multi-stage screening, citation chaining, quality assessment, and structured data extraction. Use when the user needs to demonstrate complete literature coverage or conduct rigorous gap analysis.
.claude/skills/yogsoth-ai-systematic-survey/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-01 | ✗→✓ | ▲ Improved | -68% | 0% |
| case-02 | ✗→✓ | ▲ Improved | 18% | 0% |
| case-03 | ✗→✓ | ▲ Improved | -65% | 0% |
| case-09 | ✗→✓ | ▲ Improved | -18% | 0% |
| case-10 | ✗→✓ | ▲ Improved | 7% | 0% |
Purpose: Deep and exhaustive — exhaustive coverage of all related work on a specific question. PRISMA-style rigor.
When to use: User needs to demonstrate comprehensive literature coverage (e.g., for a survey paper's related work section, or gap analysis requiring complete picture).
| Base SOP | Target | ±10% Range | |----------|--------|------------| | web-search | 50 results | 45–55 | | web-research | 5 pages | 4–6 | | paper-overview | 60 papers | 54–66 | | paper-search | 40 papers | 36–44 | | paper-research | 30 papers | 27–33 |
Print this table before each major iteration decision:
| SOP | Target | Current | % Complete |
|----------------|--------|---------|------------|
| web-search | 50 | ??? | ???% |
| web-research | 5 | ??? | ???% |
| paper-overview | 60 | ??? | ???% |
| paper-search | 40 | ??? | ???% |
| paper-research | 30 | ??? | ???% |Do not exit the strategy until all rows reach ≥90%.
prisma-screening — multi-stage filtering (identification → screening → eligibility → inclusion)citation-chaining — forward/backward citation expansion until saturationImport (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.mdpaper-research → literature-engine/skills/literature-research/SKILL.mdSubagent (CC decides when to invoke):
define-search-protocol — formalize queries + inclusion/exclusion criteriaextract-data — structured comparison tables from deep-read papersquality-assessment — methodological rigor scoringprisma-flowchart — PRISMA-compliant flow documentationsaturation-detection — determine when to stop expandinggap-identification — find what the literature hasn't addressedsurvey-synthesis — produce final structured outputComprehensive Systematic Review containing:
<!-- BEGIN available-tables (generated) -->
Optional, no fixed order; the final leaf is always a sop.
| Tactic | When to use | | --- | --- | | citation-chaining | Forward and backward citation tracing tactic — expand paper coverage by tracing citation networks in both directions from seed/key papers. Alternates forward (who cited this) and backward (what this cited) passes until saturation. | | prisma-screening | Multi-stage PRISMA screening tactic — progressively filter papers from a large candidate pool to a focused set for deep reading. Four stages (identification, title/abstract screening, full-text screening, inclusion) with documented counts at each stage. |
Optional, no fixed order; the final leaf is always a sop.
| SOP | When to use | | --- | --- | | define-search-protocol | Formalize search queries and inclusion/exclusion criteria for systematic surveys. Produces a reproducible search protocol document. Used by systematic-survey. | | extract-data | Structured data extraction from deep-read papers — produces comparison tables (method, dataset, metrics, results, limitations). Used by systematic-survey and deep-survey. | | 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-research | Full-depth paper reading with raw text extraction. Import of literature-engine/literature-research skill. Must read fullText (true) — equations, hyperparameters, specific claims extracted. | | 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-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. | | 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. | | prisma-flowchart | Generate PRISMA-compliant flow data documenting the screening funnel — counts at each stage (identification, screening, eligibility, inclusion) with exclusion reasons. Used by systematic-survey via prisma-screening tactic. | | quality-assessment | Methodological rigor scoring for papers — evaluates bias risk, reproducibility, sample adequacy using established frameworks. Used by systematic-survey. | | 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. |
<!-- 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→pass | 50,472 | 13,372 | -74% | 1 | 1 | 0% | 8,283 | 2,640 | -68% | 0 | 0 | — |
case-02 | fail→pass | 52,283 | 49,406 | -6% | 1 | 1 | 0% | 8,280 | 9,748 | +18% | 0 | 0 | — |
case-03 | fail→pass | 54,421 | 13,745 | -75% | 1 | 1 | 0% | 8,276 | 2,902 | -65% | 0 | 0 | — |
case-04 | pass→pass | 6,479 | 13,716 | +112% | 1 | 1 | 0% | 998 | 2,723 | +173% | 0 | 0 | — |
case-05 | fail→fail | 7,274 | 45,522 | +526% | 1 | 1 | 0% | 367 | 9,694 | +2541% | 0 | 0 | — |
case-06 | pass→fail | 15,122 | 6,485 | -57% | 1 | 1 | 0% | 1,570 | 2,546 | +62% | 0 | 0 | — |
case-07 | pass→pass | 17,542 | 8,380 | -52% | 1 | 1 | 0% | 1,951 | 3,016 | +55% | 0 | 0 | — |
case-08 | pass→pass | 22,782 | 38,265 | +68% | 1 | 1 | 0% | 2,692 | 7,038 | +161% | 0 | 0 | — |
case-09 | fail→pass | 47,412 | 8,443 | -82% | 1 | 1 | 0% | 2,545 | 2,080 | -18% | 0 | 0 | — |
case-10 | fail→pass | 17,547 | 8,774 | -50% | 1 | 1 | 0% | 2,048 | 2,190 | +7% | 0 | 0 | — |
case-11 | fail→pass | 46,089 | 8,527 | -81% | 1 | 1 | 0% | 2,405 | 2,112 | -12% | 0 | 0 | — |
case-12 | fail→pass | 43,126 | 7,748 | -82% | 1 | 1 | 0% | 3,404 | 1,923 | -44% | 0 | 0 | — |
case-13 | fail→pass | 21,298 | 7,077 | -67% | 1 | 1 | 0% | 743 | 1,731 | +133% | 0 | 0 | — |
case-14 | pass→pass | 16,932 | 4,906 | -71% | 1 | 1 | 0% | 1,825 | 2,258 | +24% | 0 | 0 | — |
case-15 | pass→fail | 22,311 | 8,555 | -62% | 1 | 1 | 0% | 2,575 | 2,635 | +2% | 0 | 0 | — |
case-16 | fail→pass | 16,042 | 54,987 | +243% | 1 | 1 | 0% | 2,661 | 9,680 | +264% | 0 | 0 | — |
case-17 | fail→fail | 23,651 | 15,269 | -35% | 1 | 1 | 0% | 3,081 | 3,131 | +2% | 0 | 0 | — |
case-18 | fail→pass | 17,907 | 146,225 | +717% | 1 | 1 | 0% | 2,732 | 9,679 | +254% | 0 | 0 | — |
case-19 | fail→pass | 12,728 | 42,023 | +230% | 1 | 1 | 0% | 1,304 | 8,345 | +540% | 0 | 0 | — |
case-20 | fail→pass | 20,705 | 8,040 | -61% | 1 | 1 | 0% | 3,437 | 2,035 | -41% | 0 | 0 | — |
case-21 | fail→pass | 16,138 | 8,324 | -48% | 1 | 1 | 0% | 1,723 | 2,026 | +18% | 0 | 0 | — |
case-22 | fail→fail | 10,714 | 8,284 | -23% | 1 | 1 | 0% | 968 | 1,983 | +105% | 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 19 counted toward the lift figure. The other 3 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 +50 percentage points is the difference between those two pass rates over the 19 comparable cases. 2 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.