Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Gap Analysis Campaign — identify, classify, validate, and prioritize research gaps via systematic evidence mapping. 5 strategies (gap-identification, gap-classification, gap-validation, gap-prioritization, gap-synthesis), 3 tactics, 12 subagent SOPs.
.claude/skills/yogsoth-ai-gap-analysis/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-02 | ✗→✓ | ▲ Improved | 173% | 0% |
| case-14 | ✗→✓ | ▲ Improved | 6% | 0% |
| case-15 | ✗→✓ | ▲ Improved | -28% | 0% |
| case-19 | ✗→✓ | ▲ Improved | 48% | 0% |
| case-20 | ✗→✓ | ▲ Improved | 17% | 0% |
Identify, classify, validate, and prioritize research gaps via systematic evidence mapping.
This campaign is a strategy book — CC reads, internalizes, and autonomously constructs an approach. The SKILL.md files are textbooks, not scripts. CC decides execution order, depth, and iteration based on research context.
| Signal | Strategy | |--------|----------| | Search for gaps, identify what is missing, concept matrix, keyword extraction | → gap-identification | | Classify gap types, Miles 7-type, Müller-Bloch 6-type | → gap-classification | | Verify gap authenticity, cross-database verification, temporal sensitivity, false gaps | → gap-validation | | Rank priority, AHRQ PiCMe, feasibility, importance | → gap-prioritization | | Generate report, evidence map, research agenda, concept matrix | → gap-synthesis-strategy |
Import (5): web-search, web-research, paper-overview, paper-search, paper-research
Subagent (12): gap-keyword-extraction, concept-matrix-construction, egm-construction, gap-typology-classification, ahrq-reason-classification, cross-database-verification, false-gap-filtering, temporal-sensitivity-testing, multi-criteria-scoring, stakeholder-confirmation, evidence-grading, gap-synthesis
Shared (2): evidence-synthesis, multi-stakeholder-simulation
context-checkpoint after each strategy completes. Accumulated state persists across strategies within a campaign run.
<!-- BEGIN available-tables (generated) -->
Optional, no fixed order; the final leaf is always a sop.
| Strategy | When to use | | --- | --- | | deep-insight-gap-identification | Identify research gaps via PICOS frameworks, concept matrices, evidence gap maps, keyword extraction, citation analysis, and topic modeling. Systematic discovery of what is missing in the literature. | | deep-insight-gap-prioritization | Score and rank validated gaps on importance, feasibility, novelty, and urgency. Multi-criteria decision analysis with stakeholder confirmation. | | gap-classification | Classify identified gaps using Miles 7-type taxonomy and AHRQ 4-reason framework. Determines gap type (theoretical, methodological, empirical, etc.) and root cause of gap existence. | | gap-synthesis-strategy | Compile all gap analysis products into a coherent final report with evidence gap maps, research agenda, and concept matrices. | | gap-validation | Validate gap authenticity via cross-database verification, temporal sensitivity testing, and false-gap filtering. Ensures gaps are genuine absences, not search artifacts. |
Optional, no fixed order; the final leaf is always a sop.
| SOP | When to use | | --- | --- | | context-checkpoint | Append research process and results to the current Phase's context file. Covers both process and results with genuine substance. Use this skill at plan-designated checkpoint points — typically after each strategy completes or at key decision nodes within a research Phase. | | context-init | Create a new context file for a research Phase. Called once at Phase start to initialize the file that subsequent context-checkpoint calls will append to. Use this skill whenever a new research Phase begins and a fresh context file is needed. |
<!-- 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-10 | pass→pass | 15,986 | 17,204 | +8% | 1 | 1 | 0% | 2,504 | 3,709 | +48% | 0 | 0 | — |
case-01 | fail→fail | 19,499 | 10,339 | -47% | 1 | 1 | 0% | 3,151 | 1,271 | -60% | 0 | 0 | — |
case-02 | fail→pass | 10,872 | 23,016 | +112% | 1 | 1 | 0% | 1,694 | 4,620 | +173% | 0 | 0 | — |
case-03 | fail→fail | 37,576 | 8,417 | -78% | 1 | 1 | 0% | 6,184 | 1,367 | -78% | 0 | 0 | — |
case-04 | fail→fail | 25,372 | 61,501 | +142% | 1 | 1 | 0% | 6,214 | 1,896 | -69% | 0 | 0 | — |
case-05 | pass→pass | 35,231 | 34,770 | -1% | 1 | 1 | 0% | 6,206 | 6,987 | +13% | 0 | 0 | — |
case-06 | pass→fail | 16,189 | 38,691 | +139% | 1 | 1 | 0% | 2,486 | 6,991 | +181% | 0 | 0 | — |
case-07 | pass→pass | 19,511 | 34,821 | +78% | 1 | 1 | 0% | 3,156 | 6,993 | +122% | 0 | 0 | — |
case-08 | pass→pass | 13,620 | 22,692 | +67% | 1 | 1 | 0% | 2,206 | 4,338 | +97% | 0 | 0 | — |
case-09 | pass→fail | 18,993 | 22,369 | +18% | 1 | 1 | 0% | 3,376 | 1,760 | -48% | 0 | 0 | — |
case-11 | fail→fail | 22,856 | 25,133 | +10% | 1 | 1 | 0% | 4,678 | 5,153 | +10% | 0 | 0 | — |
case-12 | pass→pass | 11,304 | 23,515 | +108% | 1 | 1 | 0% | 2,067 | 5,029 | +143% | 0 | 0 | — |
case-13 | pass→pass | 19,393 | 33,759 | +74% | 1 | 1 | 0% | 3,317 | 6,377 | +92% | 0 | 0 | — |
case-14 | fail→pass | 7,931 | 2,732 | -66% | 1 | 1 | 0% | 1,189 | 1,255 | +6% | 0 | 0 | — |
case-15 | fail→pass | 9,954 | 2,029 | -80% | 1 | 1 | 0% | 1,526 | 1,096 | -28% | 0 | 0 | — |
case-16 | pass→pass | 14,574 | 3,947 | -73% | 1 | 1 | 0% | 2,496 | 1,522 | -39% | 0 | 0 | — |
case-17 | pass→pass | 11,002 | 3,406 | -69% | 1 | 1 | 0% | 1,905 | 1,443 | -24% | 0 | 0 | — |
case-18 | pass→pass | 13,615 | 3,869 | -72% | 1 | 1 | 0% | 2,228 | 1,511 | -32% | 0 | 0 | — |
case-19 | fail→pass | 28,594 | 4,512 | -84% | 1 | 1 | 0% | 1,078 | 1,598 | +48% | 0 | 0 | — |
case-20 | fail→pass | 8,287 | 3,791 | -54% | 1 | 1 | 0% | 1,260 | 1,469 | +17% | 0 | 0 | — |
case-21 | pass→pass | 8,146 | 2,814 | -65% | 1 | 1 | 0% | 1,375 | 1,197 | -13% | 0 | 0 | — |
case-22 | pass→pass | 10,648 | 3,912 | -63% | 1 | 1 | 0% | 1,698 | 1,504 | -11% | 0 | 0 | — |
case-23 | pass→pass | 19,325 | 28,229 | +46% | 1 | 1 | 0% | 2,939 | 3,195 | +9% | 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. 23 cases were attempted, and 19 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 +13 percentage points is the difference between those two pass rates over the 19 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.