Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Systematic Enumeration Campaign — exhaustive coverage analysis to discover overlooked solution spaces via benchmark sweep, method-problem matrix, ablation, and failure taxonomy
.claude/skills/yogsoth-ai-systematic-enumeration/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-15 | ✗→✓ | ▲ Improved | 5% | 0% |
| case-03 | ✗→✓ | ▲ Improved | 18% | 0% |
| case-05 | ✗→✓ | ▲ Improved | -20% | 0% |
| case-06 | ✗→✓ | ▲ Improved | 2% | 0% |
| case-21 | ✗→✓ | ▲ Improved | 132% | 0% |
Exhaustive coverage analysis to discover overlooked solution spaces via benchmark sweep, method-problem matrix, ablation, and failure taxonomy.
| Strategy | Signal Keywords | |----------|----------------| | benchmark-sweep | benchmark, state-of-the-art, survey, catalog, inventory, known solutions | | method-problem-matrix | matrix, crossing, intersection, method×problem, unexplored combinations | | ablation-brainstorm | ablation, remove, component, dependency, what-if-removed | | failure-taxonomy | failure, fault, error, breakdown, failure mode, robustness | | factorial-ideation | factor, level, DOE, design of experiments, combination, factorial |
| Strategy | Description | |----------|-------------| | benchmark-sweep | Systematically scan all known solutions, identify gaps | | method-problem-matrix | Cross method×problem matrix, find unexplored intersections | | ablation-brainstorm | Remove components one by one, observe system changes | | failure-taxonomy | Catalog all failure modes, generate targeted solutions | | factorial-ideation | DOE thinking: identify factors, define levels, explore combinations |
| Tactic | Description | |--------|-------------| | evaluation-filtering | Multi-dimensional evaluation and tiered filtering (shared) | | coverage-analysis | Benchmark inventory → method-problem crossing → intersection evaluation | | gap-driven-generation | Coverage gap detection → failure-driven generation → factor-level design |
| SOP | Description | |-----|-------------| | benchmark-inventory | Catalog all known solutions/methods in domain | | method-problem-crossing | Build method×problem cross-reference matrix | | intersection-evaluation | Evaluate exploration status of each matrix cell | | ablation-execution | Remove components one by one, record responses | | dependency-identification | Identify critical dependencies from ablation results | | failure-mode-cataloging | Systematically catalog failure modes | | failure-driven-generation | Generate solutions targeting each failure mode | | factor-level-design | Identify factors and levels, design experiment matrix | | coverage-gap-detection | Detect uncovered regions in solution space | | enumeration-synthesis | Synthesize all systematic enumeration outputs |
| Strategy | web-search | web-research | paper-overview | paper-search | paper-research | |----------|-----------|-------------|---------------|-------------|---------------| | benchmark-sweep | 30 | 10 | 30 | 20 | 8 | | method-problem-matrix | 25 | 8 | 25 | 15 | 5 | | ablation-brainstorm | 20 | 5 | 20 | 12 | 5 | | failure-taxonomy | 25 | 10 | 25 | 15 | 5 | | factorial-ideation | 20 | 8 | 20 | 12 | 5 |
| Tool | Server | Purpose | |------|--------|---------| | brave_web_search | brave-search | General web search for methods and examples | | brave_llm_context | brave-search | Deep content extraction from web pages | | apify/rag-web-browser | apify | Full page scraping for detailed content | | get_paper_content | alphaxiv | Read academic paper content | | discover_papers | alphaxiv | Find relevant research papers | | relevanceSearch | semantic-scholar | Search academic literature | | paper | semantic-scholar | Get paper details | | citations | semantic-scholar | Trace citation networks |
| Tactic | Role | |--------|------| | evaluation-filtering | Multi-dimensional evaluation and tiered filtering (shared) | | coverage-analysis | Benchmark inventory → crossing → intersection evaluation | | gap-driven-generation | Gap detection → failure-driven generation → factor-level design |
| SOP | Role | |-----|------| | benchmark-inventory | Catalog all known solutions in domain | | method-problem-crossing | Build method×problem cross-reference matrix | | intersection-evaluation | Evaluate exploration status of matrix cells | | ablation-execution | Component removal and response recording | | dependency-identification | Critical dependency extraction | | failure-mode-cataloging | Systematic failure mode classification | | failure-driven-generation | Targeted solution generation per failure mode | | factor-level-design | Factor/level identification and experiment matrix | | coverage-gap-detection | Uncovered region detection and prioritization | | enumeration-synthesis | Final synthesis of all enumeration outputs |
<!-- BEGIN available-tables (generated) -->
Optional, no fixed order; the final leaf is always a sop.
| Strategy | When to use | | --- | --- | | ablation-brainstorm | Remove components one by one, observe system changes to reveal hidden dependencies and generate ideas from structural gaps. | | benchmark-sweep | Systematically scan all known solutions, identify gaps in coverage and unexplored regions of the solution space. | | factorial-ideation | DOE thinking: identify factors, define levels, and explore combinations to systematically cover the design space. | | failure-taxonomy | Catalog all failure modes in a domain, classify them systematically, and generate targeted solutions for each failure type. | | method-problem-matrix | Cross method×problem matrix, find unexplored intersections where known methods have not been applied to known problems. |
Optional, no fixed order; the final leaf is always a sop.
| Tactic | When to use | | --- | --- | | coverage-analysis | Systematic coverage evaluation pipeline — benchmark inventory, method-problem crossing, and intersection evaluation to map explored vs unexplored solution space. | | creative-ideation-combination-mapping | Systematically enumerate parameter dimensions and generate viable combinations. Orchestrates parameter extraction → value enumeration → compatibility assessment → synthesis. | | evaluation-filtering | Multi-dimensional evaluation and tiered filtering of generated ideas. Orchestrates novelty assessment → feasibility check → ranking → selection. | | gap-driven-generation | Generate solutions targeting specific coverage gaps — detect gaps, generate failure-driven solutions, and design factor-level experiments. |
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. | | creative-ideation-novelty-scoring | Score ideas on novelty dimensions — structural distance from known solutions, conceptual surprise, domain-crossing depth. Produces ranked novelty assessment. | | creative-ideation-saturation-detection | Determine when additional ideation yields diminishing returns. Analyzes latest idea batch against existing corpus to judge continue/near-saturation/saturated. | | enumeration-synthesis | Synthesize all systematic enumeration outputs into a structured idea report with prioritized recommendations. | | idea-synthesis | Synthesize diverse ideas into coherent solution concepts. Combines fragments from multiple ideation passes into structured, actionable ideas with clear mechanism descriptions. | | parameter-identification | Identify the key parameters/dimensions of a problem space. Produces a structured parameter list with value ranges for morphological analysis. |
<!-- 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-15 | fail→pass | 13,842 | 7,622 | -45% | 1 | 1 | 0% | 2,082 | 2,191 | +5% | 0 | 0 | — |
case-01 | fail→fail | 61,341 | 21,605 | -65% | 1 | 1 | 0% | 8,258 | 2,675 | -68% | 0 | 0 | — |
case-02 | fail→fail | 58,040 | 23,973 | -59% | 1 | 1 | 0% | 5,168 | 4,707 | -9% | 0 | 0 | — |
case-03 | fail→pass | 39,170 | 50,324 | +28% | 1 | 1 | 0% | 6,646 | 7,841 | +18% | 0 | 0 | — |
case-04 | pass→pass | 49,685 | 47,793 | -4% | 1 | 1 | 0% | 7,573 | 7,926 | +5% | 0 | 0 | — |
case-05 | fail→pass | 21,094 | 8,734 | -59% | 1 | 1 | 0% | 3,157 | 2,513 | -20% | 0 | 0 | — |
case-06 | fail→pass | 21,236 | 6,290 | -70% | 1 | 1 | 0% | 2,549 | 2,588 | +2% | 0 | 0 | — |
case-07 | pass→fail | 15,215 | 7,990 | -47% | 1 | 1 | 0% | 1,567 | 2,187 | +40% | 0 | 0 | — |
case-08 | fail→fail | 18,502 | 16,271 | -12% | 1 | 1 | 0% | 2,021 | 3,604 | +78% | 0 | 0 | — |
case-09 | pass→pass | 17,390 | 10,661 | -39% | 1 | 1 | 0% | 1,889 | 2,623 | +39% | 0 | 0 | — |
case-10 | pass→pass | 19,941 | 10,895 | -45% | 1 | 1 | 0% | 1,907 | 2,724 | +43% | 0 | 0 | — |
case-11 | pass→pass | 17,487 | 9,539 | -45% | 1 | 1 | 0% | 1,971 | 2,407 | +22% | 0 | 0 | — |
case-12 | pass→pass | 14,344 | 13,561 | -5% | 1 | 1 | 0% | 1,755 | 2,804 | +60% | 0 | 0 | — |
case-13 | fail→fail | 12,179 | 2,522 | -79% | 1 | 1 | 0% | 1,045 | 2,218 | +112% | 0 | 0 | — |
case-14 | fail→fail | 15,367 | 7,850 | -49% | 1 | 1 | 0% | 1,867 | 2,145 | +15% | 0 | 0 | — |
case-16 | pass→fail | 24,504 | 3,097 | -87% | 1 | 1 | 0% | 2,947 | 2,253 | -24% | 0 | 0 | — |
case-17 | pass→fail | 13,523 | 7,539 | -44% | 1 | 1 | 0% | 2,131 | 2,198 | +3% | 0 | 0 | — |
case-18 | pass→fail | 20,483 | 3,852 | -81% | 1 | 1 | 0% | 2,415 | 2,364 | -2% | 0 | 0 | — |
case-19 | pass→fail | 15,551 | 8,982 | -42% | 1 | 1 | 0% | 2,346 | 2,375 | +1% | 0 | 0 | — |
case-20 | pass→fail | 5,053 | 21,603 | +328% | 1 | 1 | 0% | 886 | 5,101 | +476% | 0 | 0 | — |
case-21 | fail→pass | 13,536 | 19,246 | +42% | 1 | 1 | 0% | 1,884 | 4,375 | +132% | 0 | 0 | — |
case-22 | pass→pass | 14,527 | 24,398 | +68% | 1 | 1 | 0% | 2,069 | 5,784 | +180% | 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 21 counted toward the lift figure. The other 1 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 -9 percentage points is the difference between those two pass rates over the 21 comparable cases. 6 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.