Agent Skills by yogsoth-ai
There are 53 agent skills in our directory.
yogsoth-ai publishes 53 AI agent skills in our directory. Browse them below — each links back to its source repository.
Updated June 2026
- abp-vulnerability-classificationClassify assumptions on 2 axes — load-bearing (how much conclusion depends
- ahrq-reason-classificationClassify gap root causes using AHRQ 4-reason framework (insufficient
- assumption-cascade-tracerBuild assumption dependency graphs and trace cascade failures when root
- boundary-condition-specificationSOP: Specify the boundary conditions under which a hypothesis holds
- catwoe-analysisApply Checkland's CATWOE analysis from a specific stakeholder perspective
- claim-extractionStrategy for extracting claims from source material — identify propositions,
- combinatorial-synthesisSynthesize all combinatorial creativity outputs
- compute-normalizationNormalize results by compute budget (Pareto analysis)
- constraint-driven-ideationInject extreme constraints to force innovation — impossibility breeds
- constraint-responseGenerate creative solutions under extreme constraints — no "impossible
- construct-validity-assessmentEvaluate whether benchmark measures its claimed capability
- convergence-assessmentCompare results across multiple model variants — quantitative agreement
- convergence-paper-searchPaper AI summary reading — deeper understanding of specific methodology
- coverage-analysisSystematic coverage evaluation pipeline — benchmark inventory, method-problem
- critical-path-identificationIdentify which input uncertainties contribute most to output uncertainty
- critical-path-planningIdentify the shortest execution path via CPM forward/backward pass, resource
- crystallize-north-starFuse the GoalTree root node and user motivation into a single crystallized
- debate-defenderResponds to attacks with counter-evidence and counter-arguments. Defends
- deep-insight-provocation-generationGenerate de Bono lateral thinking provocations to challenge dominant
- deep-insight-web-researchDeep web research with full page fetching via Apify. Import of web-browsing/web-research
- destruction-synthesisSynthesize all assumption destruction outputs into structured destructive
- evaluation-filteringMulti-dimensional evaluation and tiered filtering of generated ideas.
- evaporating-cloudModel conflicts as Goldratt's Evaporating Cloud — expose hidden assumptions
- evidence-network-constructionBuild evidence network graph for network meta-analysis — nodes, edges,
- excursion-departureLeave the problem entirely and explore an unrelated domain. Produces
- execution-monitoringMonitor execution progress, detect anomalies, and report status
- experiment-execution-web-searchImport SOP: quick web scan discovery (from web-browsing skill)
- final-validationSelf-review the North Star + ResearchBrief for completeness, consistency,
- fragility-measurementCompute a fragility index from flip-point distances and degradation scores,
- gap-detectionSOP for finding structural gaps in the ontology — missing concepts, thin
- gap-synthesisCompile all gap analysis intermediate products into a coherent final
- hypothesis-formation-paper-researchImport SOP: Deep literature research, raw full text + PDF Q&A (from
- hypothesis-formation-web-searchImport SOP: quick web scan, discover URLs and snippets (from web-browsing)
- interaction-detectionDetect and characterize significant parameter interactions from Sobol
- jtbd-mappingMap stakeholder Jobs-to-be-Done — functional, emotional, and social jobs
- key-assumptions-checkMilitary ACT: systematically enumerate all assumptions, classify by
- leaderboard-dynamics-analysisAnalyze leaderboard score distributions, compression, selective reporting
- merge-candidatesSOP for identifying near-duplicate concepts that should be merged.
- multi-model-convergenceWimsatt-style multi-method cross-validation — enumerate assumptions,
- patent-family-tracingForward/backward patent citation and priority tracing until saturation
- portfolio-evaluation-per-scenarioEvaluate a specific portfolio's performance metrics and vulnerabilities
- premortem-to-fmea-pipelineTactic: Pre-mortem rapid screening feeds high-risk items into full FMEA
- random-entryRandom word/concept as thinking entry point (de Bono Random Entry)
- random-paper-entrySelect random paper facet as creative stimulus. Uses genuine randomness
- reformulation-synthesisCompile all problem reformulation analyses into a coherent report with
- reproducibility-protocolEnsure experiment reproducibility through systematic environment and
- result-collectionCollect experiment outputs — metrics, logs, artifacts — into structured
- robustness-designDesign experiments to identify failure boundaries and robustness limits
- spice-applicationSOP: Apply the SPICE framework to structure an evaluation research question
- springboard-launchConvert analogy insights into concrete feasible solutions. Transform
- stakeholder-confirmationSimulate stakeholder perspectives to validate gap priorities. Assesses
- symbolic-analogyCompress core contradiction into poetic imagery/oxymoron. Use compressed
- taxonomy-validationStrategy for validating ontology consistency — check hierarchy, detect