yogsoth-ai
- 998 skills
- 0 followers
- 17 hours ago last updated
- ▌ Creative Ideation Failure Mode Cataloging · yogsoth-ai bundleSystematically catalog all failure modes in a domain or method, producing a classified failure taxonomy.
- ▌ Experiment Execution Saturation Detection · yogsoth-ai bundleShared SOP: detect information saturation — know when to stop searching/analyzing
- ▌ Hypothesis Formation Saturation Detection · yogsoth-ai bundleShared SOP: judge whether the current activity has reached information saturation
- ▌ Knowledge Acquisition Benchmark Inventory · yogsoth-ai bundleIdentify and catalog all relevant benchmarks in target domain
- ▌ Knowledge Acquisition Claim Decomposition · yogsoth-aiIndependent/dependent claim parsing, element extraction, and feature mapping to technical domains
- ▌ Knowledge Structuring Claim Decomposition · yogsoth-aiTactic for decomposing compound claims into atomic propositions — identify logical structure, separate conjunctions, extract implicit assumptions.
- ▌ Knowledge Structuring Combination Mapping · yogsoth-aiStrategy for enumerating meaningful combinations across dimensions and marking existing work.
- ▌ Knowledge Acquisition Saturation Detection · yogsoth-ai bundleDetermine 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 Structuring Consistency Checking · yogsoth-aiTactic for verifying ontology consistency — detect contradictions, cycles, orphans, and type violations.
- ▌ Stress Test Validity Envelope Construction · yogsoth-ai bundleSynthesize breakpoints across dimensions into a coherent validity envelope for a claim.
- ▌ Hypothesis Formation Portfolio Optimization · yogsoth-ai bundleStrategy: Treat the gap set as an investment portfolio — use risk/return/diversity optimization to select the optimal gap portfolio
- ▌ North Star Crystallization Broad Web Search · yogsoth-aiQuick web scanning for field landscape understanding. Strict import of web-browsing/web-search skill. Hard constraint: brave_web_search count=10 per call, at least 150 total search results before completing.
- ▌ Hypothesis Formation Variable Identification · yogsoth-ai bundleSOP: identify variables and their roles within a hypothesis
- ▌ Creative Ideation Consistency Pair Evaluation · yogsoth-ai bundleEvaluate pairwise value consistency (logical/empirical/normative)
- ▌ Knowledge Structuring Variable Identification · yogsoth-aiIdentify key variables in the causal system
- ▌ North Star Crystallization Broad Paper Search · yogsoth-aiPaper landscape scan within selected field(s). Strict import of literature-engine/literature-overview skill. Hard constraint: at least 80 papers scanned.
- ▌ Experiment Execution Bottleneck Identification · yogsoth-ai bundleWhere is the system bottleneck? — TOC 5 Focusing Steps + Current Reality Tree to find the binding constraint
- ▌ Experiment Execution Consistency Pair Evaluation · yogsoth-ai bundlePairwise consistency assessment using Cross-Consistency Assessment (CCA) matrix
- ▌ Hypothesis Formation Scoring Matrix Construction · yogsoth-ai bundleTactic: orchestrate multi-dimensional scoring SOPs to build a comprehensive assessment matrix for all gaps
- ▌
- ▌ Benchmark Audit · yogsoth-aiSystematic quality assessment using BetterBench 46-criterion framework — 5 benchmarks, 30 papers, 40 web searches
- ▌ Benchmark Sweep · yogsoth-aiSystematically scan all known solutions, identify gaps in coverage and unexplored regions of the solution space.
- ▌ Causal Modeling · yogsoth-aiCampaign for building causal models — identify variables, map mechanisms, collect evidence, analyze interventions, validate models. Produces causal graphs in the wiki vault.
- ▌ Cycle Detection · yogsoth-ai bundleScan a pairwise comparison matrix for preference cycles and compute transitivity metrics.
- ▌ Debate Defender · yogsoth-ai bundleResponds to attacks with counter-evidence and counter-arguments. Defends artifact using evidence, clarification, and rebuttal while acknowledging valid criticisms.
- ▌ Deductive Chain · yogsoth-ai bundleDerive logical consequences step by step from a given premise, building a traceable derivation chain.
- ▌ Deep Web Search · yogsoth-ai bundleFull-page web reading for non-academic perspectives — blogs, tech reports, product pages, industry analysis. Spawns a subagent to read pages in isolated context. Hard constraint: at least 30 web pages read in full.
- ▌ Devils Advocacy · yogsoth-ai bundleConstruct the strongest possible counter-argument against a position, steelmanning the opposition before attacking.
- ▌ Domain Scanning · yogsoth-ai bundleScan distant domains for transferable principles. Uses web-search and paper-overview to identify analogous solutions in unrelated fields.
- ▌ Dominance Check · yogsoth-ai bundleIdentify dominated and non-dominated alternatives in a score matrix using Pareto dominance.
- ▌ Executing Specs · yogsoth-aiExecute a Research Spec step by step, respecting context protocol, deviation limits, and backtrack rules. Supports multi-session recovery.
- ▌ Fantasy Analogy · yogsoth-aiWish-fulfillment thinking — ignore physical laws for ideal solution. Use unconstrained imagination to reveal what the problem truly needs.
- ▌ Ontology Export · yogsoth-aiSOP for exporting ontology summary — generate a readable overview of the current ontology state.
- ▌
- ▌ Plan Formatting · yogsoth-ai bundleFormat task plan as bite-sized executable tasks following superpowers:writing-plans conventions
- ▌ Present And Ask · yogsoth-aiPresent the field panorama to the user and gather their preferences — which fields interest them, which they reject, and why. A dialogue SOP that bridges landscape-synthesis output to user decision.
- ▌ Probe Execution · yogsoth-ai bundleExecute a single attack probe against an artifact, record the result with evidence and severity classification.
- ▌ Quality Scoring · yogsoth-ai bundleMulti-dimensional patent quality assessment — forward citations, family size, claim count, geographic breadth
- ▌ Radar Synthesis · yogsoth-ai bundleSynthesize multiple dimension scores into radar chart data and compute overall readiness.
- ▌ Rank Comparison · yogsoth-ai bundleCompare multiple ranking results to assess agreement and identify divergent items.
- ▌ Relation Typing · yogsoth-aiStrategy for identifying and typing relationships between concepts — create edges with appropriate types and weights.
- ▌ Result Analysis · yogsoth-ai bundleStatistically analyze collected results, verify reproducibility, and synthesize findings
- ▌ Society Of Mind · yogsoth-aiStrategy: Multi-agent collaborative debate based on Du et al. Society of Mind. Agents share perspectives iteratively until convergence or divergence is detected.
- ▌ Stress Scenario · yogsoth-ai bundleWhat is the worst case? — Extreme condition construction and failure mode enumeration for risk preparedness
- ▌ Thematic Coding · yogsoth-ai bundleIdentify recurring themes across papers using qualitative coding methodology. Produces a codebook with theme definitions, supporting evidence, and frequency counts. Used by narrative-review.
- ▌ Threshold Sweep · yogsoth-ai bundleCompute consensus status at multiple threshold levels to produce a threshold-consensus curve.
- ▌ Validate Leaves · yogsoth-ai bundleQuality check on leaf nodes of the GoalTree. Verify each leaf is specific enough, actionable, and that the set of leaves fully covers the top goal. Flag issues for further decomposition.
- ▌ Wiki Edge Audit · yogsoth-aiSOP for auditing wikilink coverage — scans all edges and reports which source pages are missing [[dir/slug]] wikilinks to their targets.
- ▌ Activity Listing · yogsoth-ai bundleEnumerate all implementation activities from an experiment design
- ▌ Alias Resolution · yogsoth-aiSOP for detecting and resolving concept aliases — merge duplicate pages, redirect edges.
- ▌ And Or Decompose · yogsoth-ai bundleKAOS-style recursive goal decomposition. AND decomposition for sub-goals that must ALL be satisfied. OR decomposition for alternative paths where any one suffices. Produces a GoalTree (DAG structure).
- ▌ Ara From Context · yogsoth-aiCampaign: Compile a context/ research record into an ARA (Agent-Native Research Artifact) and run a Level-2 epistemic review — no LaTeX, no narrative paper
- ▌ Ara Rigor Review · yogsoth-aiSOP: Run the external ARA rigor-reviewer (Seal Level 2, six-dimension semantic review) over ../ara/ and pass its level2_report.json to the user
- ▌ Argument Mapping · yogsoth-aiCampaign for mapping argument structures — extract claims, link evidence, assess strength, synthesize positions. Produces argument graphs in the wiki vault.
- ▌
- ▌ Boundary Probing · yogsoth-aiMap parameter space, generate extreme values, test at boundaries, detect breakpoints, synthesize validity envelope.
- ▌ Category Sorting · yogsoth-aiClassify candidates into predefined categories using ELECTRE-Tri, FlowSort, AHPSort, or DRSA methods.
- ▌ Claim Extraction · yogsoth-aiStrategy for extracting claims from source material — identify propositions, decompose compound claims, classify claim types, create claim pages in the vault.
- ▌ Claim Refinement · yogsoth-ai bundlePropose a refined claim that survives counterexamples while preserving maximum explanatory power (Lakatos lemma-incorporation).
- ▌ Cluster Analysis · yogsoth-ai bundleIdentify natural opinion clusters from collected judgments and characterize each cluster.
- ▌ Concept Blending · yogsoth-aiFauconnier-Turner 4-space model: Generic + Input1 + Input2 → Blended Space
- ▌ Coverage Mapping · yogsoth-aiMap evaluation coverage, identify untested capability dimensions — 20 benchmarks, 30 papers, 50 web searches
- ▌ Coverage Scoring · yogsoth-ai bundleCompute coverage completeness, redundancy, and gap severity scores from a coverage map.
- ▌ Debate Architect · yogsoth-ai bundleDesigns debate structure based on artifact type — selects attack vectors, assigns perspectives, determines escalation ladder, and configures round parameters.
- ▌
- ▌ Dynamic Tracking · yogsoth-aiStrategy for continuous rating updates using Elo, Glicko-2, TrueSkill 2, and Whole-History Rating for live ranking systems and A/B testing.
- ▌ Escape Technique · yogsoth-ai bundleIdentify dominant thinking pattern and escape it via deliberate pattern-breaking.
- ▌ Evidence Linking · yogsoth-aiSOP for linking evidence pages to causal claims — creates supported_by or contradicts edges.
- ▌ Excursion Method · yogsoth-aiFull 8-stage Gordon-Prince excursion process. Deliberate departure from the problem into unrelated domains, then force-fit discoveries back.
- ▌ Failure Taxonomy · yogsoth-aiCatalog all failure modes in a domain, classify them systematically, and generate targeted solutions for each failure type.
- ▌ Final Validation · yogsoth-aiSelf-review the North Star + ResearchBrief for completeness, consistency, and clarity before presenting to user. If issues found, return to specific tactic/SOP for targeted fix. If passes, present final output to user for confirmation.
- ▌ Landscape Survey · yogsoth-aiPatent landscape full-scan — maps technology domain via assignee ranking, IPC/CPC classification, filing trends. Budget: 200 patent families, 0 claim parses, 80 web searches.
- ▌ Lateral Thinking · yogsoth-aiLateral Thinking Campaign — escape logical thinking tracks via PO/movement, random entry, concept fan, challenge, and six hats (de Bono)
- ▌
- ▌ Method Discovery · yogsoth-ai bundleIdentify all relevant methods via literature, leaderboards, citation chains
- ▌ Method Inventory · yogsoth-aiComprehensively identify all relevant methods for a task — 50 methods, 60 web searches budget
- ▌
- ▌ Narrative Review · yogsoth-aiTheory-driven literature review for building arguments and frameworks. Flexible, subjective, and narrative-focused — selects evidence strategically to support a thesis. High web-research budget for blogs, opinion pieces, and industry perspectives. Use when the user is writing a position paper, survey introduction, or constructing a coherent narrative around a research theme.
- ▌ Niche Definition · yogsoth-ai bundleDefine niches and capability areas that a portfolio should cover based on domain structure and objectives.
- ▌ North Star Align · yogsoth-aiSOP: Deep-read the original north-star context, distill this ARA's overall direction, and align it with the user via the reused present-and-ask / present-candidates dialogue SOPs
- ▌ Optimization Run · yogsoth-ai bundleExecute multi-objective optimization on candidates to produce a Pareto front of non-dominated solutions.
- ▌ Pairwise Ranking · yogsoth-aiPairwise Ranking Campaign — produce global rankings through pairwise comparisons and voting aggregation using Bradley-Terry, Elo, TrueSkill, Condorcet, Borda, Schulze methods.
- ▌ Patent Synthesis · yogsoth-ai bundleProduce final structured patent intelligence report from all analysis results
- ▌ Personal Analogy · yogsoth-aiEmpathic identification — become the system/component. First-person embodiment to discover hidden constraints and opportunities.
- ▌ Pico Application · yogsoth-ai bundleSOP: apply the PICO/PICOTS framework to structure a research question
- ▌ Pico Formulation · yogsoth-ai bundleConstruct PICO/PECO framework for the meta-analysis research question
- ▌ Practitioner Hat · yogsoth-ai bundleEngineer perspective — assess buildability, cost, timeline, and integration challenges.
- ▌ Prior Art Search · yogsoth-aiEvaluate novelty of specific invention — find relevant prior art across patents, publications, and products. Budget: 80 patent families, 20 claim parses, 50 web searches.
- ▌ Prisma Flowchart · yogsoth-ai bundleGenerate 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.
- ▌ Prisma Screening · yogsoth-aiMulti-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.
- ▌ Research Catalog · yogsoth-ai bundleCapability menu for the research engine. Lists the 10 freely-composable research packages, what each does, when to reach for it, and a pointer to its full skill table. Read this after north-star crystallization to decide which packages to use — no fixed order. Also serves as the skill-index (capability map).
- ▌ Scope Assessment · yogsoth-ai bundleSOP: Assess whether a research question has appropriate scope (too broad / appropriate / too narrow)
- ▌ Score Extraction · yogsoth-ai bundleExtract (Task, Dataset, Metric, Score, Conditions) tuples from a paper
- ▌ Severity Scoring · yogsoth-ai bundleRate failure mode severity 1-10 based on end-effect impact. Follows AIAG-VDA severity scale calibrated for research artifacts.
- ▌ Source Gathering · yogsoth-ai bundleSOP for gathering source material relevant to the ontology domain — fetch papers and web pages into source pages.
- ▌ Spec Self Review · yogsoth-aiQuality gate for Research Specs. Checks for placeholders, consistency, scope, ambiguity, context protocol, and quantification. Mandatory before user review.
- ▌ Strength Scoring · yogsoth-aiSOP for assigning calibrated strength scores to claims — evaluate evidence weight, count independent sources, check defeaters, produce scored assessment.
- ▌ Survey Synthesis · yogsoth-ai bundleFinal 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.
- ▌ Symbolic Analogy · yogsoth-aiCompress core contradiction into poetic imagery/oxymoron. Use compressed conflicts to reveal hidden solution directions.
- ▌ Synthesis Report · yogsoth-aiSOP for producing argument synthesis reports — aggregate evidence, resolve contradictions, identify surviving claims, write structured summary.