yogsoth-ai
- 1.8k skills
- 0 followers
- 512 repo stars
- yesterday last updated
- ▌ Pareto Visualization · yogsoth-ai bundleCreate visual representation of the Pareto frontier showing trade-offs between objectives with narrative explanation.
- ▌ Persona Construction · yogsoth-ai bundleBuild a detailed adversarial persona with background, motivation, expertise, blind spots, and preferred attack patterns.
- ▌ Plausibility Ranking · yogsoth-ai bundleSOP: rank candidate explanations by plausibility using multi-dimensional weighted scoring
- ▌ Random Word Stimulus · yogsoth-ai bundleUse random word/concept injection as creative stimulus. Selects random concepts and forces connection to the problem space, generating unexpected solution paths.
- ▌
- ▌ Separation Principle · yogsoth-ai bundleApply time/space/condition/scale separation to resolve physical contradictions where the same parameter must satisfy opposing requirements.
- ▌ Structural Synthesis · yogsoth-ai bundleSynthesize all structural transformation outputs into a coherent, ranked idea report with lineage tracking.
- ▌ Symbolic Compression · yogsoth-ai bundleCompress problem contradiction into 2-3 word oxymoron. Produces oxymorons with interpretation directions for each.
- ▌ White Space Analysis · yogsoth-aiIdentify patent coverage gaps — feature cross-matrix blank areas revealing unprotected technology combinations. Budget: 150 patent families, 10 claim parses, 60 web searches.
- ▌ Abstraction To Design · yogsoth-ai bundleAbstract biological principle to design principle. Bridge from biology to engineering.
- ▌ Advocate Construction · yogsoth-ai bundleConstruct the strongest possible case for a rejected candidate or counter-position.
- ▌ Ahrq Picme Assessment · yogsoth-ai bundleSOP: Use the AHRQ PiCMe framework to systematically assess a research gap across 6 dimensions
- ▌ Assumption Constraint · yogsoth-ai bundleWhich assumptions are most fragile? — Vulnerability ranking + impact assessment of experiment assumptions
- ▌ Assumption Excavation · yogsoth-aiSystematic extraction, challenge, and sensitivity analysis of assumptions underlying a decision to identify load-bearing beliefs.
- ▌ Benchmark Archaeology · yogsoth-aiEvaluation Methodology Archaeology Campaign — 5 strategies for systematic analysis of AI/ML benchmarks, metrics, and leaderboards. Reveals construct validity issues, saturation, data contamination, and evaluation protocol inconsistencies.
- ▌ Best Option Selection · yogsoth-aiSelect the single best candidate from a set using WSM, TOPSIS, AHP, MAUT, or VIKOR methods.
- ▌ Challenge Questioning · yogsoth-ai bundleNon-threatening 'Why?' questioning of current practices to reveal historical accidents vs. genuine constraints.
- ▌ Competitor Simulation · yogsoth-ai bundleCompetitor perspective — design strategies to defeat this solution, then use attack vectors to improve it.
- ▌
- ▌ Concept Decomposition · yogsoth-aiTactic for breaking compound concepts into atomic parts — split over-broad concepts, identify sub-components, create child pages.
- ▌ Concept Fan Expansion · yogsoth-ai bundleExpand concept fan from purpose through concepts to directions to ideas (de Bono Concept Fan).
- ▌ Concept Page Creation · yogsoth-aiSOP for creating a new concept page with proper frontmatter, content, and initial edges.
- ▌ Consensus Measurement · yogsoth-ai bundleCompute consensus score from collected judgments using the appropriate statistical method.
- ▌ Critic Defender Judge · yogsoth-aiStrategy: Classic triangular debate — Critic attacks, Defender responds, Judge adjudicates. Based on Irving AI Safety via Debate with Toulmin argumentation structure.
- ▌ Dependency Constraint · yogsoth-ai bundleWhat must be completed first? — Dependency chain analysis + prerequisite graph construction
- ▌
- ▌ Destruction Synthesis · yogsoth-ai bundleSynthesize all assumption destruction outputs into structured destructive innovation report.
- ▌ Efficient Exploration · yogsoth-aiStrategy for large-N sparse pairwise comparison using TrueSkill, active learning, and rank centrality to rank 100+ candidates from limited comparisons.
- ▌ Enumeration Synthesis · yogsoth-ai bundleSynthesize all systematic enumeration outputs into a structured idea report with prioritized recommendations.
- ▌ Factor Identification · yogsoth-ai bundleIdentify independent, dependent, and control variables for an experiment
- ▌ Failure Chain Tracing · yogsoth-aiTactic: Trace upstream causes and downstream effects of each failure mode. Builds multi-level cause-mode-effect chains for systemic understanding.
- ▌ Feasibility Synthesis · yogsoth-ai bundleSynthesize all assessments into a feasibility matrix, recommendation, and risk summary.
- ▌ Feedback Distribution · yogsoth-ai bundleCreate anonymized feedback report summarizing group judgment distribution for a given round.
- ▌ Fragility Measurement · yogsoth-ai bundleCompute a fragility index from flip-point distances and degradation scores, summarizing how robust the conclusion is.
- ▌ Gap Driven Generation · yogsoth-aiGenerate solutions targeting specific coverage gaps — detect gaps, generate failure-driven solutions, and design factor-level experiments.
- ▌ Gap Pairwise Judgment · yogsoth-ai bundleSOP: Make a criterion-by-criterion relative priority judgment between two gaps and output the preference result
- ▌ Groupthink Mitigation · yogsoth-aiStrategy: 10th Man Rule and Liberating Structures — institutionalized dissent to prevent premature consensus and expose suppressed objections.
- ▌
- ▌ Key Assumptions Check · yogsoth-ai bundleMilitary ACT: systematically enumerate all assumptions, classify by type, and evaluate evidence strength supporting each.
- ▌ Knowledge Acquisition · yogsoth-aiResearch Knowledge Acquisition Engine with 5 campaigns (literature-survey, patent-mining, benchmark-archaeology, meta-analysis, baseline-establishment). Use this skill whenever a user needs to systematically acquire research knowledge — academic literature, patent landscapes, benchmark evaluations, cross-study statistical synthesis, or SOTA performance baselines. Pre-condition: north-star-crystallization must be complete.
- ▌ Knowledge Compilation · yogsoth-aiTactic for compiling research findings into vault pages — orchestrates page creation, updates, edge linking, and index maintenance. Minimum yield ≥3 page operations per invocation.
- ▌ Mechanism Gap Hunting · yogsoth-aiMechanism-Gap Hunting Campaign — hunt the specific link where scientific progress is BLOCKED, not where literature is empty. Use this instead of gap-analysis whenever the goal is truth-seeking / AI4S research rather than finding a publishable white-space — i.e. when the user asks "where is progress actually stuck", "what mechanism is blocking this", or wants a complete blocker set rather than a ranked gap list. 4 stages over reused deep-insight SOPs, with injected per-stage directives. Exhaustive (no prioritization/ranking).
- ▌ Method Problem Matrix · yogsoth-aiCross method×problem matrix, find unexplored intersections where known methods have not been applied to known problems.
- ▌ Minimal Change Search · yogsoth-aiTactic: Generate candidate changes, detect flip-points where conclusion reverses, measure fragility as distance to nearest flip.
- ▌ Mitigation Design Sop · yogsoth-ai bundleDesign prevention, detection, and response measures for high-priority failure modes. Produces actionable countermeasure specifications.
- ▌ Mitigation Validation · yogsoth-aiTactic: Run mini-FMEA on proposed mitigations to verify they do not introduce new failure modes. Prevents mitigation-induced risks.
- ▌ Necessity Sufficiency · yogsoth-aiStrategy: Probability of Necessity and Sufficiency (PNS/PS) — systematically evaluate whether each factor is necessary, sufficient, both, or neither for the conclusion.
- ▌ Parameter Enumeration · yogsoth-ai bundleEnumerate possible values for each uncertainty driver using MECE principles
- ▌ Patent Categorization · yogsoth-ai bundleClassify patents by tech subdomain, application scenario, and value chain position
- ▌ Patent Family Tracing · yogsoth-aiForward/backward patent citation and priority tracing until saturation
- ▌ Perspective Synthesis · yogsoth-ai bundleSynthesize all perspective outputs into a structured multi-perspective idea report.
- ▌ Prerequisite Planning · yogsoth-ai bundleIdentify obstacles blocking direct achievement and design intermediate objectives to overcome each
- ▌ Problem Biologization · yogsoth-ai bundleRestate technical problem as biological question. Translate engineering challenges into nature's language.
- ▌ Problem Reformulation · yogsoth-aiProblem Reformulation Campaign — question the problem itself. Escape dominant ideas, reframe from multiple perspectives, apply dialectical inquiry, assess wickedness, discover appreciative alternatives. 5 strategies, 3 tactics, 10 subagent SOPs.
- ▌ Prospective Hindsight · yogsoth-aiStrategy: Klein pre-mortem — assume the artifact has failed, then retrospect plausible causes. Generates rapid failure scenario catalog.
- ▌ Random Stimulus Entry · yogsoth-aiRandom word/paper/concept as thinking entry point. Use genuine randomness to escape fixation and open unexpected solution paths.
- ▌ Red Team Truthseeking · yogsoth-aiStrategy: Systematic adversarial probing retuned for truth-seeking. Threat surface = the set of load-bearing claims. Output is NOT a resilience score and NOT a hardening list — it is, per claim, the specific observation/computation that would refute it, plus which attacks succeeded. Methods: UFMCS Key Assumptions Check (repurposed), CIA Devil's Advocacy, Platt strong inference.
- ▌ Resurrection Advocacy · yogsoth-aiArgue for rejected candidates using Devil's Advocacy, Dialectical Inquiry, and Adversarial Collaboration to ensure elimination was justified.
- ▌ Reverse Brainstorming · yogsoth-aiHow to make it worse? → reverse for solutions. Generate anti-solutions then invert to discover novel approaches.
- ▌ Scenario Construction · yogsoth-ai bundleConstruct distinct future scenarios spanning key uncertainties for portfolio stress testing.
- ▌ Single Factor Removal · yogsoth-ai bundleRemove one specified factor from the artifact's support structure and reason about how the conclusion changes.
- ▌ Theory Identification · yogsoth-ai bundleSOP: Identify theoretical frameworks relevant to a research gap
- ▌ Threshold Calibration · yogsoth-aiSystematically sweep consensus thresholds to observe which items achieve consensus at what level, producing a threshold-consensus curve.
- ▌
- ▌ Winner Stress Testing · yogsoth-aiStress-test the winning candidate using Pre-mortem, Red Teaming, and Failure Mode Analysis to expose hidden weaknesses before commitment.
- ▌ Repo Dependency Graph · yogsoth-ai bundleReconstruct a DARE skill repo's true use-dependency relations and render them as a self-contained, offline, Obsidian-style interactive HTML graph (pyvis / vis-network). Use this whenever the user wants to graph / map / visualize the skill dependencies of a repo or package, "画依赖图 / graph 化这个 repo / 把 skill 连边画出来 / 用 pyvis 出个图 / skill 关系图", or to audit how campaign→strategy→ tactic→sop skills connect. Trigger even if the user just says "给这个 package 做个图" without naming pyvis or HTML. Goes straight to HTML — never write an intermediate mermaid markdown first.
- ▌ Abstraction Extraction · yogsoth-ai bundleExtract abstract principles from concrete domain cases. Strips domain-specific details to reveal transferable mechanisms.
- ▌ Action Priority Matrix · yogsoth-ai bundleCompute Risk Priority Number (RPN = S x O x D), classify failure modes into H/M/L action priority per AIAG-VDA tables.
- ▌ Adversarial Escalation · yogsoth-aiStrategy: Progressive pressure escalation — starts with surface-level challenges and escalates to fundamental assumption attacks based on defender confidence decay.
- ▌ Argument Visualization · yogsoth-aiSOP for generating argument structure visualization — query graph for argument chains, format as mermaid diagram or indented tree, write to vault.
- ▌ Assignee Normalization · yogsoth-ai bundleStandardize assignee names and identify corporate group affiliations across patent offices
- ▌ Assumption Challenging · yogsoth-ai bundleChallenge each assumption's validity — shared cross-repo SOP
- ▌ Assumption Destruction · yogsoth-aiAssumption Destruction Campaign — open new solution spaces by negating, reversing, and challenging fundamental assumptions.
- ▌ Baseline Establishment · yogsoth-aiSOTA Performance Baseline Campaign — 5 strategies for systematically collecting, standardizing, and analyzing performance data across methods. Produces standardized comparison tables, progress curves, and headroom analysis.
- ▌ Biologize And Discover · yogsoth-aiBiomimicry Design Spiral: Define→Biologize→Discover→Abstract→Emulate. Translate technical challenges into biological questions and find nature's solutions.
- ▌ Checkpoint And Recover · yogsoth-aiCheckpoint state before risky operations, detect anomalies, and recover gracefully
- ▌ Insight · yogsoth-aiInsight Campaign — deep root-cause analysis of why research gaps persist. 5 strategies (root-cause-drilling, stakeholder-mapping, tension-mining, question-reformulation, assumption-audit), 4 tactics, 13 subagent SOPs.
- ▌ Snowball · yogsoth-aiCitation-chain-driven literature survey starting from seed papers. Traces research lineage in both forward (who cited this) and backward (what this cited) directions until saturation. High deep-read ratio (67%). Use when the user already has key papers and wants to find everything connected to them — ancestors, descendants, and branch points.
- ▌ Force Fit · yogsoth-ai bundleForce-fit excursion discoveries back to the original problem. Deliberately create connections between unrelated findings and the challenge.
- ▌ Hot Start · yogsoth-aiMinimal crystallization strategy for users who already have a specific research topic or problem (e.g., "I want to improve CoT faithfulness in LLMs") and need structuring into a formal North Star. Heavily simplifies or skips exploration tactics, focusing on obstacle analysis, goal decomposition, and synthesis. Use when the user's first message reveals a specific, actionable research direction.
- ▌ Synectics · yogsoth-aiSynectics Campaign — systematic use of analogy and metaphor for breakthrough associations via Gordon's 4 analogy types and excursion method.
- ▌ Biomimicry · yogsoth-aiBiomimicry Campaign — discover transferable solutions from biological systems via Design Spiral, BioTRIZ, functional analogy, ecosystem patterns, and evolution strategies.
- ▌ Cold Start · yogsoth-aiFull crystallization strategy for users who have no research direction at all. Covers actor profiling, landscape reconnaissance, direction narrowing, obstacle analysis, goal decomposition, and north-star synthesis. Use when the user's first message reveals zero specificity about what they want to research.
- ▌ Re Scoring · yogsoth-ai bundleRe-evaluate S/O/D scores after mitigation measures are in place. Validates that mitigations actually reduce risk as expected.
- ▌ Warm Start · yogsoth-aiSimplified crystallization strategy for users who have a general research direction (e.g., "I'm interested in LLM reasoning") but lack specificity. Simplifies actor profiling and landscape reconnaissance, then proceeds through direction narrowing, obstacle analysis, goal decomposition, and north-star synthesis. Use when the user's first message reveals a general area but not a specific problem.
- ▌ Web Search · yogsoth-aiQuick web scanning — discover pages, get snippets, find URLs. For orientation only, not substantive analysis.
- ▌ Ara Compile · yogsoth-aiSOP: Turn the feeding plan into the compiler's $ARGUMENTS and run the external ARA compiler once inline to produce ../ara/
- ▌ Concept Fan · yogsoth-aiExpand from purpose to concepts to directions to ideas (de Bono Concept Fan)
- ▌ Deep Survey · yogsoth-aiPrecise, targeted investigation of a specific sub-problem — few papers, all read in full depth. High paper-research ratio (50% deep-read rate). Use when the user knows exactly what they need to understand and requires detailed technical analysis with equations, hyperparameters, and specific claims extracted.
- ▌ Design Fmea · yogsoth-aiStrategy: Research design-level FMEA — function analysis, failure mode identification, severity/occurrence/detection scoring per AIAG-VDA 2019.
- ▌ Red Teaming · yogsoth-aiCampaign: Systematic adversarial attack from military/intelligence/AI-safety traditions. Core question: Can systematic adversarial attacks find fatal flaws? Methods: UFMCS Red Team Handbook v9.0, CIA SAT, Anthropic Red Teaming, NIST AI RMF, Inie et al. 12-strategy taxonomy.
- ▌ Spawn Agent · yogsoth-aiSpawn a customized CC subagent with full MCP tool access. Used by SOPs that declare execution: subagent.
- ▌ Wiki Search · yogsoth-aiSOP wrapping vault_search — BM25 full-text search across vault pages. Returns ranked results with snippets.
- ▌ Context Init · yogsoth-aiCreate 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.
- ▌ Debate Judge · yogsoth-ai bundleEvaluates debate exchanges, adjudicates argument quality, and produces round verdicts with confidence scores and reasoning.
- ▌ Extract Data · yogsoth-ai bundleStructured data extraction from deep-read papers — produces comparison tables (method, dataset, metrics, results, limitations). Used by systematic-survey and deep-survey.
- ▌ Fantasy Wish · yogsoth-ai bundleUnconstrained wish-fulfillment ideation. Ignore all physical laws to imagine the ideal solution, then identify realization directions.
- ▌ Full Ranking · yogsoth-aiProduce a complete ordering of all candidates using PROMETHEE I/II, ELECTRE III, or MAVT methods.
- ▌ Gap Analysis · yogsoth-aiGap 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.
- ▌ Plan Writing · yogsoth-ai bundleFormat critical path and prerequisites into bite-sized executable plan following superpowers:writing-plans conventions