yogsoth-ai
- 998 skills
- 0 followers
- 13 hours ago last updated
- ▌ 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
- ▌ Process Fmea · yogsoth-aiStrategy: Research execution process FMEA — analyzes how the research process itself can fail during execution, distinct from design-level failures.
- ▌
- ▌ Rapid Triage · yogsoth-ai bundleStrategy: rapid coarse screening — two filtering rounds compress a large set of gaps into a fine-rankable candidate set
- ▌ Removal Path · yogsoth-ai bundleDesign concrete removal steps for a constraint with timeline and resource needs.
- ▌ Theorist Hat · yogsoth-ai bundleTheorist perspective — assess theoretical foundations, formal rigor, and formalization opportunities.
- ▌ Time Machine · yogsoth-ai bundleTemporal projection — view a solution from future/past time horizons to generate temporally-informed insights.
- ▌ Web Research · yogsoth-aiDeep web research — fetches full page content for analysis. Snippets alone are PROHIBITED for conclusions.
- ▌ Ahp Weighting · yogsoth-ai bundleSOP: Use the AHP (Analytic Hierarchy Process) to determine scoring-dimension weights, outputting a weight vector
- ▌ Analogy Chain · yogsoth-ai bundleChain analogies to deeper levels (3-5 layers). Each layer reveals new aspects and insights not visible at the surface.
- ▌ Buffer Sizing · yogsoth-ai bundleCalculate project, feeding, and resource buffers — shared with implementation-planning
- ▌ Claim Parsing · yogsoth-ai bundlePatent claim syntax parsing — independent/dependent relationships and element extraction
- ▌ Critic Attack · yogsoth-ai bundleAttack an advocate's case with multiple arguments rated by severity.
- ▌ Debate Critic · yogsoth-ai bundleGenerates structured criticism from attack stance using Toulmin model. Produces claims, grounds, warrants, and rebuttals targeting artifact weaknesses.
- ▌ Fractionation · yogsoth-ai bundleSplit concepts into smaller units and recombine them differently to produce novel structures.
- ▌ Gap Detection · yogsoth-aiSOP for finding structural gaps in the ontology — missing concepts, thin branches, disconnected clusters.
- ▌ Gate Judgment · yogsoth-ai bundleEvaluate a candidate against gate criteria and render GO/KILL/RECYCLE verdict with evidence.
- ▌ Judge Verdict · yogsoth-ai bundleRender an impartial verdict on advocate case vs critic attacks with explicit reasoning.
- ▌ Matrix Export · yogsoth-aiSOP for exporting the dimensional matrix as a readable document or structured data.
- ▌ Meta Analysis · yogsoth-aiCross-Study Statistical Synthesis Campaign — 5 strategies for systematic collection and methodological planning of multi-study evidence synthesis. Covers pairwise, network, cumulative meta-analysis, heterogeneity investigation, and bias detection. Stops at protocol design (no computation).
- ▌ Niche Mapping · yogsoth-ai bundleMap each candidate to the niches it covers, indicating strength of coverage for each assignment.
- ▌ Normalization · yogsoth-ai bundleNormalize a score matrix using a specified method to make scores comparable across criteria.
- ▌ Pair Selector · yogsoth-ai bundleSelect the next comparison pairs that maximize information gain given current ratings and comparison history.
- ▌ Patent Mining · yogsoth-aiSystematic Patent Analysis Campaign — 5 strategies for patent landscape analysis, prior art search, white space identification, competitive intelligence, and claim analysis. Produces structured patent intelligence reports.
- ▌ Rating Update · yogsoth-ai bundleIncorporate a new judgment into the rating model and return updated ratings for all candidates.
- ▌ Reviewer2 Hat · yogsoth-ai bundleHostile reviewer perspective — find fatal flaws, logical gaps, and missing evidence in a solution.
- ▌ Steel Manning · yogsoth-aiSteel-Manning Campaign — adversarial verification of convergence decisions through resurrection advocacy, winner stress-testing, criteria interrogation, and multi-perspective attack using Devil's Advocacy, Pre-mortem, Red Teaming, Dialectical Inquiry methods.
- ▌ Wiki Add Edge · yogsoth-aiSOP wrapping vault_add_edge — create a typed relationship between two vault pages.
- ▌ Wiki Lint Fix · yogsoth-aiSOP wrapping vault_lint — run batch validation, report issues, optionally auto-fix safe problems.
- ▌ Writing Specs · yogsoth-aiGenerate a complete, executable Research Spec from North Star + user input. Strategy-level skill that orchestrates questioning, outline, and spec writing.
- ▌ Anti Benchmark · yogsoth-aiChallenge industry best practices' hidden assumptions. Deconstruct benchmarks to reveal unexamined constraints.
- ▌ Axiom Negation · yogsoth-aiIdentify and suspend fundamental assumptions via de Bono PO. Systematically negate axioms to reveal hidden solution spaces.
- ▌ Bias Detection · yogsoth-aiAssess systematic biases in the evidence body — publication bias, reporting bias, and selective outcome reporting. Budget: 40 studies, 40 effect sizes, 40 web searches.
- ▌ Claim Analysis · yogsoth-aiDeep claim scope analysis — decompose independent/dependent claims and assess protection scope breadth. Budget: 30 patent families, 30 claim parses, 20 web searches.
- ▌ Claim Negation · yogsoth-ai bundleFormally negate the core claim, producing the logical complement for reductio testing.
- ▌ Closest Worlds · yogsoth-aiStrategy: Lewis Possible Worlds — find the minimal change to reality that would flip the conclusion, measuring how close the nearest world where the conclusion fails.
- ▌ Context Review · yogsoth-aiTactic: Review a context/ directory — sort material into ARA types, locate and align the north-star, and produce a feeding plan for the compiler
- ▌ Direct Analogy · yogsoth-aiFind structurally similar systems in nature/technology/society. Map structural parallels to generate transferable solution principles.
- ▌ Domain Scoping · yogsoth-aiStrategy for defining ontology boundaries — identify seed concepts, classify topic size, establish scope constraints.
- ▌ Evidence Scout · yogsoth-ai bundleSearches for external evidence supporting or opposing specific claims. Returns structured evidence with source assessment and relevance scoring.
- ▌ Explore Resume · yogsoth-aiUnderstand the user's background comprehensively — technical stack, project experience, research experience, publications, research directions. Allows user to express interest beyond their resume. Execute once only, never re-run.
- ▌ Factor Removal · yogsoth-aiStrategy: Systematic factor removal — remove factors one at a time and observe whether the conclusion remains stable, identifying which factors are load-bearing.
- ▌ Idea Synthesis · yogsoth-ai bundleSynthesize diverse ideas into coherent solution concepts. Combines fragments from multiple ideation passes into structured, actionable ideas with clear mechanism descriptions.
- ▌ Impact Scoring · yogsoth-ai bundleSOP: assess the potential impact of a research gap, identify beneficiaries and output an impact score
- ▌ Po Provocation · yogsoth-ai bundleGenerate PO (Provocative Operation) statements per de Bono's lateral thinking. Creates deliberately illogical provocations to escape dominant thinking patterns.
- ▌ Risk Balancing · yogsoth-aiBalance portfolio risk and return using Markowitz mean-variance, CVaR, Risk parity, and Kelly criterion methods.
- ▌ Round Decision · yogsoth-ai bundleDecide whether to continue iterating or stop based on consensus score, round number, and stability.
- ▌ Scaling Design · yogsoth-ai bundleDesign scaling experiments to characterize performance-resource relationships
- ▌ Scoping Survey · yogsoth-aiBroad landscape mapping strategy — quickly understand what exists in a field. Prioritizes breadth over depth with high paper-overview volume and minimal deep reading. Use when entering a new field or needing orientation before committing to deeper investigation.
- ▌ Seed Selection · yogsoth-ai bundleValidate and prioritize starting papers for snowball surveys. Evaluates which seeds will yield the richest citation traces based on citation count, recency, and network position.
- ▌ Stepping Stone · yogsoth-ai bundleUse impractical ideas as stepping stones to reach practical solutions (de Bono Stepping Stone technique).
- ▌ Trend Analysis · yogsoth-ai bundlePatent filing volume time-series, technology lifecycle stage, and S-curve analysis
- ▌ Ablation Design · yogsoth-ai bundleDesign ablation studies to isolate component contributions in ML systems
- ▌ Actor Profiling · yogsoth-aiUnderstand who the user is — background, resources, constraints, and deep motivations. Produces an ActorProfile that informs all downstream decisions. Use this tactic at the start of any crystallization process to build a model of the user's capabilities, limitations, and intent.
- ▌ Ask Constraints · yogsoth-aiUnderstand hard boundaries on the user's research — target venues, methodology preferences, areas to avoid, advisor/team requirements. Not limited to ML/AI — works for any research domain.
- ▌ Axis Extraction · yogsoth-aiTactic for systematically extracting axes of variation from literature — identify how practitioners compare approaches.