yogsoth-ai
- 1.8k skills
- 0 followers
- 512 repo stars
- yesterday last updated
- ▌ Snowball 3 · 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.
- ▌ Deep Survey 3 · 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.
- ▌ Extract Data 3 · yogsoth-ai bundleStructured data extraction from deep-read papers — produces comparison tables (method, dataset, metrics, results, limitations). Used by systematic-survey and deep-survey.
- ▌ Scoping Survey 3 · 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 3 · 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.
- ▌ Thematic Coding 3 · 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.
- ▌ Narrative Review 3 · 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.
- ▌ Prisma Flowchart 3 · 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.
- ▌ Wiki Add Edge 3 · yogsoth-aiSOP wrapping vault_add_edge — create a typed relationship between two vault pages.
- ▌ Wiki Compile Page 3 · yogsoth-aiSOP for wiki page creation/update — create or update a synthesized wiki page with edges and index update.
- ▌ Web Research 4 · yogsoth-aiDeep web research — fetches full page content for analysis. Snippets alone are PROHIBITED for conclusions.
- ▌ Knowledge Acquisition Web Search · yogsoth-aiQuick web scanning for landscape understanding. Import of web-browsing/web-search skill. Snippets only — no conclusions from snippets alone.
- ▌ Knowledge Acquisition Paper Overview · yogsoth-aiAbstract-level paper scanning for broad coverage. Import of literature-engine/literature-overview skill. Abstract-level only — no methodology conclusions from abstracts.
- ▌
- ▌ Context Init 2 · 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.
- ▌ Context Checkpoint 2 · yogsoth-aiAppend research process and results to the current Phase's context file. Each append MUST contain >=500 lines of markdown covering both process and results. Use this skill at plan-designated checkpoint points — typically after each strategy completes or at key decision nodes within a research Phase.
- ▌ Web Search 3 · yogsoth-aiQuick web scanning — discover pages, get snippets, find URLs. For orientation only, not substantive analysis.
- ▌ Literature Search 2 · yogsoth-aiMedium-depth literature search — read AI-summarized reports for every paper analyzed
- ▌ Literature Overview 2 · yogsoth-aiQuick landscape scan — discover papers on a topic without full-text reading
- ▌ Literature Research 2 · yogsoth-aiDeep literature research — raw full text reading and targeted PDF queries for rigorous analysis
- ▌ Insight 2 · 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.
- ▌ Gap Analysis 2 · 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.
- ▌ Boundary Analysis 2 · yogsoth-aiBoundary Analysis Campaign — probe where methods fail, map validity envelopes, test robustness, catalog failure modes, detect scaling limits. 5 strategies, 3 tactics, 11 subagent SOPs.
- ▌ Mechanism Gap Hunting 2 · 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).
- ▌ Problem Reformulation 2 · 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.
- ▌ Deep Insight Sensitivity Analysis 2 · yogsoth-aiSensitivity Analysis Campaign — identify which assumptions are most critical by measuring their impact on conclusions. 5 strategies (parameter-screening, variance-decomposition, assumption-criticality, uncertainty-propagation, decision-sensitivity), 3 tactics, 11 subagent SOPs.
- ▌ Gap Identification 2 · yogsoth-ai bundleIdentify what the literature has NOT addressed — missing methods, untested combinations, unexplored applications, contradictions without resolution. Used by all strategies.
- ▌ Intervention Page Creation 2 · yogsoth-aiSOP for documenting an intervention — what happens when a causal variable is manipulated.
- ▌ Gap Detection 2 · yogsoth-aiSOP for finding structural gaps in the ontology — missing concepts, thin branches, disconnected clusters.
- ▌ Matrix Export 2 · yogsoth-aiSOP for exporting the dimensional matrix as a readable document or structured data.
- ▌ Wiki Add Edge 2 · yogsoth-aiSOP wrapping vault_add_edge — create a typed relationship between two vault pages.
- ▌ Domain Scoping 2 · yogsoth-aiStrategy for defining ontology boundaries — identify seed concepts, classify topic size, establish scope constraints.
- ▌ Axis Extraction 2 · yogsoth-aiTactic for systematically extracting axes of variation from literature — identify how practitioners compare approaches.
- ▌ Axis Validation 2 · yogsoth-aiSOP for validating that candidate axes are independent and meaningful.
- ▌ Causal Modeling 2 · yogsoth-aiCampaign for building causal models — identify variables, map mechanisms, collect evidence, analyze interventions, validate models. Produces causal graphs in the wiki vault.
- ▌ Novelty Scoring 2 · yogsoth-aiSOP for scoring empty cells by novelty potential — how surprising and valuable would this combination be?
- ▌ Ontology Export 2 · yogsoth-aiSOP for exporting ontology summary — generate a readable overview of the current ontology state.
- ▌ Relation Typing 2 · yogsoth-aiStrategy for identifying and typing relationships between concepts — create edges with appropriate types and weights.
- ▌ Wiki Edge Audit 2 · yogsoth-aiSOP for auditing wikilink coverage — scans all edges and reports which source pages are missing [[dir/slug]] wikilinks to their targets.
- ▌ Alias Resolution 2 · yogsoth-aiSOP for detecting and resolving concept aliases — merge duplicate pages, redirect edges.
- ▌ Argument Mapping 2 · yogsoth-aiCampaign for mapping argument structures — extract claims, link evidence, assess strength, synthesize positions. Produces argument graphs in the wiki vault.
- ▌ Claim Extraction 2 · yogsoth-aiStrategy for extracting claims from source material — identify propositions, decompose compound claims, classify claim types, create claim pages in the vault.
- ▌ Evidence Linking 2 · yogsoth-aiSOP for linking evidence pages to causal claims — creates supported_by or contradicts edges.
- ▌
- ▌
- ▌ Source Gathering 2 · yogsoth-aiSOP for gathering source material relevant to the ontology domain — fetch papers and web pages into source pages.
- ▌ Strength Scoring 2 · yogsoth-aiSOP for assigning calibrated strength scores to claims — evaluate evidence weight, count independent sources, check defeaters, produce scored assessment.
- ▌ Synthesis Report 2 · yogsoth-aiSOP for producing argument synthesis reports — aggregate evidence, resolve contradictions, identify surviving claims, write structured summary.
- ▌ Confidence Update 2 · yogsoth-aiSOP for updating confidence scores on claims and evidence pages based on new information.
- ▌ Evidence Weighing 2 · yogsoth-aiTactic for assessing the strength and relevance of evidence for causal claims — distinguishes correlation from causation.
- ▌ Matrix Generation 2 · yogsoth-aiTactic for generating and populating combination matrices — cross dimensions to enumerate the design space.
- ▌
- ▌ Ontology Building 2 · yogsoth-aiCampaign for building domain ontologies — systematic concept extraction, relation typing, taxonomy construction, and iterative refinement. Produces a structured concept hierarchy in the wiki vault.
- ▌ Validation Report 2 · yogsoth-aiSOP for generating a causal model validation report — summarize coverage, confidence, gaps, contradictions.
- ▌ Wiki Compile Page 2 · yogsoth-aiSOP for wiki page creation/update — create or update a synthesized wiki page with edges and index update.
- ▌ Argument Synthesis 2 · yogsoth-aiStrategy for synthesizing argument positions — aggregate evidence, resolve contradictions, produce synthesis reports identifying which claims survive scrutiny.
- ▌ Causal Chain Query 2 · yogsoth-aiSOP for tracing causal chains — follow edges from cause to effect through intermediate variables.
- ▌ Concept Extraction 2 · yogsoth-aiStrategy for mining concepts from sources — systematic extraction, page creation, alias resolution.
- ▌ Confidence Scoring 2 · yogsoth-aiSOP for assigning calibrated confidence scores to causal claims based on evidence quality and quantity.
- ▌ Loop Documentation 2 · yogsoth-aiSOP for documenting a feedback loop — classify, describe dynamics, identify break points.
- ▌ Claim Decomposition 2 · yogsoth-aiTactic for decomposing compound claims into atomic propositions — identify logical structure, separate conjunctions, extract implicit assumptions.
- ▌ Claim Page Creation 2 · yogsoth-aiSOP for creating a claim page in the vault — atomic proposition with type classification, source attribution, and initial confidence.
- ▌ Combination Mapping 2 · yogsoth-aiStrategy for enumerating meaningful combinations across dimensions and marking existing work.
- ▌ Dimension Discovery 2 · yogsoth-aiStrategy for identifying fundamental dimensions of variation in a design space.
- ▌ Edge Batch Creation 2 · yogsoth-aiSOP for creating multiple edges in a batch — efficient bulk relationship creation.
- ▌ Evidence Attachment 2 · yogsoth-aiSOP for attaching evidence to a claim — create typed edge (supported_by, contradicts, qualifies) with evidence quality metadata.
- ▌
- ▌ Model Gap Detection 2 · yogsoth-aiSOP for finding gaps in the causal model — missing variables, unexplained effects, weak links.
- ▌ Ontology Refinement 2 · yogsoth-aiStrategy for iterative ontology improvement — merge duplicates, fill gaps, update confidence, prune dead branches.
- ▌ Question Generation 2 · yogsoth-aiSOP for generating research questions from promising gaps in the design space.
- ▌ Seed Concept Search 2 · yogsoth-aiSOP for finding seed concepts in existing vault and web sources to anchor ontology construction.
- ▌ Strength Assessment 2 · yogsoth-aiTactic for assessing argument strength — evaluate evidence quality, count independent sources, check for defeaters, assign calibrated confidence scores.
- ▌ Taxonomy Validation 2 · yogsoth-aiStrategy for validating ontology consistency — check hierarchy, detect cycles, verify completeness.
- ▌ Consistency Checking 2 · yogsoth-aiTactic for verifying ontology consistency — detect contradictions, cycles, orphans, and type violations.
- ▌ Dimensional Analysis 2 · yogsoth-aiCampaign for mapping design spaces — discover dimensions/axes, enumerate combinations, identify gaps and novel opportunities. Produces dimensional maps in the wiki vault.
- ▌ Evidence Linking Arg 2 · yogsoth-aiStrategy for linking evidence to claims — find supporting/contradicting evidence, create typed edges, assess evidence quality, identify gaps in evidential coverage.
- ▌ Concept Decomposition 2 · yogsoth-aiTactic for breaking compound concepts into atomic parts — split over-broad concepts, identify sub-components, create child pages.
- ▌ Concept Page Creation 2 · yogsoth-aiSOP for creating a new concept page with proper frontmatter, content, and initial edges.
- ▌
- ▌ Argument Visualization 2 · yogsoth-aiSOP for generating argument structure visualization — query graph for argument chains, format as mermaid diagram or indented tree, write to vault.
- ▌ Contradiction Flagging 2 · yogsoth-aiSOP for flagging contradictions in the causal model — identify conflicting evidence or mechanism claims.
- ▌ Hierarchy Construction 2 · yogsoth-aiTactic for building is-a and part-of hierarchies — establish parent-child relationships, verify transitivity, detect cycles.
- ▌ Rebuttal Documentation 2 · yogsoth-aiSOP for documenting rebuttals and counter-claims — create rebuttal pages with typed contradiction edges and source attribution.
- ▌ Variable Page Creation 2 · yogsoth-aiSOP for creating a variable page in the causal model — documents a measurable quantity with its properties.
- ▌ Combination Enumeration 2 · yogsoth-aiSOP for systematically enumerating combinations across dimensions.
- ▌ Dimension Page Creation 2 · yogsoth-aiSOP for creating a dimension page — documents an axis of variation with its values and semantics.
- ▌ Feedback Loop Detection 2 · yogsoth-aiTactic for identifying circular causation — detect feedback loops, classify as reinforcing or balancing, document loop structure.
- ▌ Hierarchy Visualization 2 · yogsoth-aiSOP for inspecting the current hierarchy structure — query graph to display parent-child relationships.
- ▌ Mechanism Edge Creation 2 · yogsoth-aiSOP for creating a causal mechanism edge — documents how one variable causes changes in another.
- ▌ Counterfactual Reasoning 2 · yogsoth-aiTactic for reasoning about what would happen if variables were different — supports causal identification and intervention analysis.
- ▌ Snowball 2 · 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.
- ▌ Deep Survey 2 · 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.
- ▌ Extract Data 2 · yogsoth-ai bundleStructured data extraction from deep-read papers — produces comparison tables (method, dataset, metrics, results, limitations). Used by systematic-survey and deep-survey.
- ▌ Claim Parsing 2 · yogsoth-ai bundlePatent claim syntax parsing — independent/dependent relationships and element extraction
- ▌ Meta Analysis 2 · 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).
- ▌ Patent Mining 2 · 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.
- ▌
- ▌
- ▌ Scoping Survey 2 · 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 2 · 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.