yogsoth-ai

Append 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.

Create 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.

The optimizer brain for the ladder-foundry pretraining loop. Runs the two-level nested batch loop, delegates gating to gate_eval, attributes a failing batch to one weight (attribute-first), and recovers from disk after compaction. Control flow is fully scripted; only the backprop attribution is a judgment call.

Loss-2 judge (codex role). Over one topic's 6 shuffled research-design samples, pairwise-rank by quality using the D1–D5 standard. Emit the pairwise log; the harness computes the order and the ladder verdicts. Judge quality difference, never against academic standards.

Loss-1 judge (codex role). Given one sample's de-identified dialogue and its PolicyCard, decide axis-by-axis whether the user-simulator enacted the card's per-axis pressure. Judge enactment of the card, never whether the research is good.

Closing skill for the research-executor, loaded as the last step of formated-specs. Summarize the design just produced into one research-result JSON fenced block in your reply. Do not execute the research.

Spec-slot skill for the research-executor. Emit the 4-layer DARE orchestration of the assigned topic as one research-graph JSON fenced block in your reply. Replaces the generic spec-writing step.

Use the DARE research engine to crystallize research goals, write executable research specs, and execute staged research workflows.

Perform bisociation at multiple abstraction levels

Complete blend with background knowledge

Compose new connections in blended space

Construct complete 4-space blends with emergent structure. Orchestrates input-space-construction → generic-space-extraction → blend-composition.

Run blend as mental simulation

Combinatorial Creativity Campaign — produce emergent concepts via concept blending, multi-level bisociation, and function combination (Fauconnier-Turner)

Synthesize all combinatorial creativity outputs

Fauconnier-Turner 4-space model: Generic + Input1 + Input2 → Blended Space

SOTA Performance Baseline Campaign — 5 strategies for systematically collecting, standardizing, and analyzing performance data across methods. Produces standardized comparison tables, progress curves, and headroom analysis.

Assess systematic biases in the evidence body — publication bias, reporting bias, and selective outcome reporting. Budget: 40 studies, 40 effect sizes, 40 web searches.

Track evidence accumulation over time — cumulative meta-analysis protocol design. Budget: 40 studies, 40 effect sizes, 30 web searches.

Design structured data extraction form for systematic meta-analysis data collection

Systematically extract effect sizes and conditions from papers for meta-analytic synthesis

Determine effect size types and calculation methods for meta-analytic synthesis

Build evidence network graph for network meta-analysis — nodes, edges, geometry assessment

Plan the statistical synthesis approach — model selection, heterogeneity strategy, and reporting

SOP for detecting and resolving concept aliases — merge duplicate pages, redirect edges.

SOP for creating a claim page in the vault — atomic proposition with type classification, source attribution, and initial confidence.

SOP for creating a new concept page with proper frontmatter, content, and initial edges.

SOP for flagging contradictions in the causal model — identify conflicting evidence or mechanism claims.

SOP for creating a dimension page — documents an axis of variation with its values and semantics.

SOP for creating multiple edges in a batch — efficient bulk relationship creation.

SOP for attaching evidence to a claim — create typed edge (supported_by, contradicts, qualifies) with evidence quality metadata.

SOP for linking evidence pages to causal claims — creates supported_by or contradicts edges.

Identify what the literature has NOT addressed — missing methods, untested combinations, unexplored applications, contradictions without resolution. Used by all strategies.

Identify recurring themes across papers using qualitative coding methodology. Produces a codebook with theme definitions, supporting evidence, and frequency counts. Used by narrative-review.

Generate 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.

Construct a hierarchical field map from paper collection — multi-level taxonomy with parent/child relationships, paper counts per node, and maturity indicators. Used by scoping-survey.

Determine 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.

Validate and prioritize starting papers for snowball surveys. Evaluates which seeds will yield the richest citation traces based on citation count, recency, and network position.

Structured data extraction from deep-read papers — produces comparison tables (method, dataset, metrics, results, limitations). Used by systematic-survey and deep-survey.

Methodological rigor scoring for papers — evaluates bias risk, reproducibility, sample adequacy using established frameworks. Used by systematic-survey.

SOP wrapping vault_add_edge — create a typed relationship between two vault pages.

SOP for wiki page creation/update — create or update a synthesized wiki page with edges and index update.

SOP wrapping vault_query_graph — traverse knowledge graph from a node to explore its neighborhood and context.

SOP for source page creation — write immutable source page capturing raw material, then update search index.

SOP wrapping vault_lint — run batch validation, report issues, optionally auto-fix safe problems.

SOP wrapping vault_search — BM25 full-text search across vault pages. Returns ranked results with snippets.

Tactic for compiling research findings into vault pages — orchestrates page creation, updates, edge linking, and index maintenance. Minimum yield ≥3 page operations per invocation.

Tactic for vault health upkeep — lint, orphan resolution, merge candidates, confidence updates. Minimum yield ≥1 issue resolved per invocation.

Quick landscape scan — discover papers on a topic without full-text reading

Deep literature research — raw full text reading and targeted PDF queries for rigorous analysis

Medium-depth literature search — read AI-summarized reports for every paper analyzed

Append 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.

Create 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.

Deep web research — fetches full page content for analysis. Snippets alone are PROHIBITED for conclusions.

Quick web scanning — discover pages, get snippets, find URLs. For orientation only, not substantive analysis.

Spawn a customized CC subagent with full MCP tool access. Used by SOPs that declare execution: subagent.

How to use the semantic-scholar MCP tools for academic paper lookup, citation tracing, author profiling, and paper recommendations. Use this skill whenever the user asks about academic papers, citations, references, author h-index, paper metadata, or wants to search the academic literature — even if they don't mention "Semantic Scholar" by name. Also use it when you need to look up a paper by arXiv ID, DOI, or title.