900+ pure-markdown skills for autonomous AI research, organized as 9 freely-composable packages over a 4-layer hierarchy (Campaign → Strategy → Tactic → SOP). Non-linear orchestration with backtracking, 6 MCP integrations. The AI is the researcher — you set the direction.
This repository also configures its own agents. See what de-anthropocentric-research-engine tells them →
yogsoth-ai/de-anthropocentric-research-engine
Skill Claude CodeCodex
Test a claim at extreme parameter values and detect the precise point where it breaks down.
yogsoth-ai/de-anthropocentric-research-engine
Skill Claude CodeCodex
Validate analogy depth and transfer viability. Ensures only deep structural analogies (not surface-level similarities) proceed to transfer.
yogsoth-ai/de-anthropocentric-research-engine
Skill Claude CodeCodex
Optimize experiment design under compute and time budget constraints.
yogsoth-ai/de-anthropocentric-research-engine
Skill Claude CodeCodex
Calculate project, feeding, and resource buffers — shared with implementation-planning.
yogsoth-ai/de-anthropocentric-research-engine
Skill Claude CodeCodex
Structured questioning SOP to determine which campaigns to include, emphasize, or skip. Used during spec generation.
yogsoth-ai/de-anthropocentric-research-engine
Skill Claude CodeCodex
Build capability taxonomy, map existing benchmark coverage.
yogsoth-ai/de-anthropocentric-research-engine
Skill Claude CodeCodex
Cluster papers by theme, method, or timeline. Produces natural groupings from a paper collection. Used by scoping-survey and narrative-review.
yogsoth-ai/de-anthropocentric-research-engine
Skill Claude CodeCodex
Classify candidates into predefined categories using ELECTRE-Tri, FlowSort, AHPSort, or DRSA methods.
yogsoth-ai/de-anthropocentric-research-engine
Skill Claude CodeCodex
Apply Checkland's CATWOE analysis from a specific stakeholder perspective to reveal how the problem looks from that viewpoint.
yogsoth-ai/de-anthropocentric-research-engine
Skill Claude CodeCodex
SOP for tracing causal chains — follow edges from cause to effect through intermediate variables.
yogsoth-ai/de-anthropocentric-research-engine
Skill Claude CodeCodex
Trace UDE to root cause via IF...THEN...BECAUSE logic chains.
yogsoth-ai/de-anthropocentric-research-engine
Skill Claude CodeCodex
Extract all causal claims (X causes Y, X leads to Y, X enables Y) from an artifact, producing a structured list of cause-effect pairs.
yogsoth-ai/de-anthropocentric-research-engine
Skill Claude CodeCodex
Campaign for building causal models — identify variables, map mechanisms, collect evidence, analyze interventions, validate models. Produces causal graphs in the wiki vault.
yogsoth-ai/de-anthropocentric-research-engine
Skill Claude CodeCodex
Tactic: Extract causal claims, evaluate probability of necessity (PN) and sufficiency (PS) for each, classify into necessity-sufficiency quadrants.
yogsoth-ai/de-anthropocentric-research-engine
Skill Claude CodeCodex
Build logical causal trees from symptoms to root causes — list UDEs, connect causal chains, validate logic, locate root causes. Combines ishikawa-decomposition, current-reality-tree, and clr-validation SOPs.
yogsoth-ai/de-anthropocentric-research-engine
Skill Claude CodeCodex
Non-threatening 'Why?' questioning of current practices (de Bono Challenge).
yogsoth-ai/de-anthropocentric-research-engine
Skill Claude CodeCodex
Non-threatening 'Why?' questioning of current practices to reveal historical accidents vs. genuine constraints.
yogsoth-ai/de-anthropocentric-research-engine
Skill Claude CodeCodex
Checkpoint state before risky operations, detect anomalies, and recover gracefully.
yogsoth-ai/de-anthropocentric-research-engine
Skill Claude CodeCodex
Strategy: Run BEFORE building any validator (sandbox/simulation/benchmark). Builds a non-circularity matrix of theory-claim × validator-assumption to detect when a validator would 'confirm' a theory only because it was built on the theory's own premises. A circular validator's PASS carries zero evidential weight.…
yogsoth-ai/de-anthropocentric-research-engine
Skill Claude CodeCodex
Forward and backward citation tracing tactic — expand paper coverage by tracing citation networks in both directions from seed/key papers. Alternates forward (who cited this) and backward (what this cited) passes until saturation.
yogsoth-ai/de-anthropocentric-research-engine
Skill Claude CodeCodex
Build and analyze patent citation networks — main path analysis, PageRank, cluster detection.
yogsoth-ai/de-anthropocentric-research-engine
Skill Claude CodeCodex
Deep claim scope analysis — decompose independent/dependent claims and assess protection scope breadth. Budget: 30 patent families, 30 claim parses, 20 web searches.
yogsoth-ai/de-anthropocentric-research-engine
Skill Claude CodeCodex
Strategy for extracting claims from source material — identify propositions, decompose compound claims, classify claim types, create claim pages in the vault.
yogsoth-ai/de-anthropocentric-research-engine
Skill Claude CodeCodex
Formally negate the core claim, producing the logical complement for reductio testing.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: