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
Systematic structure-mapping from source to target domain (Gentner). Identify relational correspondences and transfer higher-order constraints.
yogsoth-ai/de-anthropocentric-research-engine
Skill Claude CodeCodex
Chain analogies to deeper levels (3-5 layers). Each layer reveals new aspects and insights not visible at the surface.
yogsoth-ai/de-anthropocentric-research-engine
Skill Claude CodeCodex
Extract transferable structural principles from source domains. Orchestrates source identification → abstraction → structural mapping → transfer validation.
yogsoth-ai/de-anthropocentric-research-engine
Skill Claude CodeCodex
Assess analogy depth (surface/structural/systemic). Determines whether an analogy warrants transfer investment.
yogsoth-ai/de-anthropocentric-research-engine
Skill Claude CodeCodex
KAOS-style recursive goal decomposition. AND decomposition for sub-goals that must ALL be satisfied. OR decomposition for alternative paths where any one suffices. Produces a GoalTree (DAG structure).
yogsoth-ai/de-anthropocentric-research-engine
Skill Claude CodeCodex
SOP: Describe and classify anomalous phenomena that existing theory cannot explain.
yogsoth-ai/de-anthropocentric-research-engine
Skill Claude CodeCodex
Tactic: Inductive/abductive path — describe anomalous phenomena, generate candidate explanations, rank by plausibility.
yogsoth-ai/de-anthropocentric-research-engine
Skill Claude CodeCodex
SOP: Design the optimal answering order for sub-questions.
yogsoth-ai/de-anthropocentric-research-engine
Skill Claude CodeCodex
Challenge industry best practices' hidden assumptions. Deconstruct benchmarks to reveal unexamined constraints.
yogsoth-ai/de-anthropocentric-research-engine
Skill Claude CodeCodex
Search for positive deviants and extract transferable principles using Appreciative Inquiry.
yogsoth-ai/de-anthropocentric-research-engine
Skill Claude CodeCodex
Find positive deviants and reframe the problem from deficit-based to asset-based using Appreciative Inquiry.
yogsoth-ai/de-anthropocentric-research-engine
Skill Claude CodeCodex
Establish acceptability standards through RAND/UCLA Appropriateness Method or Consensus Conference protocols.
yogsoth-ai/de-anthropocentric-research-engine
Skill Claude Code needs its repo
SOP: Turn the feeding plan into the compiler's $ARGUMENTS and run the external ARA compiler once inline to produce ../ara/.
yogsoth-ai/de-anthropocentric-research-engine
Skill Claude Code
Campaign: Compile a context/ research record into an ARA (Agent-Native Research Artifact) and run a Level-2 epistemic review — no LaTeX, no narrative paper.
yogsoth-ai/de-anthropocentric-research-engine
Skill Claude CodeCodex
SOP: Run the external ARA rigor-reviewer (Seal Level 2, six-dimension semantic review) over ../ara/ and pass its level2report.json to the user.
yogsoth-ai/de-anthropocentric-research-engine
Skill Claude CodeCodex
Distill the strongest arguments from each perspective through Argument Delphi or Dialectical Delphi methods.
yogsoth-ai/de-anthropocentric-research-engine
Skill Claude CodeCodex
Extract and steel-man the core arguments supporting a given opinion cluster.
yogsoth-ai/de-anthropocentric-research-engine
Skill Claude CodeCodex
Campaign for mapping argument structures — extract claims, link evidence, assess strength, synthesize positions. Produces argument graphs in the wiki vault.
yogsoth-ai/de-anthropocentric-research-engine
Skill Claude CodeCodex
Strategy for synthesizing argument positions — aggregate evidence, resolve contradictions, produce synthesis reports identifying which claims survive scrutiny.
yogsoth-ai/de-anthropocentric-research-engine
Skill Claude CodeCodex
SOP for generating argument structure visualization — query graph for argument chains, format as mermaid diagram or indented tree, write to vault.
yogsoth-ai/de-anthropocentric-research-engine
Skill Claude CodeCodex
Detect annotation artifacts and shortcuts in benchmarks.
yogsoth-ai/de-anthropocentric-research-engine
Skill Claude CodeCodex
Understand 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.
yogsoth-ai/de-anthropocentric-research-engine
Skill Claude CodeCodex
Present the GoalTree to the user for confirmation. Ask about reasonableness, missing elements, and priority ordering among sub-goals.
yogsoth-ai/de-anthropocentric-research-engine
Skill Claude CodeCodex
Deep WHY probing inspired by i Intentionality modeling. Understand the user's motivation, success definition, risk tolerance, innovation preference, independence preference, time urgency, and learning willingness. The most important SOP in actor-profiling — understanding WHY drives everything downstream.
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: