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
Present obstacles with their severity assessments and proposed mitigations to the user. Ask whether they can accept these obstacles. If unacceptable after 2 rounds, return to present-candidates.
yogsoth-ai/de-anthropocentric-research-engine
Skill Claude CodeCodex
Rate each identified obstacle's difficulty — overcomability, time cost, workaround existence. May optionally use search tools to validate assessments.
yogsoth-ai/de-anthropocentric-research-engine
Skill Claude CodeCodex
Standardize assignee names and identify corporate group affiliations across patent offices.
yogsoth-ai/de-anthropocentric-research-engine
Skill Claude CodeCodex
Surface all assumptions, classify by vulnerability (load-bearing × likely-false), validate causal logic. Focus on dangerous assumptions — high load-bearing + non-explicit.
yogsoth-ai/de-anthropocentric-research-engine
Skill Claude CodeCodex
Build assumption dependency graphs and trace cascade failures when root assumptions are invalidated.
yogsoth-ai/de-anthropocentric-research-engine
Skill Claude CodeCodex
Tactic: Surface assumptions, sort by dependency, attack root assumptions first, then trace cascade failures through the dependency graph.
yogsoth-ai/de-anthropocentric-research-engine
Skill Claude CodeCodex
Challenge each assumption's validity — shared cross-repo SOP.
yogsoth-ai/de-anthropocentric-research-engine
Skill Claude CodeCodex
Which assumptions are most fragile? — Vulnerability ranking + impact assessment of experiment assumptions.
yogsoth-ai/de-anthropocentric-research-engine
Skill Claude CodeCodex
Measure how much conclusions change when each assumption is negated. Ranks assumptions by their impact on the final result.
yogsoth-ai/de-anthropocentric-research-engine
Skill Claude CodeCodex
Assumption Destruction Campaign — open new solution spaces by negating, reversing, and challenging fundamental assumptions.
yogsoth-ai/de-anthropocentric-research-engine
Skill Claude CodeCodex
Systematic extraction, challenge, and sensitivity analysis of assumptions underlying a decision to identify load-bearing beliefs.
yogsoth-ai/de-anthropocentric-research-engine
Skill Claude CodeCodex
Classic reductio ad absurdum: negate the core claim, derive logical consequences, seek contradiction or absurdity.
yogsoth-ai/de-anthropocentric-research-engine
Skill Claude CodeCodex
Systematic stress testing of assumptions — surface, classify by vulnerability, attack, assess fragility. Combines assumption-surfacing (shared), abp-vulnerability-classification, and clr-validation SOPs.
yogsoth-ai/de-anthropocentric-research-engine
Skill Claude CodeCodex
Compute overall resilience score (0.0-1.0) based on attack results, coverage, and vulnerability severity distribution.
yogsoth-ai/de-anthropocentric-research-engine
Skill Claude CodeCodex
Generate specific attack strategies for a given threat surface, producing concrete probes that can be executed.
yogsoth-ai/de-anthropocentric-research-engine
Skill Claude CodeCodex
Identify and suspend fundamental assumptions via de Bono PO. Systematically negate axioms to reveal hidden solution spaces.
yogsoth-ai/de-anthropocentric-research-engine
Skill Claude CodeCodex
Tactic for systematically extracting axes of variation from literature — identify how practitioners compare approaches.
yogsoth-ai/de-anthropocentric-research-engine
Skill Claude CodeCodex
SOP for validating that candidate axes are independent and meaningful.
yogsoth-ai/de-anthropocentric-research-engine
Skill Claude CodeCodex
Gather independent ranking ballots from multiple judges or perspectives for a given candidate set.
yogsoth-ai/de-anthropocentric-research-engine
Skill Claude CodeCodex
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.
yogsoth-ai/de-anthropocentric-research-engine
Skill Claude CodeCodex
Select appropriate baselines for experimental comparison.
yogsoth-ai/de-anthropocentric-research-engine
Skill Claude CodeCodex
Produce final structured baseline report integrating all analysis results.
yogsoth-ai/de-anthropocentric-research-engine
Skill Claude CodeCodex
Evaluation Methodology Archaeology Campaign — 5 strategies for systematic analysis of AI/ML benchmarks, metrics, and leaderboards. Reveals construct validity issues, saturation, data contamination, and evaluation protocol inconsistencies.
yogsoth-ai/de-anthropocentric-research-engine
Skill Claude CodeCodex
Systematic quality assessment using BetterBench 46-criterion framework — 5 benchmarks, 30 papers, 40 web searches.
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: