anti-benchmark
Challenge industry best practices' hidden assumptions. Deconstruct benchmarks to reveal unexamined constraints.
386 repo starsObserved in 1 repos
Research
Research skills
Browse reusable Agent Skills, each with a clear purpose and practical guidance.
appreciative-discovery
Search for positive deviants and extract transferable principles using Appreciative Inquiry.
386 repo starsObserved in 1 repos
Research
ara-from-context
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
386 repo starsObserved in 1 repos
Research
argument-crystallization
Distill the strongest arguments from each perspective through Argument Delphi or Dialectical Delphi methods.
386 repo starsObserved in 1 repos
Research
argument-extraction
Extract and steel-man the core arguments supporting a given opinion cluster.
386 repo starsObserved in 1 repos
Research
argument-mapping
Campaign for mapping argument structures — extract claims, link evidence, assess strength, synthesize positions. Produces argument graphs in the wiki vault.
386 repo starsObserved in 1 repos
Research
argument-synthesis
Strategy for synthesizing argument positions — aggregate evidence, resolve contradictions, produce synthesis reports identifying which claims survive scrutiny.
386 repo starsObserved in 1 repos
Research
ask-constraints
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.
386 repo starsObserved in 1 repos
Research
assumption-audit
Surface all assumptions, classify by vulnerability (load-bearing × likely-false), validate causal logic. Focus on dangerous assumptions — high load-bearing + non-explicit.
386 repo starsObserved in 1 repos
Research
assumption-challenging
Challenge each assumption's validity — shared cross-repo SOP
386 repo starsObserved in 1 repos
Research