assumption-cascade
Assumption Cascade identifies and attacks root assumptions in research artifacts, then traces how their failures propagate through dependent conclusions. Use this skill when systematically validating the foundational premises of an argument or analysis to understand vulnerability pathways and which conclusions are most exposed to assumption failures.
git clone --depth 1 https://github.com/yogsoth-ai/de-anthropocentric-research-engine /tmp/assumption-cascade && cp -r /tmp/assumption-cascade/skills/assumption-cascade ~/.claude/skills/assumption-cascadeSKILL.md
# Assumption Cascade Tactic Attack assumptions at their roots and trace how failures propagate through dependency chains. ## Orchestration 1. **key-assumptions-check** surfaces all assumptions (explicit and implicit) 2. **assumption-cascade-tracer** builds dependency graph (which assumptions depend on which) 3. Root assumptions identified (those with no upstream dependencies) 4. **devils-advocacy** constructs strongest attack against each root assumption 5. **probe-execution** tests root assumptions — if root fails, trace downstream cascade 6. **assumption-cascade-tracer** maps full cascade: which conclusions collapse if root fails 7. **finding-aggregation** reports cascade paths and total impact scope ## Subagents Dispatched - key-assumptions-check (1 call for enumeration) - assumption-cascade-tracer (2 calls: dependency build + cascade trace) - devils-advocacy (1 call per root assumption) - probe-execution (1 call per root attack) - finding-aggregation (1 call at end) ## Termination Conditions - All root assumptions tested (budget permitting) - Cascade found that invalidates >50% of conclusions (critical finding) - All assumptions survive attack (artifact resilient at assumption level) - Budget exhausted (report partial coverage) <!-- BEGIN available-tables (generated) --> ## Available SOPs Optional, no fixed order; the final leaf is always a sop. | SOP | When to use | | --- | --- | | assumption-cascade-tracer | Build assumption dependency graphs and trace cascade failures when root assumptions are invalidated. | | devils-advocacy | Construct the strongest possible counter-argument against a position, steelmanning the opposition before attacking. | | finding-aggregation | Aggregate, deduplicate, and classify findings from multiple probes into a coherent vulnerability report. | | key-assumptions-check | Military ACT: systematically enumerate all assumptions, classify by type, and evaluate evidence strength supporting each. | | probe-execution | Execute a single attack probe against an artifact, record the result with evidence and severity classification. | <!-- END available-tables (generated) -->
Experiment-specific - summarize the DARE executor's research design into a clean research_result report, forced to write back into the spec file produced by formated-specs.
Experiment-specific - replaces writing-specs, emits DARE's 4-layer call plan as a clean research_graph schema. Last step forces load formated-result.
loss-1 judge - read a sample's full dialogue and decide whether the user simulator semantically enacted its Policy Card. check-blind.
loss-2 judge - pairwise quality comparison across the n rungs within one topic; decide monotonicity and endpoint separation. check-blind, D1-D5 only.
Strategy: Inference to the best explanation in the face of anomalies
Remove components one by one, observe system changes to reveal hidden
Map system architecture to ablatable units for ablation studies
Design ablation studies to isolate component contributions in ML systems