abstract-structure
Remove domain surface details to expose transferable relational/mechanistic structure at a chosen abstraction level.
Break fixation by surfacing assumptions and applying deliberate provocation modes (reversal, negation, random entry, exaggeration, extreme/zero-resource constraint, distortion), then extract constructive movement and synthesize candidate directions.
$ npx -y skills add yogsoth-ai/de-anthropocentric-research-engine --skill destructive-ideation --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/destructive-ideationContext preview
The summary Claude sees to decide when to auto-load this skill.
Break fixation by surfacing assumptions and applying deliberate provocation modes (reversal, negation, random entry, exaggeration, extreme/zero-resource constraint, distortion), then extract constructive movement and synthesize candidate directions.
name: destructive-ideation description: "Break fixation by surfacing assumptions and applying deliberate provocation modes (reversal, negation, random entry, exaggeration, extreme/zero-resource constraint, distortion), then extract constructive movement and synthesize candidate directions."
Break fixation with explicit provocation modes, then extract constructive movement and candidate directions.
mode_contracts:
reverse: &destructive_input
required: [current_frame, target_problem]
optional: [load_bearing_assumptions, constraints]
constraints: [provocation_must_name_the_frame_or_assumption_it_attacks]
negation: *destructive_input
random-entry: *destructive_input
extreme-constraint: *destructive_input
sacred-cow: *destructive_input
distortion: *destructive_inputDo not perform called SOP operations inline; each loaded SOP owns its contract and thresholds.
1. You MUST load skill `surface-assumptions` to surface assumptions. 2. You MUST load skill `generate-provocation` to generate the mode-specific provocation. 3. You MUST load skill `extract-constructive-movement` to extract constructive movement. 4. You MUST load skill `synthesize-idea` to synthesize an idea. 5. You MUST load skill `build-concept-fan` to expand the concept fan. If the idea now requires explicit component transformation, consider `structural-transformation`. If it exposes a technical or physical contradiction, consider `resolve-inventive-contradiction`. Deviation: mode may be reverse, negation, random-entry, extreme-constraint, sacred-cow, or distortion; record the selected mode.
mode_contracts:
reverse: &assumption_attack_output
produces: [assumption_targets, provocations, constructive_movements, idea_set]
delta_fields: [findings, hypothesis_updates, assumption_updates, decisions, recommended_jumps]
negation: *assumption_attack_output
random-entry: &provocation_output
produces: [provocations, constructive_movements, idea_set]
delta_fields: [findings, hypothesis_updates, assumption_updates, decisions, recommended_jumps]
extreme-constraint: *assumption_attack_output
sacred-cow: *assumption_attack_output
distortion: *provocation_outputReject unbounded randomness, provocation without a target, and ideas that cannot state what constructive movement they preserve.
Append mode, attacked assumptions, provocations, movements, and selected directions.
The complete research orchestration system for AI-native science. What It Does Design Philosophy Architecture (v3.2.2) Quick Start Configuration Roadmap License DARE is not a tool that helps you do research. It is the researcher.
Repo: yogsoth-ai/de-anthropocentric-research-engine
Remove domain surface details to expose transferable relational/mechanistic structure at a chosen abstraction level.
Evaluate competing arguments against stated criteria and produce a reasoned verdict with uncertainty.
Move a scientific object up/down in abstraction or narrow/broaden selected scope dimensions (population, mechanism, context, outcome, timeframe, system…
Run structured attack/defense/adjudication over a claim, candidate, criterion set, or current winner. Perspective, target, escalation depth,…
Aggregate criterion or comparison results into an ordered recommendation under an explicit rule.
Abstract relational structure from source domains, map it to the target, validate depth, and instantiate transferable mechanisms.