destructive-ideation
SkillDev toolsLets your agent break out of stuck thinking by challenging assumptions and generating new problem-solving angles.
Available today. Use it from your connected AI after setup.
No other account needed.
Add ahel to your AI once: Claude, ChatGPT, Cursor, Claude Code or Codex. Then ask it to use this.
Then ask your AI: use the destructive-ideation skill
About 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.
What this skill tells your AI
The instructions your AI receives, as published by yogsoth-ai/de-anthropocentric-research-engine in skills/destructive-ideation/SKILL.md and read by ahel’s review.
Purpose
Break fixation with explicit provocation modes, then extract constructive movement and candidate directions.
Input contract
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_input
Execution protocol
Do not perform called SOP operations inline; each loaded SOP owns its contract and thresholds.
- You MUST load skill
surface-assumptionsto surface assumptions. - You MUST load skill
generate-provocationto generate the mode-specific provocation. - You MUST load skill
extract-constructive-movementto extract constructive movement. - You MUST load skill
synthesize-ideato synthesize an idea. - You MUST load skill
build-concept-fanto expand the concept fan. If the idea now requires explicit component transformation, considerstructural-transformation. If it exposes a technical or physical contradiction, considerresolve-inventive-contradiction. Deviation: mode may be reverse, negation, random-entry, extreme-constraint, sacred-cow, or distortion; record the selected mode.
Mode branches
reverse: invert the current desired/undesired relation.negation: negate a load-bearing assumption or axiom.random-entry: introduce an explicitly recorded external/random concept.extreme-constraint: force zero-resource or boundary conditions.sacred-cow: challenge an explicitly protected convention.distortion: exaggerate, compress, or otherwise perturb a salient feature.
Output contract
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_output
Thresholds and quality gates
- B: selected mode is explicit; each provocation has a constructive movement; candidate ideas retain a trace to the attacked frame.
Failure and counterexamples
Reject unbounded randomness, provocation without a target, and ideas that cannot state what constructive movement they preserve.
Provenance map
assumption-destruction,axiom-negation,provocation-and-movement,provocation-generation,movement-extraction: resolved/concept per exact v3 lookup.- Status:
assumption-destruction,axiom-negation,provocation-and-movement,movement-extractionresolved;provocation-generationconcept (only package-prefixed variants found).
Preserved source criteria ledger
- Preserve reversal, negation, random entry, exaggeration/extreme constraint, distortion, and movement extraction.
Context checkpoint / Delta notes
Append mode, attacked assumptions, provocations, movements, and selected directions.
Signals
- GitHub stars
- 501
- Forks
- 41
- Last commit
- Sep 2026
Advanced
- Catalog kind
- skill
- Key
destructive-ideation- Source
- github.com/yogsoth-ai/de-anthropocentric-research-engine