axiom-negation
Axiom Negation systematically identifies and suspends fundamental assumptions using Edward de Bono's Provocative Operation (PO) technique to reveal hidden solution spaces. Use this skill when exploring complex problems where conventional thinking has reached an impasse, needing to break free from unstated paradigmatic constraints through formal negation and alternative construction.
git clone --depth 1 https://github.com/yogsoth-ai/de-anthropocentric-research-engine /tmp/axiom-negation && cp -r /tmp/axiom-negation/skills/axiom-negation ~/.claude/skills/axiom-negationSKILL.md
# Axiom Negation Identify and suspend fundamental assumptions via de Bono PO. ## State Ledger | Resource | Target | Current | % | |----------|--------|---------|---| | web-search | 20 | 0 | 0% | | web-research | 5 | 0 | 0% | | paper-overview | 20 | 0 | 0% | | paper-search | 12 | 0 | 0% | | paper-research | 5 | 0 | 0% | ## HARD-GATE Cannot exit strategy until ≥80% of each budget line is consumed OR yield targets are met with justification for remaining budget. ## Available Tactics | Tactic | Role | |--------|------| | provocation-generation | Generate PO provocations from negated axioms | | assumption-enumeration | Surface assumptions to negate | ## Available SOPs | SOP | Role | |-----|------| | assumption-perturbation | Perturb each axiom and observe consequences | | reversal-generation | Generate formal negations of axioms | | constructive-rebellion | Build alternatives from negated axioms | | destruction-synthesis | Synthesize negation outputs | ## Execution Guidance 1. **Surface axioms**: Use assumption-enumeration tactic to identify paradigmatic assumptions 2. **Apply PO**: For each axiom, state "PO: [negation]" — suspend judgment 3. **Perturb**: Run assumption-perturbation to observe system response under negation 4. **Extract movement**: Use provocation-generation to find constructive directions 5. **Build alternatives**: Use constructive-rebellion to form viable solutions 6. **Synthesize**: Produce structured output via destruction-synthesis
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: 面对异常的最佳解释推理
Remove components one by one, observe system changes to reveal hidden dependencies and generate ideas from structural gaps.
Map system architecture to ablatable units for ablation studies
Design ablation studies to isolate component contributions in ML systems