Anti-Benchmark

SkillDev tools

Challenge industry best practices' hidden assumptions. Deconstruct benchmarks

Available today. Use it from your connected AI after setup.

Connect ahel once, and every AI you use reads what you have installed.

Then ask your AI: use the Anti-Benchmark skill

What this skill tells your AI

The instructions your AI receives, as published by yogsoth-ai/de-anthropocentric-research-engine in skills/anti-benchmark/SKILL.md and read by ahel’s review.

Challenge industry best practices' hidden assumptions.

State Ledger

ResourceTargetCurrent%
web-search2500%
web-research1000%
paper-overview2500%
paper-search1500%
paper-research500%

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

TacticRole
assumption-enumerationSurface assumptions hidden in benchmarks

Available SOPs

SOPRole
benchmark-challengeIdentify and negate benchmark assumptions
sacred-cow-identificationFind unquestioned beliefs behind best practices
assumption-perturbationTest what happens when benchmark assumptions fail
constructive-rebellionBuild alternatives that violate benchmarks constructively
destruction-synthesisSynthesize anti-benchmark outputs

Execution Guidance

  1. Identify benchmarks: Catalog the industry best practices and standards in the domain
  2. Deconstruct: Use benchmark-challenge to expose hidden assumptions in each
  3. Surface sacred cows: Use sacred-cow-identification for deeper unquestioned beliefs
  4. Perturb: Use assumption-perturbation to test "what if this standard is wrong?"
  5. Research alternatives: Search for domains that succeed WITHOUT these benchmarks
  6. Build: Use constructive-rebellion to form solutions that violate conventions productively
  7. Synthesize: Produce structured output via destruction-synthesis

Available Tactics

Optional, no fixed order; the final leaf is always a sop.

TacticWhen to use
creative-ideation-assumption-enumerationSurface, perturb, and prioritize assumptions by disruption potential. Orchestrates assumption surfacing → perturbation → sacred cow identification → prioritization.

Available SOPs

Optional, no fixed order; the final leaf is always a sop.

SOPWhen to use
benchmark-challengeIdentify and negate benchmark assumptions. Deconstruct best practices to reveal hidden constraints and open new spaces.
constructive-rebellionBuild constructive alternatives from destructive negation. Transform violated assumptions into viable innovation directions.
creative-ideation-assumption-perturbationPerturb each assumption, observe system response. Systematic stress-testing of assumptions to reveal fragility and opportunity.
destruction-synthesisSynthesize all assumption destruction outputs into structured destructive innovation report.
sacred-cow-identificationFind domain's unquestioned beliefs. Systematic identification of dogma that constrains innovation.

Signals

GitHub stars
469
Forks
37
Last commit
Sep 2026
Advanced
Catalog kind
skill
Gateway key
anti-benchmark
Source
github.com/yogsoth-ai/de-anthropocentric-research-engine