audit-explanatory-compression
SkillDev toolsLets your agent check whether a simple explanation is genuinely powerful or just relabeling observations in fancy words.
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 audit-explanatory-compression skill
About this skill
Test whether an elegant/simple explanation earns its compression by forbidding alternatives, subsuming independent facts, or making risky predictions, rather than merely relabeling observations with a compact vocabulary.
What this skill tells your AI
The instructions your AI receives, as published by yogsoth-ai/de-anthropocentric-research-engine in skills/audit-explanatory-compression/SKILL.md and read by ahel’s review.
Purpose
Test whether an elegant explanation earns compression by excluding alternatives, subsuming independent facts, or making risky predictions.
Input contract
mode_contracts:
earned-simplicity: &compression_audit_input
required: [explanation, covered_facts, alternatives]
optional: [predictions, evidence]
constraints: [facts_and_alternatives_must_be_independently_enumerated]
decorative-simplicity: *compression_audit_input
risky-prediction: *compression_audit_input
Execution protocol
Do not perform called SOP operations inline; each loaded SOP owns its contract and thresholds.
- You MUST load skill
classify-simplicity-evidenceto classify the explanation's compression evidence. - You MUST load skill
test-risky-predictionto derive and test risky predictions. - You MUST load skill
construct-critiqueto attack the explanation. You MUST load skillscore-objectto score its remaining support. Deviation: omit prediction testing only when no nontrivial prediction can be derived, and mark the explanation non-discriminating.
Output contract
mode_contracts:
earned-simplicity: &compression_audit_output
produces: [forbidden_set, risky_predictions, accommodation_audit, deletion_test_result, elegance_verdict, earning_prediction]
delta_fields: [findings, evidence_updates, uncertainties, decisions]
decorative-simplicity: *compression_audit_output
risky-prediction: *compression_audit_output
Thresholds and quality gates
- Earned simplicity requires at least one independent fact compressed and one risky alternative-forbidding prediction, each evidence-linked.
- Decorative simplicity is a failure when it merely renames observations.
Failure and counterexamples
Do not reward brevity alone. Mark weak when independent facts, exclusions, or predictions are absent.
Provenance map
- resolved: elegance-trap-probe
Preserved source criteria ledger
| source | source line | kind | source criterion |
|---|---|---|---|
| v4 architecture | node desc | textual | Distinguish earned simplicity from decorative relabeling. |
Context checkpoint / Delta notes
Append covered facts, alternatives, risky predictions, critique, and score rationale.
Mode branches
earned-simplicity: seek independent compression and exclusions.decorative-simplicity: test for relabeling.risky-prediction: prioritize prospective constraints.
Signals
- GitHub stars
- 501
- Forks
- 41
- Last commit
- Sep 2026
Advanced
- Catalog kind
- skill
- Key
audit-explanatory-compression- Source
- github.com/yogsoth-ai/de-anthropocentric-research-engine