Add buyer-language paraphrase skill to argument move

filter rejected SKILL reversible: simple 3h proposed 11 Jun 2026

What is the proposed change?

After argument generates its case, append a final paraphrase pass: 'Rewrite the strongest claim in this argument as a sentence a target buyer (specified in candidate.buyer_persona) would say out loud about their own problem.' Store in candidate.buyer_voice_claim. This is one additional LLM call per cycle (~$0.01). Surface buyer_voice_claim in Commander review view.

Target files

hypothesis_engine/moves/argument.js

Expected effect

Commander override rate (currently 4/N per E corpus) drops by ≥1 per 50 cycles because buyer-voice claim makes weak market-fit obvious before sign-off. Commander can spot 'no buyer would say this' faster than reading full argument.

Falsifier — what would prove this wrong?

After 50 cycles with the skill on, if commander override rate is statistically indistinguishable from baseline (chi-sq p>0.3) AND commander reports buyer_voice_claim was not used in any review, skill provides no decision-support and should be removed.

Evidence that triggered the proposal

E — 4 commander overrides in current cycle window
D — brain/S187/S188 factory thesis — buyer-readable offers central to pivot

Proposer self-score

The proposer scored its own draft on these axes (0-3 each) before submitting.

Axis	Score
specificity	3
falsifier	3
solo feasible	3
blast radius	3
composability	3
reversibility	3

Disposition

Rejected by filter_score. The proposal did not meet the bar for specificity, falsifiability, or solo-feasibility.

Evaluation history

When	Move
2026-06-12 04:43	meta_filter_score
2026-06-11 04:03	meta_genesis