down-skilling

Down-Skilling: Opus → Haiku Distillation

Translate your reasoning capabilities into explicit, structured instructions that Haiku 4.5 can execute reliably. You are a compiler: your input is context, intent, and domain knowledge; your output is a Haiku-ready prompt with decision procedures and diverse examples.

Core Principle

Opus infers from WHY. Haiku executes from WHAT and HOW.

Your job: convert implicit reasoning, contextual judgment, and domain expertise into explicit procedures, concrete decision trees, and demonstrative examples. Every inference you would make silently, Haiku needs stated explicitly.

Economics: Why Examples Are Free

Opus 5 costs 5× Haiku 4.5 on both sides ($5/$25 vs $1/$5 per MTok; 2026-09 pricing). A task that costs $1.00 on Opus costs ~$0.20 on Haiku — but only if Haiku gets it right on the first try. One retry halves the savings; a few retries makes Haiku more expensive.

The math that matters:

• Input tokens are cheap (Haiku 4.5: $1.00/MTok input vs $5.00/MTok output)
• Adding 2,000 tokens of examples costs ~$0.002 per call
• A single failed-then-retried call costs ~$0.008+ in wasted output
• Examples pay for themselves if they prevent even 1-in-5 retries

What this means for prompt design:

• If you're sending an 8K token document, you can afford 3-4K tokens of examples — the examples cost less than the document itself
• Lengthy input prompts don't inflate output costs — output pricing is independent of input length
• The constraint is not token cost but diminishing returns: after 5-7 examples, additional examples rarely improve performance

Bottom line: Every example that prevents a Haiku misfire saves 5-25× its input cost in wasted output tokens. Under-investing in examples is the most expensive mistake in down-skilling.

Before Distilling: Check Whether the Task Needs It (2026-07 calibration)

This skill's gap catalog was originally derived from model-card priors. A 2026-07-15 empirical calibration (300 measured Haiku 4.5 calls; data in the agent-routing skill's references/calibration-2026-07-15.md) found Haiku 4.5 substantially stronger than those priors on mechanically checkable work: 240/240 on nested modular arithmetic (16-leaf expression trees), 30-hop function chains, 25-operation state tracking, trap-laden word math, and 5-simultaneous-constraint sentence generation (exact word counts, required/forbidden tokens, a lipogram) — at effort: low, and in one control with chain-of-thought suppressed entirely. On the same battery Sonnet at low effort scored 17/20, missing exact-count constraints Haiku satisfied.