All skills
oaustegard avatar

/down-skilling

@5e58100

Distill Opus-level reasoning into optimized instructions for Haiku 4.5 (and Sonnet). Generates explicit, procedural prompts with n-shot examples that maximize smaller model performance on a given task. Use when user says "down-skill", "distill for Haiku", "optimize for Haiku", "make this work on Haiku", "generate Haiku instructions", or needs to delegate a task to a smaller model with high reliability.

Use this Skill: https://skilld.dev/gh/oaustegard/claude-skills/down-skilling

This session only. Nothing lands on disk.

gapssummarization-fidelity.md

≈310 tokens on demand. Your agent reads this file only when SKILL.md points to it.

Summarization Fidelity

Opus: Produces summaries that accurately reflect source material. Naturally distinguishes between main claims and supporting detail. Maintains appropriate level of abstraction.

Haiku: Summaries may:

  • Overweight content from the beginning/end of the source (position bias)
  • Lose nuance (turn hedged claims into definitive statements)
  • Miss the central thesis while including peripheral details
  • Add interpretive framing not present in the source

Mitigation: Constrain the summarization process.

Step 1: Identify the single main claim or thesis of the text.
        Write it in one sentence.
Step 2: Identify 3 supporting points. Write each in one sentence.
Step 3: Combine into a coherent paragraph of 60-80 words.

Rules:
- The main claim MUST appear in the first sentence of your summary.
- Do not add interpretation or analysis.
- Do not introduce information not in the source.
- If the source hedges a claim ("may", "suggests", "could"),
  preserve the hedging in your summary.

For longer documents, fight position bias:

Divide the text into thirds (beginning, middle, end).
Extract one key point from each third.
Your summary must include content from all three sections.

Source: SKILL.md on GitHub

No alerts12d4 checks · Risk SAFE
  • Gen Agent Trust Hub12d

    The skill provides guidelines and templates for optimizing AI prompts for smaller models by distilling complex reasoning into explicit procedures and many-shot examples. No security issues were detected.

  • Socket12d

    No alerts

  • Snyk12d

    Risk: LOW · No issues

  • Runlayer7mo

    2/37 files flagged

Signed by skilld at 5e58100. This ties the file your Agent reads to that commit on GitHub. It does not review the instructions.

Last checked against GitHub yesterday.

Activeupdated 3 weeks ago
metadata
{
  "author": "Oskar Austegard and Opus",
  "version": "1.3.1"
}

README badge

README badge for oaustegard/claude-skills/down-skilling