down-skilling SKILL.md skillA
down-skilling from oaustegard/claude-skills is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add oaustegard/claude-skills/down-skilling@v1.7.1Pins v1.7.1 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- oaustegard/claude-skills
- Path
plugins/ai-and-reasoning/skills/down-skilling/SKILL.md- Versions recorded
- 8
- Latest version
- v1.7.1, committed Oct 10, 2026
- First version recorded
- Jul 7, 2026
- Size
- 26,000 bytes
- Repository stars
- 158
- License
- MIT
Distill Opus-level reasoning into optimized instructions for Haiku 5.5 (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.
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
# Down-Skilling: Opus → Haiku Distillation Translate your reasoning capabilities into explicit, structured instructions that Haiku 5.5 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 5.5 costs 40× Haiku 5.5 on both sides ($4/$20 vs $0.10/$0.50 per MTok for prompts up to 100K tokens; 2026-10 pricing), and Sonnet 5.5 costs 20×. A task that costs $1.00 on Opus costs ~$0.025 on Haiku, so retries no longer erase the saving: Haiku can fail and retry a dozen times and still cost less than one Opus attempt. (At Haiku 4.5's $1/$5 it was 5×, and one retry halved the saving.) What a misfire costs now is mostly *silent* error, a plausible wrong answer no verifier caught, not dollars. **The math that matters:** …
Read the whole file at its exact version.
How to install
mdr add oaustegard/claude-skills/down-skilling@sha256:67acd48d248b991eThe line at the top of this page pins the label v1.7.1, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
[](https://markdownregistry.com/a/art_b3gevdsd5b6na5nf)
4 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 8 versions of this file, between Jul 7, 2026 and Oct 10, 2026, about one every 13 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| v1.7.1 latest | 2026-10-10 | 63d432e | 26,000 B | A | view · diff |
| v1.7.0 | 2026-10-08 | 6fc82b8 | 25,961 B | A | view · diff |
| v1.6.0 | 2026-10-07 | a77b9b4 | 24,976 B | A | view · diff |
| v1.5.0 | 2026-10-07 | 7f784a1 | 24,570 B | A | view · diff |
| v1.4.0 | 2026-10-07 | 87f7fec | 21,952 B | A | view · diff |
| v1.3.1 | 2026-09-09 | 5e58100 | 21,427 B | A | view · diff |
| v1.3.0 | 2026-07-15 | 28683db | 21,429 B | A | view · diff |
| v1.2.0 | 2026-07-07 | 6154d36 | 19,188 B | A | view |
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (26000 bytes)
- pass: No zero-width or bidi control characters
- pass: No instruction hidden inside an HTML comment
- pass: No link to an exfiltration or paste host
- pass: No credential-shaped string
- pass: No instruction to send local credentials anywhere
- pass: No text hidden with inline styles
- pass: No prompt-injection phrasing
- pass: No curl or wget piped into a shell
- pass: No recursive delete of root, home or parent
- pass: No instruction to read or print local credentials
- pass: No base64 blob over 200 characters
- pass: No link to a raw IP address
- pass: No script tag
Source
oaustegard/claude-skills · 158 stars · license MIT · pushed 2026-11-07 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_b3gevdsd5b6na5nf GET https://markdownregistry.com/api/v1/resolve?ref=oaustegard/claude-skills/down-skilling GET https://markdownregistry.com/api/v1/blob/67acd48d248b991e669bbe50e3dbbd81ff33924b1a47d7710a27df2e2d3459be
Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.
More from oaustegard/claude-skills
Every file in oaustegard/claude-skills