# Skill Autoresearch

> Route reusable skill-improvement work into one bounded repo-local ratcheting packet: ratchet elig…

Route reusable skill-improvement work into one bounded repo-local ratcheting packet: ratchet eligibility, benchmark readiness, loop charter freeze, baseline scoring, one-change mutation, support-surface sync, or final keep/revert report. Use when an existing `SKILL.md`, SOP, prompt, or workflow doc may need sharper triggers, clearer instructions, better support files, or cleaner discovery wording and you want a frozen evaluation harness, append-only experiment logs, and explicit keep-or-revert decisions instead of ad hoc rewriting. Also use when you need to prove that no ratchet is justified yet. Not for GPU-bound Karpathy `autoresearch` runs or hosted app-scale eval / observability platforms such as LangSmith, Braintrust, Weave, or Promptfoo.

- Page: https://ss33.ai/skills/akillness/skill-autoresearch-64151908038
- Publisher: akillness
- Category: [AI & Agents](https://ss33.ai/skills/category/ai-and-agents-y6jz7i) › [Skill & prompt authoring](https://ss33.ai/skills/category/ai-and-agents-y6jz7i/skill-and-prompt-authoring-p179rh)
- Source: https://github.com/akillness/jeo-skills/blob/d9af9e3de37b0fd940d5cab1897c9b9a00fd8a35/.agent-skills/skill-autoresearch/SKILL.md

## Skill

This skill's licence does not allow redistribution, so the store does not serve its text. Get it from the author: https://github.com/akillness/jeo-skills/blob/d9af9e3de37b0fd940d5cab1897c9b9a00fd8a35/.agent-skills/skill-autoresearch/SKILL.md
