eval-autoresearch-fit
CommunityAssess autoresearch viability for a skill.
Authorrichfrem
Version1.0.0
Installs0
System Documentation
What problem does it solve?
This Skill helps teams determine whether a given skill is a viable candidate for Karpathy's autoresearch autonomous optimization loop, enabling fast, structured evaluation and ranking.
Core Features & Use Cases
- Scores a skill on Objectivity, Execution Speed, Frequency of Use, and Potential Utility.
- Proposes a 3-file architecture (Spec, Mutation Target, Evaluator) and a concrete mutation target for iterative improvement.
- Outputs a verdict (HIGH / MEDIUM / LOW / NOT_VIABLE) and updates the canonical ranked-skills.json.
Quick Start
Inspect the target skill's SKILL.md and trigger the autoresearch-fit evaluation to generate a ranked verdict and architecture plan.
Dependency Matrix
Required Modules
None requiredComponents
scriptsassets
💻 Claude Code Installation
Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.
Please help me install this Skill: Name: eval-autoresearch-fit Download link: https://github.com/richfrem/agent-plugins-skills/archive/main.zip#eval-autoresearch-fit Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
Agent Skills Search Helper
Install a tiny helper to your Agent, search and equip skill from 471,000+ vetted skills library on demand.