autoresearch
autoresearch is a Skill evaluation & testing skill for AI agents, published by byungjunjang in the jangpm-meta-skills repository on GitHub. Skillspace rates autoresearch C (70/100) and it passed the safety scan; the rating is based on static analysis only.
Autonomously optimize any Codex skill or agent system by running it repeatedly, scoring outputs against evals (binary for rules + comparative for quality), mutating any owned artifact — the skill's prompt, reference assets, and executable artifacts (scripts, agent/subagent definitions like `agents/openai.yaml`, MCP servers, hooks, harness code) — and keeping improvements. Based on Karpathy's autoresearch methodology. Use this skill whenever the user mentions optimizing a skill, improving a skill or agent, running autoresearch, making a skill or agent better, self-improving a skill, benchmarking a skill, evaluating a skill, running evals on a skill, optimizing an agent system, or any request to iteratively test and refine a skill or agent — even if they don't use the word "autoresearch" explicitly. Also trigger on 스킬 개선, 스킬 최적화, 스킬 벤치마크, 스킬 평가, 에이전트 개선, 에이전트 최적화. Outputs an improved target skill file (and any mutated executable artifacts), a results log, a changelog, and a research log…
- Grade
- C
- Quality
- 70 / 100
- Safety
- Passed
- GitHub stars
- 113
Unproven: rated by static analysis only, not yet compared head-to-head.
Not launch-quality. It is graded C with a clean safety verdict, but our quality filters exclude it: it looks like a template or a stub that was never filled in. So it is not in our launch-quality set, the skills our MCP server searches and recommends. How launch-quality is decided
This rating describes the version of the repository we crawled; it may have changed since, so go by its current files.
Our review
- Architecture
- 92 / 100
- Maturity
- Structured: ships references or scripts
- Security scan
- No issues found
- License
- Not declared. Check the repository before reusing it.
- Adoption
- Adopted by 0 other repositories, in 0 collections
Not checked yet
- Category is a classifier prediction; no model has read this skill yet
- Not judged on the rubric yet (not a contender in its category)
- No blind task eval yet
- Scope (portable / vendor / repo-internal) not assessed; only the top of each category is read for scope
- Sibling files (scripts, references) not fetched; security scan covers SKILL.md only
Skillspace indexes and rates this skill; it does not host or endorse it. Run third-party skills at your own risk.