agr
agr is an Execution & autonomous loops skill for AI agents, published by JoaquinMulet in the Artificial-General-Research repository on GitHub. Skillspace rates agr C (73/100) and it passed the safety scan; the rating is based on static analysis only.
AGR: Artificial General Research — autonomous iterative optimization framework for Claude Code. Generalizes Karpathy's autoresearch to any measurable problem with variance-aware acceptance, correctness verification, and fresh-context-per-iteration (Ralph Loop). Use when setting up autoresearch, creating optimization loops, or autonomous research. Triggers on: autoresearch, AGR, auto research, optimization loop, auto optimize, artificial general research.
- Grade
- C
- Quality
- 73 / 100
- Safety
- Passed
- GitHub stars
- 29
Unproven: rated by static analysis only, not yet compared head-to-head.
Our two independent classifiers differ on this skill's category, so treat the placement as provisional.
This rating describes the version of the repository we crawled; it may have changed since, so go by its current files.
Our review
- Architecture
- 97 / 100
- Maturity
- Structured: ships references or scripts
- Security scan
- No issues found
- License
- MIT
- Adoption
- Adopted by 0 other repositories, in 0 collections
Not checked 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.