av/skills · Archived
autoresearch
Runs autonomous keep/discard experiments on a codebase to optimize a single metric for a fixed duration, in the style of karpathy/autoresearch. Use when the…
Stronger alternatives
This repository is archived — consider an actively maintained alternative.
Use when the user specifies a task and a duration, and the work should be done iteratively by s…
19 installsSystematically explore and test any software project (CLI, API, Backend, Library, etc.) to find…
19 installsDeep learning framework development with tinygrad - a minimal tensor library with autograd, JIT…
19 installsComprehensive guide for setting up and running local LLMs using Harbor. Use when user wants to …
18 installsSimilar popular skills
Related neighbors and high-traction skills in the same topics — useful to compare before installing.
Autonomous iterative experimentation loop for any programming task. Guides the user through def…
3.3K installsAutonomous iteration loop: modify, verify, keep/discard against any metric
2.3K installsOrchestrates end-to-end autonomous AI research projects using a two-loop architecture. The inne…
759 installsAutonomous experiment loop that optimizes any file by a measurable metric. Inspired by Karpathy…
597 installsRun a bounded, source-grounded research loop, draft a cited dossier, and optionally propose a s…
472 installsStateful single-mission improvement loop with strict evaluator contract, markdown decision logs…
399 installsAlso in this package
Other skills from av/skills · top by installs.
npx skills add https://github.com/av/skills
More details
Agent compatibility
Declared targets from SKILL.md / docs. Unmarked agents are not listed — the skill may still install via the CLI.
Repository health
master
History
- First seen on skills.sh
- First recorded snapshot · 3 installs