ml-autoresearch
90 / 100 · Low risk
Fine to try.
Use when the user wants an autonomous ML research loop that does more than blindly try changes. After every training run the agent analyses what actually happened inside the model — gradients, activations, embeddings, errors, data — and grounds the next change in that evidence. A `<literature>` on/off dial adds scientific-literature grounding: off behaves as a pure analysis-first loop; on searches papers, grades the evidence, and implements only what prior work supports. One change per run; loo…
What this skill can do
Changes files outside its own folder
Install
Paste this into your terminal. It downloads exactly the version we scanned, not whatever is newest.
if [ -e ~/.agents/skills/'ml-autoresearch' ] || [ -L ~/.agents/skills/'ml-autoresearch' ]; then echo 'A skill folder named ml-autoresearch already exists — not replacing it' >&2; false; else d=$(mktemp -d) && git clone --quiet --filter=blob:none --no-checkout 'https://github.com/gaasher/Agent-Loop-Skills' "$d" && git -C "$d" checkout --quiet 'f1169e6db0b0f8a83ced3a18562b7c57e14a748a' -- 'loops/ml-autoresearch' && mkdir -p ~/.agents/skills && cp -R "$d"/'loops/ml-autoresearch' ~/.agents/skills/'ml-autoresearch' && rm -rf "$d"; fi
Codex reads ~/.agents/skills directly. For Claude Code, Cursor, Copilot, Gemini CLI, Antigravity or OpenCode, also link it. For Claude Code: ln -s ~/.agents/skills/'ml-autoresearch' ~/.claude/skills/'ml-autoresearch' (other agents: ~/.cursor/skills, ~/.copilot/skills, ~/.gemini/skills, ~/.gemini/config/skills, ~/.config/opencode/skills). Or install through the finder skill, which does both.
Badge for your README
[](https://zalavijaysinh.github.io/skilltrust/repos/gaasher/Agent-Loop-Skills/)
Score history
| Date | Version | Score |
|---|---|---|
| 2026-11-07 | f1169e6 | 100 |