← All skills
arize-experiment
82 / 100 · Low risk
Fine to try.
By github/awesome-copilot (GitHub) · other · 41,001 stars · scanned at commit 227949a
Creates, runs, and analyzes Arize experiments for evaluating and comparing model performance. Covers experiment CRUD, exporting runs, comparing results, and evaluation workflows using the ax CLI. Use when the user mentions create experiment, run experiment, compare models, model performance, evaluate AI, experiment results, benchmark, A/B test models, or measure accuracy.
Works with any agent that supports SKILL.md skills.
What this skill can do
Runs commands on your computer
This is disclosed by the author in the skill's SKILL.md or README.
Found in 17 places.
Show 14 more
- skills/arize-experiment/SKILL.md, line 144
ax experiments create --name "gpt-4o-baseline" --dataset DATASET_NAME --space SPACE --file runs.json - skills/arize-experiment/SKILL.md, line 164
echo '[{"example_id": "ex_001", "output": "Paris"}]' | ax experiments create --name "my-experiment" --dataset DATASET_NAME --space SPACE --file - - skills/arize-experiment/SKILL.md, line 184
ax experiments delete NAME_OR_ID - skills/arize-experiment/SKILL.md, line 238
ax datasets list --space SPACE - skills/arize-experiment/SKILL.md, line 243
ax datasets export DATASET_NAME --space SPACE - skills/arize-experiment/SKILL.md, line 248
ax datasets export DATASET_NAME --space SPACE --stdout | python3 infer.py > runs.json - skills/arize-experiment/SKILL.md, line 320
python3 -c "import json; runs=json.load(open('runs.json')); print(f'{len(runs)} runs'); print(json.dumps(runs[0], indent=2))" - skills/arize-experiment/SKILL.md, line 325
ax experiments create --name "gpt-4o-baseline" --dataset DATASET_NAME --space SPACE --file runs.json - skills/arize-experiment/SKILL.md, line 333
ax experiments export "experiment-a" --dataset DATASET_NAME --space SPACE --stdout > a.json - skills/arize-experiment/SKILL.md, line 339
jq '[.[] | .evaluations.correctness.score] | add / length' a.json - skills/arize-experiment/SKILL.md, line 346
jq -s '.[0] as $a | .[1][] | . as $run | - skills/arize-experiment/SKILL.md, line 356
jq '[.[] | .evaluations.correctness.label] | group_by(.) | map({label: .[0], count: length})' a.json - skills/arize-experiment/SKILL.md, line 360
jq -s ' - skills/arize-experiment/SKILL.md, line 380
ax experiments export EXPERIMENT_NAME --dataset DATASET_NAME --space SPACE --stdout | jq 'length'
Downloads and installs other software
The author does not mention this.
Found in 4 places.
Show 1 more
Install
Paste this into your terminal. It downloads exactly the version we scanned, not whatever is newest.
if [ -e ~/.agents/skills/'arize-experiment' ] || [ -L ~/.agents/skills/'arize-experiment' ]; then echo 'A skill folder named arize-experiment already exists — not replacing it' >&2; false; else d=$(mktemp -d) && git clone --quiet --filter=blob:none --no-checkout 'https://github.com/github/awesome-copilot' "$d" && git -C "$d" checkout --quiet '227949a7542a55d2155c00e7cdb998d9a0fee4f3' -- 'skills/arize-experiment' && mkdir -p ~/.agents/skills && cp -R "$d"/'skills/arize-experiment' ~/.agents/skills/'arize-experiment' && rm -rf "$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/'arize-experiment' ~/.claude/skills/'arize-experiment' (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
The badge for github/awesome-copilot shows the score of its lowest-scoring skill.
[](https://zalavijaysinh.github.io/skilltrust/repos/github/awesome-copilot/)
Score history
| Date | Version | Score |
|---|
| 2026-11-10 | 227949a | 82 |
| 2026-11-08 | 797337f | 82 |
| 2026-11-07 | 797337f | 82 |