Upsonic experiment_management

Name: experiment_management
Author: upsonic

Experiment Management Skill

install

source · Clone the upstream repo

git clone https://github.com/Upsonic/Upsonic

Claude Code · Install into ~/.claude/skills/

T=$(mktemp -d) && git clone --depth=1 https://github.com/Upsonic/Upsonic "$T" && mkdir -p ~/.claude/skills && cp -r "$T/prebuilt_autonomous_agents/applied_scientist/skills/experiment_management" ~/.claude/skills/upsonic-upsonic-experiment-management && rm -rf "$T"

manifest: prebuilt_autonomous_agents/applied_scientist/skills/experiment_management/SKILL.md

source content

Experiment Management Skill

Purpose

Set up and manage the experiment folder structure. This is Phase 0 — it runs before any analysis begins. All bookkeeping files are JSON (never markdown).

When to Use

At the very start of a new experiment
When updating
```
experiments.json
```
or
```
comparison.json
```
after an experiment completes

Input

Parameter	Type	Description
research_name	string	The experiment name as given by the caller. Use it verbatim — do not rename it, do not re-derive it from the paper title.
research_paper	path	Path to the PDF paper
current_notebook	path	Path to the current baseline .ipynb
current_data	path	Path to the current dataset (file or directory)
experiments_directory	path	The directory (inside the workspace) where experiment folders live (e.g. `./experiments` ).

Actions

Setup (start of experiment)

Create experiment directory:

experiments/{research_name}/

Copy files (NEVER move, NEVER modify originals):

cp {current_notebook} experiments/{research_name}/current.ipynb
cp -r {current_data}  experiments/{research_name}/current_data/
cp {research_paper}   experiments/{research_name}/research.pdf

current_data

is a code-based download (e.g.

fetch_ucirepo(id=2)

), leave

current_data/

empty and record the download spec in

log.json

's metadata.

Create

log.json

with the starting skeleton:

{
  "name": "{research_name}",
  "metadata": {
    "date": "YYYY-MM-DD",
    "original_notebook": "{current_notebook}",
    "original_data":     "{current_data}",
    "research_paper":    "{research_paper}"
  },
  "phases": []
}

Phases append entries here as they finish; never overwrite earlier entries.

Register in

experiments/experiments.json

If the file does not exist, create it with
```
{"experiments": []}
```
.

Append a new entry with

status: "in_progress"

{
  "name": "{research_name}",
  "date": "YYYY-MM-DD",
  "status": "in_progress",
  "paper": "{paper_title}",
  "baseline_model": null,
  "new_method": null,
  "verdict": null,
  "key_metric": null,
  "path": "experiments/{research_name}/"
}

Create initial
```
progress.json
```
(see
```
skills/progress/SKILL.md
```
for schema) with:
- ```
status: "RUNNING"
```
- all phases listed, all
```
pending
```
  , Phase 0 marked
```
current
```
- ```
started_at
```
  and
```
updated_at
```
  set to now (UTC ISO-8601)

Finalize (end of experiment)

Update the experiment entry in

experiments.json

with final

status

verdict

, and

key_metric

(see

skills/evaluate/SKILL.md

Append a row to
```
experiments/comparison.json
```
.
- If the file does not exist, create it with
```
{"experiments": []}
```
  .

Output

```
experiments/{research_name}/
```
directory with copied files
```
experiments/{research_name}/log.json
```
initialized

experiments/{research_name}/progress.json

initialized

```
experiments/experiments.json
```
updated