Organize Experiments

Documents

organize-experiments

Organize Experiments is an Agent Skill for documents published in the marin-community/marin repository on GitHub: a SKILL.md instruction file an AI agent can load to do this task.

Curate the experiment report index at docs/reports/index.md.

View on GitHub ↗

QUICK START

How to use this skill

Bring this guide into your coding agent with a prompt tailored to the tool you use.

Open your project in Codex.
Copy and paste the prompt below.
Review files and risks before approving any action.

Prompt to paste

Inspect the Agent Skill at https://github.com/marin-community/marin/blob/HEAD/.agents/skills/organize-experiments/SKILL.md and all supporting files. Report provenance, permissions, scripts, dependencies, and security risks. Propose an exact installation into .agents/skills/organize-experiments, but wait for my approval before writing files or running scripts.

Copying this prompt does not install or run the skill. Review third-party files before use.

Skill: Organize Experiment Reports

Overview

Curate docs/reports/index.md after new experiment issues are harvested: fold fresh entries into the right sections, refresh links, and leave ## Uncategorized empty.

Prerequisites

Local checkout of the marin repository with write access.
Ability to run uv commands.
Familiarity with the existing experiment categories in docs/reports/index.md.

Guidelines for Humans

Standard Workflow

Run uv run scripts/pm/itemize_experiment_issues.py to append new experiments.
Open the diff for docs/reports/index.md and identify the additions in ## Uncategorized.
For each experiment:
- Match it to an existing section (e.g., Training and Performance, Data Experiments).
- Merge any new resources (WandB links, Data Browser URLs) into the canonical entry in that section.
- Remove the placeholder entry from ## Uncategorized.
If an experiment truly does not fit, leave it under ## Uncategorized and add a note explaining why.
Proofread for duplicate bullets, broken Markdown, and consistent title casing.
Commit the curated report, open a PR, or, if an interactive agent, signal to the user to look.

Link Hygiene

Prefer direct https://wandb.ai/... links when available; keep legacy api.wandb.ai links only if the direct share link does not exist.
Use https://marin.community Data Browser URLs when the script surfaces them.
Preserve access tokens embedded in links.

Rules for Agents

NEVER delete existing sections or conclusions.
Keep badge styling consistent: [![#NNN](https://img.shields.io/...)] next to each experiment title.
When merging new content, update the canonical entry instead of duplicating it.
Leave ## Uncategorized empty whenever possible; a single placeholder sentence is fine.
Ask for guidance if an experiment does not map cleanly to known categories.

Validation

rg "^- " docs/reports/index.md to confirm bullets exist only under curated sections, not under ## Uncategorized.
Re-run uv run scripts/pm/itemize_experiment_issues.py if unsure that all experiments were captured.
Optional: markdownlint docs/reports/index.md to catch formatting drift.