agentleFS
Sign inStart free
Industrial-AI-Research-LabIndustrial-AI-Research-Lab/nir-agent-overlay/skills/experiment-issue/SKILL.md

experiment-issue

Skill0 starsChanged 45 days agoMITView on GitHub

Open a GitHub issue for one experiment from the Experiment form and add it to the project board. Use when the student says "заведи эксперимент", "создай issue на гипотезу", "open an experiment issue".

The file

We split this skill into the rules it gives an agent

3 rules. About 0 are common, 2 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Ask for what is missing; never invent it.

    line 10
  2. Very specific:

    Create the issue with the form's fields as the body and the title exp: <short hypothesis>:

    line 11
  3. Distinctive:

    When the student names the checkpoint issue, add the new issue as its sub-issue (GitHub UI or the sub-issues API).

    line 21

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

experiment-issue

One hypothesis, one issue, nested under the checkpoint's parent issue.

  1. Collect: the hypothesis (one sentence), the setup (data, baseline, metric), the expected result. Ask for what is missing; never invent it.

  2. Create the issue with the form's fields as the body and the title exp: <short hypothesis>:

    gh issue create --title "exp: <short hypothesis>" \
  --body "$(printf '## Hypothesis\n%s\n\n## Setup\n%s\n\n## Expected result\n%s\n' "<hypothesis>" "<setup>" "<expected>")" \
  --project "<board title>"

    --project takes the board title. If it fails with a scope error, run gh auth refresh -s project once and retry.

  3. When the student names the checkpoint issue, add the new issue as its sub-issue (GitHub UI or the sub-issues API).
  4. Report the issue number: it goes into the PR as Closes #N and into the MLflow run note.
  5. At the end of the experiment the student closes the issue with the outcome and its interpretation; a negative result is closed as completed, not as not planned.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free