let-it-rip
Skill1 starsChanged 13 days agoMITView on GitHub
Implement or fix an experiment in a Jupyter notebook from its experiment doc and pipeline, expectation-first: run every cell, review the result with /exp-review, then commit. Use when the experiment is planned and it is time to write the code.
- Reads credentials
In this repository15 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- llms.txtllms.txt
- critic-reviewSkill
- developing-data-science-notebooksSkill
- expectation-driven-scienceSkill
- experiment-graphSkill
- experiment-pipelineSkill
- exp-reviewSkill
- hypothesysSkill
- literature-researchSkill
- mad-science-setupSkill
- notify-gchat-human-waitSkill
- to-articleSkill
- to-docSkill
- what-i-doSkill
The file
We split this skill into the rules it gives an agent
4 rules. About 0 are common, 4 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈4
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 10
Run this implementation or fix in a sub-agent.
- Distinctive: line 14
If you are using the experiment pipeline, update the doc at the end of each experiment.
- Distinctive: line 22
Create the .env with uv if it does not exist, and use it to run.
- Distinctive: line 28
Commit your work to the current branch.
≈ “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.
Files
Run this implementation or fix in a sub-agent.
Implement the work described by the user in the docs at docs/experiments-doc/<related_name.md>, with the pipeline workflow in docs/experiments-pipeline/<related_name.md>. The code must satisfy the requirements described in both documents, when both exist.
If you are using the experiment pipeline, update the doc at the end of each experiment.
Workflow
- Load the development-principle skills below if needed:
- expectation-driven-science: Development guide for the data-science process.
- developing-data-science-notebooks: Development rules for writing usable, higher-quality notebooks in a data-science context.
- Create the .env with uv if it does not exist, and use it to run.
- For each cell you write, run it to make sure it works.
- Once finished, before returning to the main agent, call the Skill tool with "exp-review" to review the work, and fix everything that is needed.
- Commit your work to the current branch.
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
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.