experiment-pipeline
Skill1 starsChanged 14 days agoMITView on GitHub
Break an experiment doc into small vertical slices (stages, phases, experiments) with goals, metrics, status and dependencies, tracked in docs/experiments-pipeline. Use when the experiment contract is settled and the user wants a run plan, wants to know which experiments can run in parallel, or wants to update experiment status.
1 other project uses a version of this.
Adopted by
Most recently taken up by
- EvoScientist/EvoSkillstheir own version, first seen Sep 30, 2026
Other versions1 project uses a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 1
- EvoScientist/EvoSkills★ 481same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
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
- exp-reviewSkill
- hypothesysSkill
- let-it-ripSkill
- 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
3 rules. About 0 are common, 3 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈3
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 31
Result: When status is completed, write here a short text about the result of experiment.
- Distinctive: line 35
When the workflow order is completed, ask the user:
- Distinctive: line 39
Should any experiments be merged or split further?
≈ “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
Experiments Workflow
Based on the experiment doc, create the experiment pipeline. To do this, analyze the Experiment Stories to see which experiments will run and in what order, and check whether any of them can run in parallel with another.
The main idea is to break the experiments into small slices and create a file to help track the pipeline workflow.
Then show the workflow order to the user, broken down as a numbered list in this pattern:
<vertical-slice-rules>
### Experiment Stage <number>
<description of the main idea of the stage>Phase <number>
<description of the main idea of the phase>Experiment <number>
title: short descriptive name Goals: Experiment goals and the metric that will be checked. Status: Control tag for the experiment; tell the user whether it is not-implemented, waiting-to-run, running, or completed. Blocked by: Which other experiments (if any) must complete first. Result: When status is completed, write here a short text about the result of experiment.
</vertical-slice-rules>When the workflow order is completed, ask the user:
- Does the granularity feel right? (too coarse / too fine)
- Are the blocking edges correct: does each experiment depend only on experiments that genuinely gate it?
- Should any experiments be merged or split further?
Then, if the user approves, write this document to docs/experiments-pipeline/<name.md>
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.