idea2experiment
Skill9 starsChanged 5 months agoNo licenceView on GitHub
Turn a rough AI/ML research idea, an existing or starter codebase, available data, and compute into a complete executable and auditable experiment program. Use when Codex must inspect a repository and datasets, reproduce baselines, prove the training path with deterministic and tiny-set overfit gates, run model- and data-scaling studies, design module/strategy and key-parameter experiments, diagnose unexpected results, re-plan the experiment DAG, and return measured evidence with exact run provenance. Triggers include idea2experiment, automate experiments, run all experiments, scale experiment, data scaling, ablation implementation, hyperparameter study, experiment debugging, 自动做实验, 自动跑完实验, 模型scale, 数据scale, 过拟合小数据, and 实验不符合预期.
- Deletes or force-pushes
In this repository22 other files it gives its agents.
- image-to-editable-ppt-skill/AGENTS.mdAGENTS.md
- ai-literature-surveySkill
- autodebugSkill
- autorunSkill
- paper-readSkill
- db-analyzeSkill
- frontend-designSkill
- full-autoSkill
- generate-docsSkill
- gpt-imageSkill
- idea2paperSkill
- impeccableSkill
- latex-float-layoutSkill
- mysql-motiondataSkill
- nature-paper-cardSkill
- paperjurySkill
- query-motion-databaseSkill
- research-paper-writingSkill
- reverse-engineer-anythingSkill
- sync-ceph-dataSkill
- thesis-reviewSkill
- track-ai-papersSkill
The file
Show its rules and text
We split this skill into the rules it gives an agent
18 rules. About 0 are common, 16 are distinctive, and 2 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈16
Distinctive · estimate
This author's own choices. Worth a look.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
No licence file, so all rights are reserved — read it at the source. We count its rules but don't quote them. Read them on GitHub.
≈ “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.
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.