Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →brycewang-stanford/research-workflow-automation
Automate repetitive research tasks with pipelines, schedulers, and scripting
Passed 23 of 24 test cases with the skill, and 22 of 24 without it.
1 fixed22 passed either way1 still failing0 broke
Tokens, turns and time describe resource use, not a dollar price.
A test case the skill fixed. Same model, same prompt, with and without the skill.
We have multiple figure scripts like plot_main.py and plot_supplement.py that output corresponding PDF files. Rather than writing duplicate Makefile rules, how do we write a generic pattern rule using Makefile stem substitution?
| Checked | Without skill | With skill |
|---|---|---|
| The target pattern uses the percent symbol (%) wildcard. | Passed | Passed |
| The shell command references the stem variable to dynamically determine script names. | Missed | Passed |
The instructions your model reads when the skill loads.
A skill for automating repetitive research tasks using workflow managers, pipeline tools, and scripting. Covers data pipeline design, experiment tracking, automated reporting, and reproducible research workflows.
| Tool | Language | Best For | Complexity | License |
|---|---|---|---|---|
| Snakemake | Python | Bioinformatics, data pipelines | Medium | MIT |
| Nextflow | Groovy/DSL | Genomics, HPC | Medium | Apache 2.0 |
| Prefect | Python | Data engineering, ML | Medium | Apache 2.0 |
| Airflow | Python | Scheduled ETL pipelines | High | Apache 2.0 |
| Make | Makefile | Simple file-based pipelines | Low | GPL |
| DVC | YAML/CLI | ML experiment tracking | Low | Apache 2.0 |
# Snakefile for a research data pipeline
# Configuration
configfile: "config.yaml"
# Define the final outputs
rule all:
input:
"results/figures/main_figure.pdf",
"results/tables/summary_table.csv",
"results/manuscript_stats.json"
# Step 1: Download and preprocess data
rule download_data:
output:
"data/raw/{dataset}.csv"
params:
url = lambda wildcards: config["datasets"][wildcards.dataset]["url"]
shell:
"curl -L {params.url} -o {output}"
test cases passed, vs 22 / 24 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.