omics-skills
AGENTS.md9 starsChanged 4 months agoMITView on GitHub
An agent is a Markdown system prompt. It sets a role, the skills to use, and a workflow decision tree. Claude Code or Codex loads the prompt; the agent runs nothing by itself. When the right agent is not obvious, ask the router. --agent limits the answer to one agent:
Where files are headingNew AGENTS.md files have more rules about keeping secrets out of the code, and fewer about code style.
Of the AGENTS.md files we read, the 31,700 first seen in the last six months, against the older ones: the kind of rule that gained most share, and the kind that lost most. About files like this in general, not this one, and an estimate, since a kind is a pattern in the words.
In this repository35 other files it gives its agents.
- AGENTS.mdAGENTS.md
- ai-scientist-evaluatorSkill
- arxiv-searchSkill
- beautiful-data-vizSkill
- bio-annotationSkill
- bio-assembly-qcSkill
- bio-binning-qcSkill
- bio-fasta-database-curatorSkill
- bio-foundation-housekeepingSkill
- bio-gene-callingSkill
- bioinformatics-projectSkill
- bio-interdomain-hgtSkill
- bio-logicSkill
- bio-phylogenomicsSkill
- bio-prefect-dask-nextflowSkill
- bio-protein-clustering-pangenomeSkill
- bio-reads-qc-mappingSkill
- biorxiv-searchSkill
- bio-stats-ml-reportingSkill
- bio-structure-annotationSkill
- bio-viromicsSkill
- bio-workflow-methods-docwriterSkill
- crossref-lookupSkill
- csag-extractionSkill
- exploratory-data-analysisSkill
- manuscript-review-councilSkill
- notebooksSkill
- pdf-to-mdSkill
- plotly-dashboard-skillSkill
- polars-dovmedSkill
- proposal-reviewSkill
- public-db-lookupSkill
- scientific-impact-assessmentSkill
- scientific-writingSkill
- tracking-taxonomy-updatesSkill
The file
We split this agents.md into the rules it gives an agent
1 rule. About 0 are common, 0 are distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈0
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
- Very specific: line 12
When the right agent is not obvious, ask the router.
≈ “Common” is an estimate: at least 1 in 5 of the 40,246 AGENTS.md 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
Agents
An agent is a Markdown system prompt. It sets a role, the skills to use, and a workflow decision tree. Claude Code or Codex loads the prompt; the agent runs nothing by itself.
| Agent | Use it for | Common first skills |
omics-scientist | Reads, assemblies, MAGs, annotation, taxonomy, phylogenomics, viral discovery, public database records, project setup and biological interpretation. | bioinformatics-project, bio-reads-qc-mapping, bio-assembly-qc, tracking-taxonomy-updates, bio-annotation |
literature-expert | Literature and preprint search, DOI and citation metadata, citation impact, and claim and evidence extraction. | polars-dovmed, arxiv-search, biorxiv-search, crossref-lookup, csag-extraction |
science-writer | Manuscripts, revisions and response letters, proposal review, methods sections, multi-reviewer evaluation and argument graphs. | scientific-writing, manuscript-review-council, proposal-review, bio-workflow-methods-docwriter, csag-extraction |
dataviz-artist | Data inspection, notebooks, exploratory plots, figures and dashboards, greyscale first. | exploratory-data-analysis, notebooks, beautiful-data-viz, plotly-dashboard-skill |
When the right agent is not obvious, ask the router. --agent limits the answer to one agent:
python3 scripts/skill_index.py route --agent omics-scientist "annotate viral contigs and compare relatives"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.