agentleFS
45ck45ck/open-genome-agent/.claude/skills/ingest-vcf/SKILL.md

ingest-vcf

Skill4 starsChanged 7 months agoMITView on GitHub

Validate and inventory VCF or BCF input files before downstream analysis.

The file

We split this skill into the rules it gives an agent

5 rules. About 0 are common, 3 are distinctive, and 2 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.

  • 2

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Create the first trustworthy manifest for a supplied VCF/BCF input.

    line 32
  2. Very specific:

    Check for the expected index (.tbi or .csi) where relevant.

    line 37
  3. Very specific:

    Create a minimal sample_summary.json with unresolved fields set to null.

    line 40
  4. Distinctive:

    Never rewrite the source file in place.

    line 44
  5. Distinctive:

    Do not guess the reference build from chromosome names alone if the evidence is weak.

    line 45

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 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.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Ingest VCF

Validate and inventory VCF or BCF input files before downstream analysis. Use when a user provides a genome variant file or asks what data is inside it.

When to use

  • a VCF, VCF.GZ, BCF, TBI, or CSI file arrives
  • you need sample names, header metadata, or file hashes

Do not use when

  • the workflow starts from FASTQ only

Expected outputs

  • run_manifest.json
  • sample_summary.json

Goal

Create the first trustworthy manifest for a supplied VCF/BCF input.

Procedure

  1. Identify the file kind: vcf, vcf.gz, or bcf.
  2. Check for the expected index (.tbi or .csi) where relevant.
  3. Extract sample names and header metadata without modifying the raw input.
  4. Hash the input files and record them in run_manifest.json.
  5. Create a minimal sample_summary.json with unresolved fields set to null.

Guardrails

  • Never rewrite the source file in place.
  • Do not guess the reference build from chromosome names alone if the evidence is weak.
  • Multi-sample files require explicit sample-selection logic.

Escalate when

  • the file has no samples
  • the header is malformed
  • the file is compressed but unindexed

References

See references/README.md for durable notes and scripts/ for deterministic helpers.

Download now (ZIP)

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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.