agentleFS
45ck45ck/open-genome-agent/.claude/skills/detect-build-normalize/SKILL.md

detect-build-normalize

Skill4 starsChanged 7 months agoMITView on GitHub

Detect the reference build and create a normalized derived copy without

The file

We split this skill into the rules it gives an agent

4 rules. About 0 are common, 4 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈4

    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
  1. Distinctive:

    If build is still uncertain, mark it ambiguous rather than guessing.

    line 38
  2. Distinctive:

    Create a derived normalized file in a run-specific output directory.

    line 39
  3. Distinctive:

    Do not overwrite source inputs.

    line 46
  4. Distinctive:

    If a liftover or reference swap would be needed, stop and surface that requirement.

    line 47

≈ “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

Detect build and normalize

Detect the reference build and create a normalized derived copy without touching the raw input. Use before annotation or cross-tool comparison.

When to use

  • build is unknown or ambiguous
  • contig naming style differs across tools
  • annotation expects normalized variants

Do not use when

  • the input is already validated and normalized for the selected toolchain

Expected outputs

  • derived/normalized.vcf.gz
  • normalization_notes.json

Goal

Resolve build and representation issues before downstream tools disagree.

Procedure

  1. Inspect contig style (chr1 vs 1) and obvious build indicators.
  2. If build is still uncertain, mark it ambiguous rather than guessing.
  3. Create a derived normalized file in a run-specific output directory.
  4. Preserve raw input hashes and link the derived file back to them.
  5. Record every normalization step in machine-readable notes.

Guardrails

  • Derived files belong under runs/<run_id>/derived/.
  • Do not overwrite source inputs.
  • If a liftover or reference swap would be needed, stop and surface that requirement.

Escalate when

  • the build is ambiguous
  • contig naming is mixed
  • normalization would drop or alter records unexpectedly

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.