agentleFS
45ck45ck/open-genome-agent/.claude/skills/annotate-variants/SKILL.md

annotate-variants

Skill4 starsChanged 7 months agoMITView on GitHub

Annotate variants with deterministic tools such as VEP and preserve exact

The file

We split this skill into the rules it gives an agent

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

  • 0

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Run the selected annotation tool with explicit version capture.

    line 38
  2. Distinctive:

    Keep tool failures visible and non-silent.

    line 41
  3. Distinctive:

    Do not collapse multiple transcripts into a single unqualified claim.

    line 46

≈ “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

Annotate variants

Annotate variants with deterministic tools such as VEP and preserve exact tool versions and command provenance. Use after normalization and before prioritization.

When to use

  • gene/transcript consequences are needed
  • you need a structured annotation file for later ranking

Do not use when

  • you only need simple file QC

Expected outputs

  • annotations.tsv
  • tool_versions.json
  • commands.jsonl

Goal

Produce a structured annotation layer that downstream agents can rank and report.

Procedure

  1. Confirm build and normalization state first.
  2. Run the selected annotation tool with explicit version capture.
  3. Preserve raw command lines and output paths in commands.jsonl.
  4. Emit a stable tabular or JSON annotation artifact.
  5. Keep tool failures visible and non-silent.

Guardrails

  • Annotation is not interpretation.
  • Do not collapse multiple transcripts into a single unqualified claim.
  • Record exact tool and cache versions when available.

Escalate when

  • required annotation caches are missing
  • reference build does not match tool expectations
  • command output suggests truncation or partial failure

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.