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

query-variants

Skill4 starsChanged 7 months agoMITView on GitHub

Answer targeted questions about genes, rsIDs, coordinates, or variant

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:

    Prefer exact local evidence over speculative interpretation.

    line 41
  2. Distinctive:

    If nothing matches, say so directly.

    line 43
  3. Distinctive:

    Do not turn a simple query into a full report unless asked.

    line 48
  4. Distinctive:

    If a query depends on annotation that is not yet available, state that dependency.

    line 49

≈ “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

Query variants

Answer targeted questions about genes, rsIDs, coordinates, or variant panels from local genome files. Use for focused exploration before full reporting.

When to use

  • the user asks about a gene, variant, or coordinate range
  • you need quick local evidence without running a full pipeline

Do not use when

  • a full end-to-end report is required

Expected outputs

  • query_results.tsv
  • query_notes.md

Goal

Answer targeted local questions quickly and with file-level provenance.

Procedure

  1. Convert the user request into a precise local query:
    • gene
    • rsID
    • coordinate interval
    • panel list
  2. Prefer exact local evidence over speculative interpretation.
  3. Return raw hits, file locations, and concise caveats.
  4. If nothing matches, say so directly.

Guardrails

  • Keep scope narrow.
  • Do not turn a simple query into a full report unless asked.
  • If a query depends on annotation that is not yet available, state that dependency.

Output contract

Emit query results plus a short note describing how the query was executed.

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.