annotate-variants
Skill4 starsChanged 7 months agoMITView on GitHub
Annotate variants with deterministic tools such as VEP and preserve exact
In this repository21 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- detect-build-normalizeSkill
- generate-reportSkill
- ingest-vcfSkill
- nextflow-runnerSkill
- pharmacogenomicsSkill
- polygenic-riskSkill
- prioritize-findingsSkill
- query-variantsSkill
- setup-workstationSkill
- annotate-variantsSkill
- detect-build-normalizeSkill
- generate-reportSkill
- ingest-vcfSkill
- nextflow-runnerSkill
- pharmacogenomicsSkill
- polygenic-riskSkill
- prioritize-findingsSkill
- query-variantsSkill
- setup-workstationSkill
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
- Distinctive: line 29
Run the selected annotation tool with explicit version capture.
- Distinctive: line 32
Keep tool failures visible and non-silent.
- Distinctive: line 37
Do not collapse multiple transcripts into a single unqualified claim.
≈ “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.
Files
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.tsvtool_versions.jsoncommands.jsonl
Goal
Produce a structured annotation layer that downstream agents can rank and report.
Procedure
- Confirm build and normalization state first.
- Run the selected annotation tool with explicit version capture.
- Preserve raw command lines and output paths in
commands.jsonl. - Emit a stable tabular or JSON annotation artifact.
- 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.
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.

