prioritize-findings
Skill4 starsChanged 7 months agoMITView on GitHub
Convert raw annotations into ranked, evidence-linked findings. Use after
In this repository21 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- annotate-variantsSkill
- detect-build-normalizeSkill
- generate-reportSkill
- ingest-vcfSkill
- nextflow-runnerSkill
- pharmacogenomicsSkill
- polygenic-riskSkill
- 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 35
Keep caveats adjacent to the finding instead of hiding them at the end.
- Distinctive: line 40
Do not let a finding through without evidence.
- Distinctive: line 41
Do not over-rank exploratory trait signals.
≈ “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
Prioritize findings
Convert raw annotations into ranked, evidence-linked findings. Use after annotation when building a structured report.
When to use
- annotations are complete and need triage
- a user wants a ranked output instead of raw tables
Do not use when
- annotation has not been completed
Expected outputs
findings.jsonevidence.jsonl
Goal
Turn raw annotations into ranked findings with confidence labels and evidence refs.
Procedure
- Group candidate findings by category.
- Assign one of the approved confidence labels:
verifiedstrongplausiblehypothesisunsupported
- Attach at least one evidence ref to every kept finding.
- Keep caveats adjacent to the finding instead of hiding them at the end.
- Flag anything high-impact for human review.
Guardrails
- Do not let a finding through without evidence.
- Do not over-rank exploratory trait signals.
- Separate deterministic QC findings from interpretation findings.
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.

