ClawHub

ACMG Variant Classifier

v1.0.0

Standard workflow for ACMG/AMP germline small-variant classification — collect evidence, assign criteria, detect conflicts, and produce a review-ready classi...

⭐ 0· 65·0 current·0 all-time
by@alex4xu
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
VirusTotalVirusTotal
Benign
View report →
OpenClawOpenClaw
Benign
high confidence
✓
Purpose & Capability
Name and description (ACMG variant classification) match the included materials: templates, SOP, test cases, and a small classifier script. Nothing requested (no env vars, no binaries) is out of scope for this purpose.
✓
Instruction Scope
SKILL.md gives a narrow, guided interview workflow and describes exactly which fields to collect and how to apply combination logic. Instructions do not ask for unrelated files, system state, or external endpoints; they explicitly state this is decision support only.
✓
Install Mechanism
No install spec — instruction-only with an included Python script. There are no downloads, external packages, or extract/install steps. The script is local and self-contained.
✓
Credentials
The skill requires no environment variables, credentials, or config paths. The inputs it asks the user to provide (variant, phenotype, segregation, literature, etc.) are appropriate for ACMG classification.
✓
Persistence & Privilege
Skill is not always-enabled and does not request persistent or elevated privileges. It does not modify other skills or system-wide settings.
Assessment
This appears to be a straightforward decision-support skill: the included Python classifier only applies combination rules to counts (no network calls or secret access). Before installing, confirm you are comfortable providing genetic/clinical data to the agent (these are sensitive), ensure local privacy/PHI policies are followed, and understand the skill is explicitly for provisional review only — final clinical classification requires expert manual review and possible ClinGen VCEP adjustments. If you will deploy this in a regulated environment, have a domain expert review the SOP and the classifier logic and confirm any gene-specific rule changes.

Like a lobster shell, security has layers — review code before you run it.

latestvk9717rqmw7cdw69pqny02y4exx83twtb

License

MIT-0
Free to use, modify, and redistribute. No attribution required.
Termshttps://spdx.org/licenses/MIT-0.html

Comments