ClawHub

Crispr Screen Analyzer

v0.1.0

Process CRISPR screening data to identify essential genes and hit candidates. Performs quality control, statistical analysis (RRA), and hit calling for poole...

⭐ 0· 99·0 current·0 all-time
byAIpoch@aipoch-ai
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/description match the provided code and SKILL.md: the package performs QC, log fold-change, a simplified RRA-like analysis, and hit calling on sgRNA count matrices. Required resources (none) are appropriate for a local analysis tool.
✓
Instruction Scope
SKILL.md and the example usage instruct the agent to load counts and a samplesheet and call methods from scripts/main.py. The runtime instructions and code only reference user-supplied files and produce local CSV output; there are no directives to read unrelated system files, access credentials, or send data externally.
✓
Install Mechanism
No install spec or remote downloads are present. The bundled requirements.txt lists standard Python packages (numpy, pandas, scipy) consistent with the code; nothing is pulled from untrusted URLs or installed silently.
✓
Credentials
The skill requests no environment variables, no credentials, and no config paths. The code only needs the user-provided count matrix and sample sheet; requested permissions are minimal and proportional.
✓
Persistence & Privilege
always is false and the skill does not request persistent system-wide changes. It does not modify other skills or agent configuration. Autonomous invocation is allowed (platform default) but not combined with other concerning privileges.
Assessment
This skill appears to do what it claims: local numeric analysis of CRISPR count data with no network exfiltration or secret access. Before installing or running: (1) review the included scripts/main.py yourself or run it in a sandbox/VM to confirm behavior; (2) ensure numpy/pandas/scipy are installed in a controlled environment; (3) validate the statistical approach (RRA/FDR are simplified in this implementation) before using results for publication or critical decisions; and (4) avoid sending sensitive or proprietary datasets to unknown external services—this skill operates locally, so keep data files local when running.

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

latestvk975vmwkaw6aey54gk755cys2s8356bt

License

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

Comments