Microbiome Diversity Reporter
v1.0.0Interpret Alpha and Beta diversity metrics from 16S rRNA sequencing results.
⭐ 0· 52·0 current·0 all-time
byAIpoch@aipoch-ai
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Benign
medium confidencePurpose & Capability
Name/description (interpret alpha/beta diversity from 16S data) match the included SKILL.md and the Python script's visible functionality (alpha and beta calculators, rarefaction, PCoA). Requested libraries (numpy, pandas, scipy, scikit-bio, plotting libs) are appropriate for this domain. The lack of required env vars, binaries, or config paths is proportionate.
Instruction Scope
Runtime instructions restrict the agent to validating inputs and running the packaged script on local OTU/metadata TSV files, producing local reports in HTML/JSON/Markdown. SKILL.md does not instruct reading unrelated system files, exporting secrets, or contacting external endpoints.
Install Mechanism
No install spec is provided (instruction-only skill with an included script). Dependencies are declared in requirements.txt and are common scientific packages. There are no network download URLs or extraction steps in the metadata that would write arbitrary code to disk beyond the packaged files.
Credentials
No environment variables, credentials, or config paths are required. The script uses only local file inputs (OTU/metadata) and standard libraries; requested env/credential access would have been disproportionate but none are present.
Persistence & Privilege
The skill does not request permanent presence (always:false) and does not declare modifications to other skills or system-wide settings. It appears to be a self-contained, on-demand analysis tool.
Assessment
Overall this package looks coherent for running local microbiome diversity analyses. Before installing or running: (1) review the full scripts/main.py yourself (or run python -m py_compile scripts/main.py) to confirm no hidden network calls or file access, (2) install dependencies in an isolated virtual environment, (3) run initial tests on synthetic or non-sensitive data, and (4) prefer executing in a sandboxed environment if the skill origin is unknown (no homepage/author verification). If you need higher assurance, ask the publisher for a link to source or a provenance record before using with sensitive data.Like a lobster shell, security has layers — review code before you run it.
latestvk976f0jk2fzsp1fwyx5n7w00rx83qaek
License
MIT-0
Free to use, modify, and redistribute. No attribution required.