NIH Biosketch Builder
v1.0.0Generate NIH Biosketch documents compliant with the 2022 OMB-approved.
⭐ 0· 45·0 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
high confidencePurpose & Capability
The name/description match the delivered artifacts: SKILL.md documents how to run scripts/main.py and the repository contains a Python implementation that builds DOCX biosketches and (optionally) fetches publication data from NCBI PubMed. The declared dependencies (python-docx and requests) are proportionate to that purpose.
Instruction Scope
Runtime instructions are narrowly scoped to validating inputs, running the provided script, and producing a DOCX. The SKILL.md does not instruct reading unrelated system files or exfiltrating data. The only external network access described is to the NCBI eutils PubMed API, which is appropriate for the 'auto-import-pubmed' feature.
Install Mechanism
There is no automated install spec (instruction-only skill with an included script). Dependency installation is via normal pip packages (python-docx/requests) referenced in SKILL.md/requirements.txt, which is standard and expected.
Credentials
The skill requests no environment variables, no credentials, and no config paths. Network access to a public NIH API is the only external interaction and is justified by the PubMed import functionality.
Persistence & Privilege
The skill is not always-enabled and does not request elevated or persistent privileges. It does not modify other skills or agent configuration per the provided files.
Assessment
This package appears coherent and focused, but remember it includes executable Python code that will run on your machine and may access the public NCBI eutils API if you use the PubMed import feature. Before running: (1) inspect scripts/main.py to confirm there are no unexpected network endpoints or data-collection behaviors, (2) run python -m py_compile scripts/main.py and try --help, (3) run first in a sandbox or isolated environment if you are unsure, and (4) be aware that any input JSON you provide will be read and the output DOCX will be written locally (no credentials are requested). If you need absolute assurance, review the full script or run it on a disposable VM.Like a lobster shell, security has layers — review code before you run it.
latestvk9787y95g210jh7d9d5ew2z21n83xm3x
License
MIT-0
Free to use, modify, and redistribute. No attribution required.