Clinical Data Extractor
PassAudited by ClawScan on May 1, 2026.
Overview
This instruction-only skill is coherent for extracting clinical trial data, but it will browse user-provided URLs/PDFs and save generated Markdown files locally.
Before installing, confirm the output directory you want, use only URLs/PDFs you are comfortable having the agent inspect, and verify any optional external tools or manual GitHub install steps before running them.
Findings (4)
Artifact-based informational review of SKILL.md, metadata, install specs, static scan signals, and capability signals. ClawScan does not execute the skill or run runtime probes.
The agent may visit external clinical-data pages and capture their content as part of the requested extraction.
The skill directs the agent to automate a browser against user-provided URLs and capture page contents/screenshots. This is expected for webpage extraction, but users should be aware it loads external sites.
browser action=open targetUrl=<provided-url> ... browser action=snapshot format=markdown ... browser action=screenshot fullPage=true
Use this skill only with URLs and PDFs you intend the agent to inspect, and review generated output before relying on it.
If PDF extraction tools are missing, a user may need to install or run local commands.
The skill documents optional local CLI tools and installation commands for PDF extraction. These are user-directed and purpose-aligned, not automatic execution.
pdftotext (poppler-utils) ... sudo apt-get install poppler-utils ... brew install poppler ... nano-pdf --file <path-to-pdf> --action read
Install PDF tools only from trusted package managers and avoid running installation commands unless you understand the system impact.
Manual installation from a moving GitHub branch could install content different from the reviewed registry artifact.
The README offers a manual install path from an external GitHub repository without pinning a commit. This is optional documentation, but users should verify the source if installing that way.
git clone https://github.com/abinww/clinical-data-extractor.git ~/.openclaw/skills/clinical-data-extractor
Prefer the registry-installed artifact or verify the repository and commit before manually cloning it.
Generated reports may be saved somewhere other than the location a user expects from one of the documents.
The README states a default output path that differs from the SKILL.md configuration excerpt, which states `~/.openclaw/workspace`. This could confuse users about where files are saved.
输出路径：默认 `~/obsidian/AI`
Check and, if needed, edit the Configuration section before using the skill so the output path is explicit.