Content Alchemy
v1.0.0Turn articles, web pages, PDFs, and excerpts into structured notes, key insights, practical actions, and reusable takeaways.
⭐ 0· 81·0 current·0 all-time
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Benign
medium confidencePurpose & Capability
The name/description (transform articles, web pages, PDFs into structured notes) matches the included scripts and instructions. Requesting python3, pdftotext and pdfinfo is appropriate for a PDF/text extraction and processing workflow.
Instruction Scope
SKILL.md limits behavior to three routes (plain_text, web_url, pdf_file) and instructs running the local Python scripts. The scripts read PDFs, plan/maintain session state, extract text, and save results. They accept user-supplied file paths and save session artifacts under ~/.content-alchemy by default — expected for persistent PDF sessions. No instructions ask the agent to read unrelated system config or secret env vars. Caveat: some files were truncated in the report (notably the full content of the web extractor and remaining scripts), so those specific scripts should be inspected to confirm they only fetch the requested URLs and do not phone home or exfiltrate data.
Install Mechanism
There is no install spec (instruction-only execution of bundled scripts). That minimizes supply-chain risk because nothing is downloaded or executed from remote URLs during install. The runtime does call system binaries (pdftotext/pdfinfo) which are standard for PDF text extraction.
Credentials
The skill declares no required environment variables or credentials. It writes session files under a user-owned directory (~/.content-alchemy/sessions) and otherwise operates on user-supplied files/URLs — this is proportional to its stated functionality.
Persistence & Privilege
The skill is not flagged as always: true and does not request elevated privileges. It stores its own session artifacts (normal for a long-PDF workflow) and does not modify other skills or system-wide agent settings in the visible code.
Assessment
This skill appears coherent with its stated purpose: it uses python3 plus pdftotext/pdfinfo to extract text and contains scripts to plan/read/record PDF sessions and to extract web text. Before installing or running it, review the full contents of the omitted/truncated files (especially extract_web_text.py and any other network-handling code) to confirm they only fetch the URLs you provide and do not transmit data to unknown endpoints. Be aware the scripts will read user-supplied file paths and write session artifacts (default: ~/.content-alchemy/sessions). Avoid pointing the skill at sensitive system files and confirm pdftotext/pdfinfo are the official system packages on your machine. If you need higher assurance, request the full listing of the omitted scripts for a complete audit.Like a lobster shell, security has layers — review code before you run it.
latestvk97awee0bgxy2xzn5tr4hettwd83m6ws
License
MIT-0
Free to use, modify, and redistribute. No attribution required.
Runtime requirements
🧪 Clawdis
OSLinux · macOS · Windows
Binspython3, pdftotext, pdfinfo