ClawHub

paper-report

v1.0.3

Convert academic PDF papers into structured Chinese reading reports with original figures. Use when the user asks to summarize, read, analyze, or create a re...

⭐ 0· 87·0 current·0 all-time
byxu.li@nuaalixu
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
ℹ
Purpose & Capability
The skill’s name/description match the included scripts (PDF→PNG, figure crop) and HTML template. Minor inconsistencies: the SKILL.md uses {PYTHON} and a curl command but the registry metadata does not declare required binaries (python3 / curl) — this is an operational omission rather than malicious. Otherwise the requested capabilities are appropriate for the stated purpose.
ℹ
Instruction Scope
Instructions stay within scope: they read local PDF files or download PDFs from arXiv, render pages to images, crop figure regions, and generate a self-contained HTML report. No instructions direct data to external endpoints other than arxiv.org. Minor practical issues: examples in the documentation mix human-friendly 1-indexed page descriptions and the crop script expects 0-indexed page numbers (possible off-by-one confusion); SKILL.md assumes an agent 'Read' tool to view files which is expected for agent workflows.
✓
Install Mechanism
No install spec (instruction-only). The only runtime dependency is PyMuPDF, which SKILL.md tells the user to pip install; code files are local and small. No external downloads or obscure installers are used.
✓
Credentials
The skill does not request any environment variables, secrets, or credentials. It operates on local files and optionally downloads PDFs from arXiv — proportional to its function.
✓
Persistence & Privilege
Skill is user-invocable, not always-enabled, and does not request elevated/system-wide persistence or modify other skills. It reads/writes only under the declared workspace paths.
Assessment
This skill appears to do what it says, but check a few practical points before use: (1) Ensure python3 and curl are available on the host and install PyMuPDF as instructed. (2) Be careful with page indexing: the crop script expects 0-based page numbers while some examples use human 1-based counts — test on a small PDF first. (3) The skill will write files under {workspace}/paper-report; review those outputs before sharing. (4) Downloading PDFs from arXiv is fine for research copies, but confirm copyright/usage terms for other sources. If you need the skill to run in an environment without curl or with custom Python paths, adapt the commands or declare those binaries before invoking the skill.

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

latestvk973sqm5fk49dgtyfj3z5pmb4h83f1r2

License

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

Comments