wps-doc-scraper

An agent skill by daymade, from daymade/claude-code-skills. Tags: documents, download, image, markdown, scraping.

What it does

Faithfully archive public WPS/KDocs/金山文档 links, especially embedded ProcessOn .pof mind maps and canvases, as raw source data, original SVG/PNG, and Markdown. Use when a user gives a kdocs.cn or wps.processon.com link and asks to scrape, save, download, 扒下来, 归档, or 转 Markdown without logging in or saving the document to an account.

Install

With the skills CLI, which installs into Claude Code, Codex, Cursor and other agents:

npx skills add daymade/claude-code-skills --skill wps-doc-scraper

Or copy the skill folder into Claude Code's skills directory by hand (~/.claude/skills for every project, or .claude/skills inside one):

git clone --depth 1 https://github.com/daymade/claude-code-skills
cp -r claude-code-skills/wps-doc-scraper ~/.claude/skills/wps-doc-scraper

Safety box score

Grade B, low risk: 18 of 100 risk points, rated 2026-10-19. The grade rates what the skill and its scripts can reach on the machine of whoever installs it, across eight categories from shell execution to secrets access. How the score works.

This skill archives public WPS/KDocs/ProcessOn documents by downloading public metadata/API JSON and rendering local SVG/PNG/Markdown artifacts. The main risks are local command execution through the bundled render scripts and network access to public WPS/ProcessOn endpoints; it does not ask for logins, secrets, or privileged system changes.

Category levels, from 0 (none) to 3 (high)
Category	Level	Why
Code & shell execution	2 (moderate)	Bundled scripts execute local commands and native tools, including `subprocess.run(...)`, `qlmanage`, and `magick`/`convert`, so using the skill runs code on the machine.
Network access	1 (low)	It fetches public data from `https://drive.kdocs.cn/api/v5/links/...` and `https://wps.processon.com/wpsapi/diagrams/view/api` with `urllib.request.urlopen`, but only for public archive retrieval.
Filesystem reach	1 (low)	The scripts write JSON/Markdown/SVG/PNG into the chosen `--output-dir` and can delete an existing derived temp directory via `shutil.rmtree(keep_dir)`, but they do not target system paths by default.
Secrets & credentials	0 (none)	The files explicitly say not to log in and do not read credential stores, browser sessions, `.env` files, or tokens.
Privilege & persistence	0 (none)	There is no sudo, service installation, shell startup edit, or global system configuration in the shipped files.
Instruction hijack surface	0 (none)	The docs set boundaries like "Never log in" and "Never bypass CAPTCHAs"; they do not instruct the agent to ignore its rules or fetch hidden instructions.
Irreversible actions	0 (none)	The skill only archives and renders local copies; it does not publish, post, deploy, pay, or mutate remote documents.
Transparency	1 (low)	The repository itself is readable Python/Markdown, but final PNG rendering depends on external macOS Quick Look and ImageMagick behavior at runtime, which is not bundled here.

Before installing

Check `scripts/render_svg_tiles.py` and confirm you are okay with it invoking `qlmanage` and ImageMagick locally.
Test on a scratch public link with `--output-dir` pointing to an empty temp folder first.
If you use `--keep-temp`, note it can delete an existing `*.tiles` directory next to the output file.
Do not point the output path at any sensitive directory or shell config location.

Rated 2026-10-19 by an automated review of 8 files from the skill's repository.

Source

Repository: daymade/claude-code-skills (all skills from this repository)
Path: wps-doc-scraper/SKILL.md
Branch: main
Updated: 2026-09-20

twitter-reader — Fetch Twitter/X post content including long-form Articles with full images and metadata.
doc-to-markdown — Converts DOCX/PDF/PPTX to high-quality Markdown with automatic post-processing.
download-gemini-images — Download, export, save, or package images from a Google Gemini conversation/chat/app page.
feishu-doc-scraper — Extract Feishu (Lark) Docs, Wiki pages/collections, spreadsheets.
llm-icon-finder — Finding and accessing AI/LLM model brand icons from lobe-icons library.
pdf-creator — Convert markdown files to professional PDF documents with proper Chinese font support, theme system, and visual self-check.