Huashu Markdown Publishing Pipeline
alchaincyf/huashu-md-html
Converts files and web pages into clean Markdown, then turns Markdown into polished HTML, Word, PDF and EPUB using four templates.
Convert documents to PDF via a typst-based pipeline. An agent skill from OpenMinis/MinisSkills.
Install PDF Converter
$ npx skills add OpenMinis/MinisSkills --skill pdf-converter -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install OpenMinis/MinisSkills pdf-converter --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/OpenMinis/MinisSkills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/pdf-converter .claude/skills/pdf-converter && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "pdf-converter" agent skill from https://github.com/OpenMinis/MinisSkills/tree/main/pdf-converter into .claude/skills/pdf-converter/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "pdf-converter", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/OpenMinis/MinisSkills/tree/main/pdf-converterType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add OpenMinis/MinisSkills --skill pdf-converter -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install OpenMinis/MinisSkills pdf-converter --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/OpenMinis/MinisSkills.git skills-src && mkdir -p .agents/skills && cp -r skills-src/pdf-converter .agents/skills/pdf-converter && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "pdf-converter" agent skill from https://github.com/OpenMinis/MinisSkills/tree/main/pdf-converter into .agents/skills/pdf-converter/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "pdf-converter", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add OpenMinis/MinisSkills --skill pdf-converter -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install OpenMinis/MinisSkills pdf-converter --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/OpenMinis/MinisSkills.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/pdf-converter .cursor/skills/pdf-converter && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "pdf-converter" agent skill from https://github.com/OpenMinis/MinisSkills/tree/main/pdf-converter into .cursor/skills/pdf-converter/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "pdf-converter", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/OpenMinis/MinisSkills.git --path pdf-converter--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add OpenMinis/MinisSkills --skill pdf-converter -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install OpenMinis/MinisSkills pdf-converter --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/OpenMinis/MinisSkills.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/pdf-converter .gemini/skills/pdf-converter && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "pdf-converter" agent skill from https://github.com/OpenMinis/MinisSkills/tree/main/pdf-converter into .gemini/skills/pdf-converter/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "pdf-converter", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install OpenMinis/MinisSkills pdf-converterInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add OpenMinis/MinisSkills --skill pdf-converter -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/OpenMinis/MinisSkills.git skills-src && mkdir -p .github/skills && cp -r skills-src/pdf-converter .github/skills/pdf-converter && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "pdf-converter" agent skill from https://github.com/OpenMinis/MinisSkills/tree/main/pdf-converter into .github/skills/pdf-converter/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "pdf-converter", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add OpenMinis/MinisSkills --skill pdf-converter -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install OpenMinis/MinisSkills pdf-converter --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/OpenMinis/MinisSkills.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/pdf-converter .opencode/skills/pdf-converter && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "pdf-converter" agent skill from https://github.com/OpenMinis/MinisSkills/tree/main/pdf-converter into .opencode/skills/pdf-converter/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "pdf-converter", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
pdf-converter- GitHub stars
- 444
- Token cost
- ~2.1k tokens
- SKILL.md length
- 765 words
- Files
- 7 (incl. scripts, assets)
- Skills in repo
- 49
- Repo updated
- First seen
- Licence
- MIT
At a glance
Convert documents to PDF via a typst-based pipeline. An agent skill from OpenMinis/MinisSkills.
- Works in 3 steps: Prerequisites (self-checked on every run) → Run the conversion → Verify the output
- The user asks to convert to PDF
- SKILL.md covers When to Use This Skill, Workflow, Performance and Output Formatting (amber theme), plus 6 more sections
- Runs Python scripts from its folder; calls python3, pandoc and apk
What it does
PDF Converter is an agent skill from OpenMinis/MinisSkills. Convert documents to PDF via a typst-based pipeline. Supports Markdown, HTML, plain text, images, and any pandoc-supported format. Use this skill whenever the user asks to "convert to PDF", "generate a PDF", "export as PDF", "turn X into a PDF", or says "转PDF" / "生成PDF" / "导出PDF". Also covers merging multiple images into one PDF.
Its SKILL.md is about 2.1k tokens, which your agent loads only when the skill is triggered. The skill folder holds 9 other files, including scripts and assets (for example `evals/evals.json`, `evals/pdf-format-test.md` and `scripts/to_pdf.py`). Compatibility notes: Python 3, pandoc, typst, py3-pillow; Alpine (iSH) / Termux (Android) / Debian
It sits in Documents & Office, covering PDF and Document parsing. It works with Pandoc. The repository describes itself as: Skills collection for Minis. The licence is MIT.
When your agent uses it
- The user asks to convert to PDF
- Turn X into a PDF
- Says 转PDF / 生成PDF / 导出PDF
Example prompts
- “convert to PDF”
- “generate a PDF”
- “export as PDF”
- “/pdf-converter”
Requirements
- Python 3
- Docker
- Compatibility (from SKILL.md): Python 3, pandoc, typst, py3-pillow; Alpine (iSH) / Termux (Android) / Debian
Workflow steps
3 steps, taken from the step headings in SKILL.md.
What it can do on your machine
Read from SKILL.md and the folder at commit ae8c5db. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
Ships 1 file in scripts/ (Python), which the agent can run.
Shell commands in SKILL.md call:
python3pandocapkapt
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Compatibility
Python 3, pandoc, typst, py3-pillow; Alpine (iSH) / Termux (Android) / Debian
From compatibility in the SKILL.md frontmatter.
Context cost
PDF Converter loads about 2.1k tokens when it runs. Until then it costs about 86 tokens; SKILL.md has 765 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.
SKILL.md
The full file from OpenMinis/MinisSkills at commit ae8c5db, republished under its MIT licence (© OpenMinis). 765 words, ~2,052 tokens.
Download SKILL.mdSave it as
.claude/skills/pdf-converter/SKILL.md (or your agent's skills folder). This skill also uses 6 other files; get the full folder from GitHub.- name
- pdf-converter
- description
- Convert documents to PDF via a typst-based pipeline. Supports Markdown, HTML, plain text, images, and any pandoc-supported format. Use this skill whenever the user asks to "convert to PDF", "generate a PDF", "export as PDF", "turn X into a PDF", or says "转PDF" / "生成PDF" / "导出PDF". Also covers merging multiple images into one PDF.
- compatibility
- Python 3, pandoc, typst, py3-pillow; Alpine (iSH) / Termux (Android) / Debian
pdf-converter
Convert documents to PDF with proper CJK rendering, half-width digits, and emoji support. Uses a typst-based pipeline that compiles markup directly to PDF in ~5 s per conversion for a typical 10-page document.
When to Use This Skill
Use this skill when the user needs to:
- Convert Markdown (
.md) to PDF preserving tables, code blocks, emoji, and Chinese text - Convert HTML (
.htm,.html) to PDF - Convert plain text (
.txt) to PDF - Convert images (
.png/.jpg/.jpeg/.gif/.bmp/.webp) to PDF, including multi-image merge into one PDF - Convert any pandoc-supported format (
.rst,.org,.latex, etc.) to PDF
Workflow
Step 1 — Prerequisites (self-checked on every run)
The script verifies pandoc + typst are on PATH (and PIL for the
image-merge path). If anything is missing, it prints platform-specific install
commands and exits non-zero — no silent pandoc/typst failure later.
| Platform | Install |
|---|---|
| Alpine (iSH / Docker) | apk add pandoc typst py3-pillow font-wqy-zenhei font-dejavu font-noto-emoji |
| Termux (Android) | pkg install pandoc typst python-pillow font-wqy-zenhei font-dejavu noto-color-emoji |
| Debian / Ubuntu | apt install pandoc typst python3-pillow fonts-wqy-zenhei fonts-dejavu fonts-noto-color-emoji |
The font directory is auto-detected from candidate paths (/usr/share/fonts,
$PREFIX/share/fonts, /usr/local/share/fonts).
Step 2 — Run the conversion
Format is detected by the file extension:
# Markdown → PDF (formatting, emoji, Chinese, half-width digits, amber theme)
python3 scripts/to_pdf.py doc.md -o out.pdf
# HTML → PDF
python3 scripts/to_pdf.py page.html -o out.pdf
# Plain text → PDF (file stem used as title unless --title given)
python3 scripts/to_pdf.py notes.txt -o out.pdf --title "My Notes"
# Merge images into one PDF (one page per image)
python3 scripts/to_pdf.py img1.jpg img2.png -o merged.pdf
# Any pandoc-supported format (.rst/.org/.latex…) → PDF
python3 scripts/to_pdf.py doc.rst -o out.pdfStep 3 — Verify the output
ls -la out.pdfOn success the script prints ✅ PDF generated: <path> and exits 0. On failure
it prints a ❌-prefixed diagnostic to stderr and exits non-zero.
Performance
pandoc (input → typst markup) ~1-2 s
emoji SVG prefetch (parallel) ~0 s warm cache, ~30 s first-run for ~90 emoji
typst compile (typst → PDF) ~1-3 s for a 10-page document
─────────────────────────────────────────
total ~5 s warm cacheOn iOS (iSH, emulated x86) expect a 5–10× slowdown; for very large documents or first-run emoji downloads, run in the background to avoid iOS killing the app:
nohup python3 scripts/to_pdf.py big.md -o big.pdf > /tmp/pdf.log 2>&1 &Output Formatting (amber theme)
- Headings: h1 with amber underline (
#D97706), h1–h4 hierarchy - Tables: amber header (white bold text) + zebra stripes + thin grid borders, spans full content width
- Code blocks: light gray background (
#f2f3f5) + DejaVu Sans Mono + top gray bar - Blockquotes: amber left bar + light orange background (
#fef7ed) - Emoji: Twemoji SVG vector images, baseline-aligned with CJK text
- Footer: centered page number
How It Works
pandoc (MD/HTML/… → typst) → [emoji → SVG, table-width fix] → typst compile (→ PDF)| Component | Role |
|---|---|
| pandoc | Converts MD / HTML / reST / org / latex → typst markup |
| typst | Rust binary; compiles typst markup → PDF with native font fallback |
| Twemoji SVG | Emoji → vector images; CDN download + local cache |
| PIL | Image merging (lazy-imported; image-only mode skips pandoc/typst entirely) |
Font Strategy
| Character type | Font | Handling |
|---|---|---|
| ASCII (digits / letters) | DejaVu Sans | typst native fallback — half-width glyphs |
| Chinese | WenQuanYi Zen Hei | typst native fallback |
| Emoji | Twemoji SVG | CDN download → typst image() embed |
Configuration (environment variables)
| Variable | Default | Purpose |
|---|---|---|
EMOJI_CDN_BASE | unset | Override the Twemoji CDN with a single mirror URL (corporate proxy, ghproxy, air-gapped cache). When unset, a GitHub raw → jsDelivr → unpkg fallback chain is used. |
PDF_CONVERTER_WORKERS | 8 on Termux, 4 elsewhere | Concurrency for SVG prefetch. iSH defaults lower because emulated x86 has tight fd / memory limits. |
EMOJI_SVG_TIMEOUT | 15 | Per-request timeout in seconds for SVG downloads. Raise on very slow networks; lower on fast reliable ones. |
File Structure
pdf-converter/
├── SKILL.md
├── .gitignore
├── assets/
│ ├── template.typ # typst amber-theme template (committed)
│ └── emoji_cache/ # Twemoji SVG cache (gitignored, created at runtime)
├── scripts/
│ └── to_pdf.py # main script (pandoc + typst + SVG emoji)
└── evals/
├── evals.json # test cases
├── pdf-format-test.md # comprehensive format test document
└── pdf-format-test.pdf # expected output reference (10 pages, ~275 KB)Show full SKILL.md (307 more words)Show less
Error Handling
| Condition | Behavior |
|---|---|
| Missing input file | Python IOError / pandoc error, exit non-zero |
Missing pandoc / typst (text mode) | Self-check prints install hints, exit 1 |
Missing PIL (image mode) | Self-check prints install hint, exit 1 |
| pandoc parse error | stderr ❌ pandoc: <msg>, exit 1 |
| typst compile error | stderr ❌ typst: <msg>, exit 1 |
| typst compile timeout | default 120 s; stderr error, exit 1 |
| Emoji SVG download fails on all mirrors | Falls back to Noto Color Emoji bitmap font; stderr warning, conversion continues |
Testing
Verify the install (and any dependency change) using the bundled format-test document, then sanity-check against the bundled reference PDF:
python3 scripts/to_pdf.py evals/pdf-format-test.md -o /tmp/test.pdf
pdfinfo /tmp/test.pdf | grep Pages # expect: Pages: 10
ls -la /tmp/test.pdf # expect: ~200-350 KBCheck visually: amber table headers at full width, SVG emoji rendered (not
tofu boxes), half-width digits inside CJK paragraphs, all sections present.
Compare against evals/pdf-format-test.pdf (generated from the same source).
Key Implementation Notes
- Table header height: a show rule replacing cells with plain
text()drops the cell'sinset; useblock(inset: ...)instead to preserve padding. - Table width: pandoc emits
columns: Nfor narrow tables → rewritten to1frcolumns so tables span full content width. - Emoji alignment:
box(image(...), baseline: 5%)aligns the image bottom with the CJK text baseline. - Emoji detection:
U+2600-27BFuses a precise frozenset of 116 Twemoji-provided codepoints (not the full range — symbols like ☐☒★♔♪ aren't Twemoji and would 404);U+1F300-1FAFFuses the full range. - Parallel SVG prefetch: unique emoji sequences are collected, then missing SVGs are batch-downloaded concurrently before the replacement pass — first-run (empty cache) ~30 s instead of >180 s serial.
- CDN fallback: each SVG tries GitHub raw → jsDelivr → unpkg (or the single URL in
EMOJI_CDN_BASE); a 404 or timeout on one mirror transparently retries the next, with a per-request timeout (EMOJI_SVG_TIMEOUT, default 15 s) to prevent hung connections from stalling the prefetch batch. - Mode-aware dependency check: image-merge mode requires only PIL; text/markup mode requires pandoc + typst. Image-only users aren't forced to install the heavy pandoc/typst toolchain.
© OpenMinis, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
SKILL.md and 6 other files (scripts, assets) in pdf-converter of OpenMinis/MinisSkills.
- SKILL.md
- .gitignore
- assets/template.typ
- evals/evals.json
- evals/pdf-format-test.md
- evals/pdf-format-test.pdf
- scripts/to_pdf.py
Open the folder on GitHubat commit ae8c5db
Compare with similar skills
PDF Converter next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| PDF Converter this skillOpenMinis/MinisSkills | 444 | — | ~2.1k | Automated safety check: Pass | MIT | |
| Huashu Markdown Publishing Pipelinealchaincyf/huashu-md-html | 907 | — | ~4.8k | Automated safety check: Pass | MIT | |
| Doc To Markdowndaymade/claude-code-skills | 1.4k | — | ~2.5k | Automated safety check: Pass | MIT | |
| PDF Processing GuideshareAI-lab/learn-claude-code | 78k | 5 repos | ~646 | Automated safety check: Pass | MIT | |
| MarkitdownImCa0/just-laws | 782 | 14 repos | ~3.2k | Automated safety check: Notes | MIT | |
| Harness Book Best Practicewquguru/harness-books | 3.2k | — | ~4.1k | Automated safety check: Pass | None |
Similar skills
Doc To Markdown
daymade/claude-code-skills
Converts DOCX/PDF/PPTX and saved HTML/HTM to high-quality Markdown with automatic post-processing.
PDF Processing Guide
shareAI-lab/learn-claude-code
Gives the agent command-line and Python recipes for reading, creating, merging and splitting PDF files, plus tips for large and scanned documents.
Markitdown
ImCa0/just-laws
Convert files and office documents to Markdown. An agent skill from ImCa0/just-laws.
Harness Book Best Practice
wquguru/harness-books
Best practices for working on the Harness books repo. An agent skill from wquguru/harness-books.
DOCX Toolkit
XiaomiMiMo/MiMo-Code
Produces, edits and reads Microsoft Word files through python-docx and lxml, with a decision table for picking the lightest workflow for a given task.
More from OpenMinis/MinisSkills
All 49 skills in this repoAndroid UI Automation
OpenMinis/MinisSkills
Automate Android apps that have no public API or web version by driving the UI layer through the Accessibility Service.
Codex On Ish
OpenMinis/MinisSkills
Install and run OpenAI Codex CLI inside the Minis/iSH Alpine sandbox on iOS, where rustls TLS and async sockets are broken.
Evidence Chain Builder
OpenMinis/MinisSkills
Score a claim against the evidence behind it. An agent skill from OpenMinis/MinisSkills.
Hyperframes CLI
OpenMinis/MinisSkills
HyperFrames CLI and Minis rendering. An agent skill from OpenMinis/MinisSkills.
Whenpeak
OpenMinis/MinisSkills
Predict when a person's brain works best from their sleep, using the WhenPeak performance-intelligence API, and turn it into concrete scheduling advice.
Openstreetmap Marker
OpenMinis/MinisSkills
Generate a mobile-first, immersive, Amap(Gaode)-style custom landmark marker HTML map for travel itinerary planning, place showcasing, location sharing, etc.
Related
Works with
Categories
Questions about PDF Converter
What does PDF Converter do?
Convert documents to PDF via a typst-based pipeline. An agent skill from OpenMinis/MinisSkills. PDF Converter is an agent skill from OpenMinis/MinisSkills. Convert documents to PDF via a typst-based pipeline.
When should I use PDF Converter?
PDF Converter fits situations like: the user asks to convert to PDF; turn X into a PDF; says 转PDF / 生成PDF / 导出PDF.
How do I install PDF Converter in Claude Code?
Run `npx skills add OpenMinis/MinisSkills --skill pdf-converter -a claude-code`. Or copy the skill folder (pdf-converter in OpenMinis/MinisSkills) into .claude/skills/pdf-converter in your project. Claude Code loads it when a task matches its description.
How do I install PDF Converter in Codex?
Run `npx skills add OpenMinis/MinisSkills --skill pdf-converter -a codex`. Or copy the skill folder (pdf-converter in OpenMinis/MinisSkills) into .agents/skills/pdf-converter in your project. Codex loads it when a task matches its description.
Can I use PDF Converter in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add OpenMinis/MinisSkills --skill pdf-converter -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/pdf-converter, .gemini/skills/pdf-converter, .github/skills/pdf-converter and .opencode/skills/pdf-converter in your project.
What does PDF Converter need to run?
Going by SKILL.md and its folder, PDF Converter needs Python for the scripts in its folder and the command-line tools its instructions call (python3, pandoc, apk and apt). Our summary lists: Python 3; Docker. Compatibility (from SKILL.md): Python 3, pandoc, typst, py3-pillow; Alpine (iSH) / Termux (Android) / Debian.
Does PDF Converter access the network?
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Is PDF Converter safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.
What licence does PDF Converter use?
PDF Converter is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does PDF Converter use?
About 2.1k tokens (SKILL.md is roughly 8.2k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
What are the alternatives to PDF Converter?
Skills that share tags, products or a category with PDF Converter: Huashu Markdown Publishing Pipeline (alchaincyf/huashu-md-html, 907 stars), Doc To Markdown (daymade/claude-code-skills, 1.4k stars), PDF Processing Guide (shareAI-lab/learn-claude-code, 78k stars) and Markitdown (ImCa0/just-laws, 782 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains PDF Converter?
OpenMinis (a GitHub organization) maintains it in OpenMinis/MinisSkills, which has 444 GitHub stars. The repository holds 49 skills in this directory. The repository was last updated on October 7, 2026.
Source: OpenMinis/MinisSkills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.