Agent skill

Pandoc Unicode Sanitize

Pre-process Markdown to replace non-ASCII characters before pandoc PDF conversion

Install Pandoc Unicode Sanitize

skills CLI

$ npx skills add HKUDS/OpenSpace --skill pandoc-unicode-sanitize -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI

$ gh skill install HKUDS/OpenSpace pandoc-unicode-sanitize --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy

$ git clone --depth 1 https://github.com/HKUDS/OpenSpace.git skills-src && mkdir -p .claude/skills && cp -r skills-src/benchmarks/gdpval/skills/pandoc-unicode-sanitize .claude/skills/pandoc-unicode-sanitize && rm -rf skills-src

Use ~/.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/

Paste into Claude Code

Install the "pandoc-unicode-sanitize" agent skill from https://github.com/HKUDS/OpenSpace/tree/main/benchmarks/gdpval/skills/pandoc-unicode-sanitize into .claude/skills/pandoc-unicode-sanitize/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "pandoc-unicode-sanitize", 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

$skill-installer install https://github.com/HKUDS/OpenSpace/tree/main/benchmarks/gdpval/skills/pandoc-unicode-sanitize

Type 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.

skills CLI

$ npx skills add HKUDS/OpenSpace --skill pandoc-unicode-sanitize -a codex

Project install goes to .agents/skills/; add -g for ~/.codex/skills/.

GitHub CLI

$ gh skill install HKUDS/OpenSpace pandoc-unicode-sanitize --agent codex

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/HKUDS/OpenSpace.git skills-src && mkdir -p .agents/skills && cp -r skills-src/benchmarks/gdpval/skills/pandoc-unicode-sanitize .agents/skills/pandoc-unicode-sanitize && rm -rf skills-src

Use ~/.agents/skills/ instead of .agents/skills for a personal install.

Codex skills documentation · loads skills from .agents/skills/

Paste into Codex

Install the "pandoc-unicode-sanitize" agent skill from https://github.com/HKUDS/OpenSpace/tree/main/benchmarks/gdpval/skills/pandoc-unicode-sanitize into .agents/skills/pandoc-unicode-sanitize/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "pandoc-unicode-sanitize", 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.

skills CLI

$ npx skills add HKUDS/OpenSpace --skill pandoc-unicode-sanitize -a cursor

Project install goes to .agents/skills/; add -g for ~/.cursor/skills/.

GitHub CLI

$ gh skill install HKUDS/OpenSpace pandoc-unicode-sanitize --agent cursor

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/HKUDS/OpenSpace.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/benchmarks/gdpval/skills/pandoc-unicode-sanitize .cursor/skills/pandoc-unicode-sanitize && rm -rf skills-src

Use ~/.cursor/skills/ instead of .cursor/skills for a personal install.

Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/

Paste into Cursor

Install the "pandoc-unicode-sanitize" agent skill from https://github.com/HKUDS/OpenSpace/tree/main/benchmarks/gdpval/skills/pandoc-unicode-sanitize into .cursor/skills/pandoc-unicode-sanitize/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "pandoc-unicode-sanitize", 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

$ gemini skills install https://github.com/HKUDS/OpenSpace.git --path benchmarks/gdpval/skills/pandoc-unicode-sanitize

--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.

skills CLI

$ npx skills add HKUDS/OpenSpace --skill pandoc-unicode-sanitize -a gemini-cli

Project install goes to .agents/skills/; add -g for ~/.gemini/skills/.

GitHub CLI

$ gh skill install HKUDS/OpenSpace pandoc-unicode-sanitize --agent gemini-cli

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/HKUDS/OpenSpace.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/benchmarks/gdpval/skills/pandoc-unicode-sanitize .gemini/skills/pandoc-unicode-sanitize && rm -rf skills-src

Use ~/.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/

Paste into Gemini CLI

Install the "pandoc-unicode-sanitize" agent skill from https://github.com/HKUDS/OpenSpace/tree/main/benchmarks/gdpval/skills/pandoc-unicode-sanitize into .gemini/skills/pandoc-unicode-sanitize/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "pandoc-unicode-sanitize", 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.

GitHub CLI

$ gh skill install HKUDS/OpenSpace pandoc-unicode-sanitize

Installs 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).

skills CLI

$ npx skills add HKUDS/OpenSpace --skill pandoc-unicode-sanitize -a github-copilot

Project install goes to .agents/skills/; add -g for ~/.copilot/skills/.

Manual copy

$ git clone --depth 1 https://github.com/HKUDS/OpenSpace.git skills-src && mkdir -p .github/skills && cp -r skills-src/benchmarks/gdpval/skills/pandoc-unicode-sanitize .github/skills/pandoc-unicode-sanitize && rm -rf skills-src

Use ~/.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/

Paste into GitHub Copilot

Install the "pandoc-unicode-sanitize" agent skill from https://github.com/HKUDS/OpenSpace/tree/main/benchmarks/gdpval/skills/pandoc-unicode-sanitize into .github/skills/pandoc-unicode-sanitize/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "pandoc-unicode-sanitize", 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.

skills CLI

$ npx skills add HKUDS/OpenSpace --skill pandoc-unicode-sanitize -a opencode

OpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.

GitHub CLI

$ gh skill install HKUDS/OpenSpace pandoc-unicode-sanitize --agent opencode

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/HKUDS/OpenSpace.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/benchmarks/gdpval/skills/pandoc-unicode-sanitize .opencode/skills/pandoc-unicode-sanitize && rm -rf skills-src

Use ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.

OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/

Paste into OpenCode

Install the "pandoc-unicode-sanitize" agent skill from https://github.com/HKUDS/OpenSpace/tree/main/benchmarks/gdpval/skills/pandoc-unicode-sanitize into .opencode/skills/pandoc-unicode-sanitize/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "pandoc-unicode-sanitize", 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: pandoc-unicode-sanitize
GitHub stars: 7.8k
Token cost: ~663 tokens
SKILL.md length: 207 words
Files: 2
Skills in repo: 199
Repo updated: Aug 12, 2026
First seen: Oct 7, 2026
Licence: MIT

At a glance

Pre-process Markdown to replace non-ASCII characters before pandoc PDF conversion

Works in 5 steps: Identify Problematic Characters → Create a Sed Substitution Script → Run Sanitization Before Pandoc → …
Tasks that involve PDF
SKILL.md covers Problem, Solution, Steps and Best Practices, plus 1 more section
Calls pandoc

What it does

Pandoc Unicode Sanitize is an agent skill from HKUDS/OpenSpace. Pre-process Markdown to replace non-ASCII characters before pandoc PDF conversion

Its SKILL.md is about 660 tokens, which your agent loads only when the skill is triggered. The skill folder holds 1 other file.

It sits in Documents & Office, covering PDF. It works with Pandoc and LaTeX. The repository describes itself as: "OpenSpace: The Skill Management Layer for AI Agents" -- https://open-space.cloud/. The licence is MIT.

When your agent uses it

Tasks that involve PDF

Example prompts

“/pandoc-unicode-sanitize”

Workflow steps

5 steps, taken from the step headings in SKILL.md.

Identify Problematic Characters
Create a Sed Substitution Script
Run Sanitization Before Pandoc
Alternative: Use iconv for Automatic Transliteration
Alternative: Use XeLaTeX or LuaLaTeX Engine

What it can do on your machine

Read from SKILL.md and the folder at commit 3827781. 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
Shell commands in SKILL.md call:
- pandoc
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.

Context cost

Pandoc Unicode Sanitize loads about 663 tokens when it runs. Until then it costs about 26 tokens; SKILL.md has 207 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it: ~26
When it runs · the whole SKILL.md, loaded when a task matches: ~663

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); files beside SKILL.md are not scanned.

SKILL.md

The full file from HKUDS/OpenSpace at commit 3827781, republished under its MIT licence (© HKUDS). 207 words, ~663 tokens.

Download SKILL.mdSave it as .claude/skills/pandoc-unicode-sanitize/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.

name: pandoc-unicode-sanitize
description: Pre-process Markdown to replace non-ASCII characters before pandoc PDF conversion

Pandoc Unicode Sanitization for PDF Conversion

Problem

LaTeX (used by pandoc for PDF output) may fail or produce errors when encountering non-ASCII Unicode characters like currency symbols (₹, €, £), special quotes, or other Unicode characters not supported by the default LaTeX engine.

Solution

Pre-process Markdown files to replace problematic Unicode characters with ASCII equivalents before running pandoc PDF conversion.

Steps

1. Identify Problematic Characters

Common problematic characters include:

Currency symbols: ₹, €, £, ¥
Special quotes: " " ' '
Arrows: →, ←, ↑, ↓
Bullets: •, ◦
Other symbols: ©, ®, ™, ±, ×, ÷, —, –

2. Create a Sed Substitution Script

Create a shell script for reusable sanitization:

bash

#!/bin/bash
# sanitize-for-pdf.sh

sed -e 's/₹/Rs/g' \
    -e 's/€/EUR/g' \
    -e 's/£/GBP/g' \
    -e 's/¥/JPY/g' \
    -e 's/"/"/g' \
    -e 's/"/"/g' \
    -e "s/'/'/g" \
    -e "s/'/'/g" \
    -e 's/→/->/g' \
    -e 's/←/<-/g' \
    -e 's/•/-/g' \
    -e 's/©/(c)/g' \
    -e 's/®/(R)/g' \
    -e 's/™/(TM)/g' \
    -e 's/±/+/ -/g' \
    -e 's/×/x/g' \
    -e 's/÷/\//g' \
    -e 's/—/--/g' \
    -e 's/–/-/g' \
    "$1"

3. Run Sanitization Before Pandoc

bash

# Using the script
./sanitize-for-pdf.sh input.md > sanitized.md
pandoc sanitized.md -o output.pdf

# Or inline
cat input.md | sed 's/₹/Rs/g; s/€/EUR/g; s/£/GBP/g' | pandoc -o output.pdf

4. Alternative: Use iconv for Automatic Transliteration

For broader Unicode coverage:

bash

iconv -f UTF-8 -t ASCII//TRANSLIT < input.md > sanitized.md
pandoc sanitized.md -o output.pdf

5. Alternative: Use XeLaTeX or LuaLaTeX Engine

If you want to preserve Unicode characters, use a Unicode-capable engine:

bash

pandoc input.md -o output.pdf --pdf-engine=xelatex
# or
pandoc input.md -o output.pdf --pdf-engine=lualatex

Best Practices

Sanitize files before conversion rather than debugging LaTeX errors after
Keep a mapping of your organization's common symbols and preferred replacements
Test with a small sample before processing large documents
Consider using XeLaTeX/LuaLaTeX if Unicode preservation is required
Document which characters cause issues in your specific environment

Common Error Signs

Look for these LaTeX errors that indicate Unicode issues:

Package inputenc Error: Unicode character ... not set up
LaTeX Error: Unicode character ... cannot be used with pdflatex
Missing or garbled characters in the output PDF

Files

SKILL.md and 1 other file in benchmarks/gdpval/skills/pandoc-unicode-sanitize of HKUDS/OpenSpace.

SKILL.md
.skill_id

Open the folder on GitHubat commit 3827781

Compare with similar skills

Pandoc Unicode Sanitize 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.

Pandoc Unicode Sanitize compared with similar skills
Skill	Stars	Used in	Tokens	Auto-check	Licence	Repo updated
Pandoc Unicode Sanitize this skillHKUDS/OpenSpace	7.8k	—	~663	Automated safety check: Pass	MIT	1 mo ago
Harness Book Best Practicewquguru/harness-books	3.2k	—	~4.1k	Automated safety check: Pass	None	5 mo ago
Pandic OfficeTeam-Commonly/commonly	1.4k	—	~642	Automated safety check: Pass	Apache-2.0	yesterday
Render PDF DocAperivue/medsci-skills	333	—	~2.1k	Automated safety check: Notes	MIT	5 days ago
Md To PDFMathews-Tom/armory	329	—	~2.4k	Automated safety check: Pass	MIT	4 days ago
Md To PDF Academicwentorai/research-plugins	298	1 repos	~1.8k	Automated safety check: Notes	MIT	3 mo ago

Similar skills

Harness Book Best Practice
wquguru/harness-books
Best practices for working on the Harness books repo. An agent skill from wquguru/harness-books.
3.2k GitHub stars~4.1k tokensUpdated 5 mo ago
Documents & OfficeAuto-check passed
Pandic Office
Team-Commonly/commonly
Convert Markdown to PDF (or DOCX/EPUB/HTML) using the pandoc CLI.
1.4k GitHub stars~642 tokensUpdated yesterday
Documents & OfficeAuto-check passed
Render PDF Doc
Aperivue/medsci-skills
A skill your agent uses when rendering a Markdown document (English or Korean) such as a proposal, IRB cover letter, handout or reference table to PDF via pandoc and xelatex, with auto-fitted table…
333 GitHub stars~2.1k tokensUpdated 5 days ago
Documents & OfficeAuto-check: notes
Md To PDF
Mathews-Tom/armory
Convert Markdown to styled PDFs with Mermaid diagrams, LaTeX/KaTeX math, tables, and code highlighting.
329 GitHub stars~2.4k tokensUpdated 4 days ago
Documents & OfficeAuto-check passed
Md To PDF Academic
wentorai/research-plugins
Convert Markdown to publication-quality PDF with LaTeX math rendering
298 GitHub starsUsed in 1 repo~1.8k tokens
Documents & OfficeAuto-check: notes
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.
910 GitHub stars~4.8k tokensUpdated 1 mo ago
Documents & OfficeAuto-check passed

Questions about Pandoc Unicode Sanitize

What does Pandoc Unicode Sanitize do?

Pre-process Markdown to replace non-ASCII characters before pandoc PDF conversion. Pandoc Unicode Sanitize is an agent skill from HKUDS/OpenSpace.

When should I use Pandoc Unicode Sanitize?

Pandoc Unicode Sanitize fits situations like: tasks that involve PDF.

How do I install Pandoc Unicode Sanitize in Claude Code?

Run `npx skills add HKUDS/OpenSpace --skill pandoc-unicode-sanitize -a claude-code`. Or copy the skill folder (benchmarks/gdpval/skills/pandoc-unicode-sanitize in HKUDS/OpenSpace) into .claude/skills/pandoc-unicode-sanitize in your project. Claude Code loads it when a task matches its description.

How do I install Pandoc Unicode Sanitize in Codex?

Run `npx skills add HKUDS/OpenSpace --skill pandoc-unicode-sanitize -a codex`. Or copy the skill folder (benchmarks/gdpval/skills/pandoc-unicode-sanitize in HKUDS/OpenSpace) into .agents/skills/pandoc-unicode-sanitize in your project. Codex loads it when a task matches its description.

Can I use Pandoc Unicode Sanitize 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 HKUDS/OpenSpace --skill pandoc-unicode-sanitize -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/pandoc-unicode-sanitize, .gemini/skills/pandoc-unicode-sanitize, .github/skills/pandoc-unicode-sanitize and .opencode/skills/pandoc-unicode-sanitize in your project.

What does Pandoc Unicode Sanitize need to run?

Going by SKILL.md and its folder, Pandoc Unicode Sanitize needs the command-line tools its instructions call (pandoc).

Does Pandoc Unicode Sanitize 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 Pandoc Unicode Sanitize 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. Review the folder before installing.

What licence does Pandoc Unicode Sanitize use?

Pandoc Unicode Sanitize 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 Pandoc Unicode Sanitize use?

About 663 tokens (SKILL.md is roughly 2.7k 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 Pandoc Unicode Sanitize?

Skills that share tags, products or a category with Pandoc Unicode Sanitize: Harness Book Best Practice (wquguru/harness-books, 3.2k stars), Pandic Office (Team-Commonly/commonly, 1.4k stars), Render PDF Doc (Aperivue/medsci-skills, 333 stars) and Md To PDF (Mathews-Tom/armory, 329 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Pandoc Unicode Sanitize?

HKUDS (a GitHub organization) maintains it in HKUDS/OpenSpace, which has 7,754 GitHub stars. The repository holds 199 skills in this directory. The repository was last updated on August 12, 2026.

Source: HKUDS/OpenSpace on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.

Install Pandoc Unicode Sanitize

Facts

At a glance

What it does

When your agent uses it

Example prompts

Workflow steps

What it can do on your machine

Tool permissions

Runs code

Network

Credentials

Context cost

Safety

SKILL.md

Pandoc Unicode Sanitization for PDF Conversion

Problem

Solution

Steps

1. Identify Problematic Characters

2. Create a Sed Substitution Script

3. Run Sanitization Before Pandoc

4. Alternative: Use iconv for Automatic Transliteration

5. Alternative: Use XeLaTeX or LuaLaTeX Engine

Best Practices

Common Error Signs

Files

Compare with similar skills

Similar skills

More from HKUDS/OpenSpace

Related

Questions about Pandoc Unicode Sanitize