Evidence Ledger
wanshuiyin/Anti-Autoresearch
Build the deterministic evidence ledger (artifactmanifest.json + claims.json) that every other Anti-Autoresearch auditor reads.
Reconstruct editable LaTeX from PDF content using page-aware extraction and visual comparison.
Install Pdf2tex
$ npx skills add Calix-L/awesome-latex-skills --skill pdf2tex -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install Calix-L/awesome-latex-skills pdf2tex --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/Calix-L/awesome-latex-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/pdf2tex .claude/skills/pdf2tex && 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 "pdf2tex" agent skill from https://github.com/Calix-L/awesome-latex-skills/tree/main/pdf2tex into .claude/skills/pdf2tex/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "pdf2tex", 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/Calix-L/awesome-latex-skills/tree/main/pdf2texType 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 Calix-L/awesome-latex-skills --skill pdf2tex -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install Calix-L/awesome-latex-skills pdf2tex --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Calix-L/awesome-latex-skills.git skills-src && mkdir -p .agents/skills && cp -r skills-src/pdf2tex .agents/skills/pdf2tex && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "pdf2tex" agent skill from https://github.com/Calix-L/awesome-latex-skills/tree/main/pdf2tex into .agents/skills/pdf2tex/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "pdf2tex", 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 Calix-L/awesome-latex-skills --skill pdf2tex -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install Calix-L/awesome-latex-skills pdf2tex --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Calix-L/awesome-latex-skills.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/pdf2tex .cursor/skills/pdf2tex && 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 "pdf2tex" agent skill from https://github.com/Calix-L/awesome-latex-skills/tree/main/pdf2tex into .cursor/skills/pdf2tex/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "pdf2tex", 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/Calix-L/awesome-latex-skills.git --path pdf2tex--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 Calix-L/awesome-latex-skills --skill pdf2tex -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install Calix-L/awesome-latex-skills pdf2tex --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Calix-L/awesome-latex-skills.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/pdf2tex .gemini/skills/pdf2tex && 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 "pdf2tex" agent skill from https://github.com/Calix-L/awesome-latex-skills/tree/main/pdf2tex into .gemini/skills/pdf2tex/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "pdf2tex", 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 Calix-L/awesome-latex-skills pdf2texInstalls 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 Calix-L/awesome-latex-skills --skill pdf2tex -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/Calix-L/awesome-latex-skills.git skills-src && mkdir -p .github/skills && cp -r skills-src/pdf2tex .github/skills/pdf2tex && 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 "pdf2tex" agent skill from https://github.com/Calix-L/awesome-latex-skills/tree/main/pdf2tex into .github/skills/pdf2tex/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "pdf2tex", 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 Calix-L/awesome-latex-skills --skill pdf2tex -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install Calix-L/awesome-latex-skills pdf2tex --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Calix-L/awesome-latex-skills.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/pdf2tex .opencode/skills/pdf2tex && 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 "pdf2tex" agent skill from https://github.com/Calix-L/awesome-latex-skills/tree/main/pdf2tex into .opencode/skills/pdf2tex/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "pdf2tex", 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
pdf2tex- GitHub stars
- 181
- Token cost
- ~1.4k tokens
- SKILL.md length
- 665 words
- Files
- 10 (incl. scripts, references, assets)
- Skills in repo
- 5
- Repo updated
- First seen
- Licence
- MIT
At a glance
Reconstruct editable LaTeX from PDF content using page-aware extraction and visual comparison.
- Tasks that involve LaTeX
- SKILL.md covers Establish the reconstruction…, Extract evidence, Reconstruct without inventing… and Build, compare, and deliver
- Runs Python scripts from its folder; calls python
- Tasks that involve PDF
What it does
Pdf2tex is an agent skill from Calix-L/awesome-latex-skills. Reconstruct editable LaTeX from PDF content using page-aware extraction and visual comparison. Preserve source evidence, flag uncertain math/tables/citations, and distinguish text extraction, OCR, reconstruction, and verified compilation.
Its SKILL.md is about 1.4k tokens, which your agent loads only when the skill is triggered. The skill folder holds 13 other files, including scripts, reference files and assets (for example `agents/config.yaml`, `agents/openai.yaml` and `references/math-reconstruction.md`).
It sits in Documents & Office, covering LaTeX, PDF and Citation management. It works with LaTeX. The repository describes itself as: LaTeX manuscript workflows with five agent skills, project diagnostics, reproducible builds and offline change review. The licence is MIT.
When your agent uses it
- Tasks that involve LaTeX
- Tasks that involve PDF
- Tasks that involve Citation management
Example prompts
- “/pdf2tex”
Requirements
- Python 3
What it can do on your machine
Read from SKILL.md and the folder at commit 7c29d3c. 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:
python
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
Pdf2tex loads about 1.4k tokens when it runs, and up to ~7.9k if it reads all its reference files. Until then it costs about 62 tokens; SKILL.md has 665 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 Calix-L/awesome-latex-skills at commit 7c29d3c, republished under its MIT licence (© Calix-L). 665 words, ~1,378 tokens.
Download SKILL.mdSave it as
.claude/skills/pdf2tex/SKILL.md (or your agent's skills folder). This skill also uses 9 other files; get the full folder from GitHub.- name
- pdf2tex
- description
- Reconstruct editable LaTeX from PDF content using page-aware extraction and visual comparison. Preserve source evidence, flag uncertain math/tables/citations, and distinguish text extraction, OCR, reconstruction, and verified compilation.
- metadata.version
- 1.25.0
Establish the reconstruction target
Inspect the PDF, requested pages, available tools, and desired output. Determine whether the user wants content recovery or close visual reconstruction. Preserve the original PDF and write new artifacts to a separate destination.
A PDF may expose text, font names, coordinates, images, and metadata. It does not reliably encode its original document class, packages, macros, bibliography database, comments, or source-file boundaries. Font/creator metadata is evidence for a candidate setup, not proof of the original engine or class.
Extract evidence
When PyMuPDF is available, use the bundled helper from this skill's own directory. The following paths are relative to the repository root; for an installed skill, substitute its actual location. Dependency installation is separate from extraction.
python -m pip install -r pdf2tex/requirements.txt
python pdf2tex/scripts/extract_pdf.py paper.pdf --output extraction --pages 1-3,5 --images --renderThe helper creates a new directory with report.html, text.txt, layout.json, and optional
embedded images and whole-page PNG previews when requested. It records page numbers, raw text spans/font/position data,
metadata, selected-page coverage, and warnings. It refuses existing output
directories and refuses publication if the input fingerprint changes during
extraction. Open report.html for offline page/text review; keep the entire
directory together when sharing. It performs no OCR or conversion.
Read PDF extraction guide for API details,
alternative readers, columns, fonts, and OCR. Sorted text is not guaranteed
reading order; inspect page layouts and use coordinates. Images can be repeated
or carry separate soft masks. Vector figures and composite panels often need
a page crop or another export workflow. Use optional --render previews to
inspect selected pages, including vector/composite figures; these are visual
evidence, not OCR or segmented assets. --dpi accepts 72–300 with a per-page pixel limit.
Use optional --chars when inspecting scripts or small notation. It adds
character origins/bounding boxes while retaining span text. Page geometry and
rotation matrices help relate unrotated text coordinates to rendered previews;
positions are evidence for candidate readings, not an automatic math parser.
A page without text may be blank, graphical, or scanned. Check it visually before choosing OCR. OCR requires separate tools and cannot establish the correctness of equations or tables. Retain page provenance and flag OCR-derived uncertainty. For a password-protected PDF, use an authorized readable copy.
Show full SKILL.md (315 more words)Show less
Reconstruct without inventing content
Use structure detection to interpret blocks, math reconstruction for notation, and table reconstruction for cells and merged regions. These heuristics need comparison with the rendered original.
- Select an available class and engine suitable for the target; state inferred choices. Use a supplied official author kit when exact publication layout is required.
- Preserve selected-page coverage, section order, prose, equations, table values, captions, footnotes, and references. Escape LaTeX-special characters in prose without indiscriminately escaping math or generated commands.
- Associate citation markers with bibliography entries only when the mapping is supported. Keep unmatched markers and uncertainty visible; do not invent bibliographic metadata or silently assign the nearest reference.
- Preserve ambiguous glyphs, merged table cells, missing images, and illegible
content as source evidence with
% [UNCERTAIN: ...]or a visible placeholder. A comment alone must not hide missing content from the generated document. - Remove headers/footers or join hyphenated lines only after checking that they are layout artifacts. Preserve meaningful hyphens and repeated scientific text.
- Do not guess original macros or file splitting. A self-contained source is a useful default, not a claim that it matches the original organization.
Build, compare, and deliver
Use the selected engine and actual bibliography backend, with additional passes
for cross-references. latex-rescue can help when available. If tools or assets
are unavailable, preserve the source and report compilation as unverified.
Compare the rendered reconstruction with the selected original pages: completeness, reading order, math symbols, tables, figure appearances, captions, and citations. Matching page counts does not establish fidelity. Check merged cells and OCR math manually, and distinguish a visual approximation from content verification.
Deliver the new source/assets, input version and selected pages, extraction and
OCR methods actually used, inferred class/engine, build and visual-check results,
and uncertainty locations. Separate recovered content from placeholders. Do not
promise exact original source, perfect reconstruction, or immediate compilation.
Use latex-polish or latex-fmt only for a further requested editing task.
© Calix-L, 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 9 other files (scripts, references, assets) in pdf2tex of Calix-L/awesome-latex-skills.
- SKILL.md
- agents/config.yaml
- agents/openai.yaml
- assets/review.css
- references/math-reconstruction.md
- references/pdf-extraction-guide.md
- references/structure-detection.md
- references/table-reconstruction.md
- requirements.txt
- scripts/extract_pdf.py
Open the folder on GitHubat commit 7c29d3c
Compare with similar skills
Pdf2tex 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 |
|---|---|---|---|---|---|---|
| Pdf2tex this skillCalix-L/awesome-latex-skills | 181 | — | ~1.4k | Automated safety check: Pass | MIT | |
| Evidence Ledgerwanshuiyin/Anti-Autoresearch | 161 | — | ~11k | Automated safety check: Notes | MIT | |
| Paper CovertGRIND-Lab-Core/night_owl_research_agent | 106 | — | ~2.1k | Automated safety check: Notes | None | |
| Kimi PDFthvroyal/kimi-skills | 238 | — | ~1.9k | Automated safety check: Pass | None | |
| Paper Auditbahayonghang/academic-writing-skills | 498 | — | ~5.1k | Automated safety check: Pass | None | |
| Thu ThesisLeoYeAI/openclaw-master-skills | 2.2k | — | ~4k | Automated safety check: Pass | MIT |
Similar skills
Paper Covert
GRIND-Lab-Core/night_owl_research_agent
Converts the final Markdown manuscript from paper-draft / paper-review-loop into a submission package for the target venue — modular LaTeX (one file per section), compiled PDF, and Word .docx.
Kimi PDF
thvroyal/kimi-skills
Professional PDF solution. An agent skill from thvroyal/kimi-skills.
Paper Audit
bahayonghang/academic-writing-skills
Reviewer-style audit and submission gate for academic papers in .tex, .typ, or .pdf.
Thu Thesis
LeoYeAI/openclaw-master-skills
清华大学毕业论文 Word → PDF 一键格式规范化工具。输入任意 Word (.docx) 格式的清华毕业论文，自动转换为符合清华 thuthesis 官方 LaTeX 模板规范的高质量 PDF。适用于所有清华学位论文（MBA/学硕/专硕），一条命令搞定。功能：自动提取章节结构、中英文摘要、参考文献（自动生成 BibTeX）、图片（含…
01 Paper Review
agentscope-ai/OpenJudge
Review academic papers for correctness, quality, and novelty using OpenJudge's multi-stage pipeline.
More from Calix-L/awesome-latex-skills
Latex Rescue
Calix-L/awesome-latex-skills
Diagnose and repair LaTeX build failures in local projects or supplied logs.
Latex Fmt
Calix-L/awesome-latex-skills
Reformat LaTeX papers for a specified venue, year, track, and submission stage.
Latex Polish
Calix-L/awesome-latex-skills
Edit academic prose in LaTeX manuscripts or supplied text at light, moderate, or strict intensity.
Paper Read
Calix-L/awesome-latex-skills
Summarize and critically analyze academic papers supplied as PDFs, text, arXiv links, or journal URLs.
Related
Works with
Categories
Questions about Pdf2tex
What does Pdf2tex do?
Reconstruct editable LaTeX from PDF content using page-aware extraction and visual comparison. Pdf2tex is an agent skill from Calix-L/awesome-latex-skills. Reconstruct editable LaTeX from PDF content using page-aware extraction and visual comparison.
When should I use Pdf2tex?
Pdf2tex fits situations like: tasks that involve LaTeX; tasks that involve PDF; tasks that involve Citation management.
How do I install Pdf2tex in Claude Code?
Run `npx skills add Calix-L/awesome-latex-skills --skill pdf2tex -a claude-code`. Or copy the skill folder (pdf2tex in Calix-L/awesome-latex-skills) into .claude/skills/pdf2tex in your project. Claude Code loads it when a task matches its description.
How do I install Pdf2tex in Codex?
Run `npx skills add Calix-L/awesome-latex-skills --skill pdf2tex -a codex`. Or copy the skill folder (pdf2tex in Calix-L/awesome-latex-skills) into .agents/skills/pdf2tex in your project. Codex loads it when a task matches its description.
Can I use Pdf2tex 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 Calix-L/awesome-latex-skills --skill pdf2tex -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/pdf2tex, .gemini/skills/pdf2tex, .github/skills/pdf2tex and .opencode/skills/pdf2tex in your project.
What does Pdf2tex need to run?
Going by SKILL.md and its folder, Pdf2tex needs Python for the scripts in its folder and the command-line tools its instructions call (python). Our summary lists: Python 3.
Does Pdf2tex 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 Pdf2tex 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 Pdf2tex use?
Pdf2tex 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 Pdf2tex use?
About 1.4k tokens (SKILL.md is roughly 5.5k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 6.5k tokens, read only when the agent opens those files.
What are the alternatives to Pdf2tex?
Skills that share tags, products or a category with Pdf2tex: Evidence Ledger (wanshuiyin/Anti-Autoresearch, 161 stars), Paper Covert (GRIND-Lab-Core/night_owl_research_agent, 106 stars), Kimi PDF (thvroyal/kimi-skills, 238 stars) and Paper Audit (bahayonghang/academic-writing-skills, 498 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Pdf2tex?
Calix-L (a GitHub user) maintains it in Calix-L/awesome-latex-skills, which has 181 GitHub stars. The repository holds 5 skills in this directory. The repository was last updated on October 7, 2026.
Source: Calix-L/awesome-latex-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.