Docsagent
docsagent/docsagent
Search and manage private, local document collections (PDF, PPTX, DOCX) offline.
Read and search PDFs, turn selected pages into Markdown, fill PDF forms, and create new copies with selected, reordered, rotated or merged pages.
Install PDF Tools
$ npx skills add Open-Document-Alliance/PDF-Tools --skill pdf-tools -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install Open-Document-Alliance/PDF-Tools pdf-tools --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/Open-Document-Alliance/PDF-Tools.git skills-src && mkdir -p .claude/skills && cp -r skills-src/plugins/pdf-tools-hosted/skills/pdf-tools .claude/skills/pdf-tools && 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-tools" agent skill from https://github.com/Open-Document-Alliance/PDF-Tools/tree/master/plugins/pdf-tools-hosted/skills/pdf-tools into .claude/skills/pdf-tools/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "pdf-tools", 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/Open-Document-Alliance/PDF-Tools/tree/master/plugins/pdf-tools-hosted/skills/pdf-toolsType 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 Open-Document-Alliance/PDF-Tools --skill pdf-tools -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install Open-Document-Alliance/PDF-Tools pdf-tools --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Open-Document-Alliance/PDF-Tools.git skills-src && mkdir -p .agents/skills && cp -r skills-src/plugins/pdf-tools-hosted/skills/pdf-tools .agents/skills/pdf-tools && 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-tools" agent skill from https://github.com/Open-Document-Alliance/PDF-Tools/tree/master/plugins/pdf-tools-hosted/skills/pdf-tools into .agents/skills/pdf-tools/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "pdf-tools", 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 Open-Document-Alliance/PDF-Tools --skill pdf-tools -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install Open-Document-Alliance/PDF-Tools pdf-tools --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Open-Document-Alliance/PDF-Tools.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/plugins/pdf-tools-hosted/skills/pdf-tools .cursor/skills/pdf-tools && 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-tools" agent skill from https://github.com/Open-Document-Alliance/PDF-Tools/tree/master/plugins/pdf-tools-hosted/skills/pdf-tools into .cursor/skills/pdf-tools/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "pdf-tools", 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/Open-Document-Alliance/PDF-Tools.git --path plugins/pdf-tools-hosted/skills/pdf-tools--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 Open-Document-Alliance/PDF-Tools --skill pdf-tools -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install Open-Document-Alliance/PDF-Tools pdf-tools --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Open-Document-Alliance/PDF-Tools.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/plugins/pdf-tools-hosted/skills/pdf-tools .gemini/skills/pdf-tools && 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-tools" agent skill from https://github.com/Open-Document-Alliance/PDF-Tools/tree/master/plugins/pdf-tools-hosted/skills/pdf-tools into .gemini/skills/pdf-tools/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "pdf-tools", 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 Open-Document-Alliance/PDF-Tools pdf-toolsInstalls 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 Open-Document-Alliance/PDF-Tools --skill pdf-tools -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/Open-Document-Alliance/PDF-Tools.git skills-src && mkdir -p .github/skills && cp -r skills-src/plugins/pdf-tools-hosted/skills/pdf-tools .github/skills/pdf-tools && 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-tools" agent skill from https://github.com/Open-Document-Alliance/PDF-Tools/tree/master/plugins/pdf-tools-hosted/skills/pdf-tools into .github/skills/pdf-tools/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "pdf-tools", 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 Open-Document-Alliance/PDF-Tools --skill pdf-tools -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install Open-Document-Alliance/PDF-Tools pdf-tools --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Open-Document-Alliance/PDF-Tools.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/plugins/pdf-tools-hosted/skills/pdf-tools .opencode/skills/pdf-tools && 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-tools" agent skill from https://github.com/Open-Document-Alliance/PDF-Tools/tree/master/plugins/pdf-tools-hosted/skills/pdf-tools into .opencode/skills/pdf-tools/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "pdf-tools", 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-tools- GitHub stars
- 160
- Token cost
- ~1k tokens
- SKILL.md length
- 575 words
- Files
- 1
- Skills in repo
- 3
- Repo updated
- First seen
- Licence
- MIT
At a glance
Read and search PDFs, turn selected pages into Markdown, fill PDF forms, and create new copies with selected, reordered, rotated or merged pages.
- Tasks that involve PDF
- SKILL.md covers Get the supplied file, Read, search and convert, Make and return a new copy and Forms and visible stamps
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
PDF Tools is an agent skill from Open-Document-Alliance/PDF-Tools. Read and search PDFs, turn selected pages into Markdown, fill PDF forms, and create new copies with selected, reordered, rotated or merged pages. Reports source coverage and extraction gaps.
Its SKILL.md is about 1k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.
It sits in Documents & Office, covering PDF. It works with Model Context Protocol. The repository describes itself as: Fill, sign, merge, split, and extract PDFs from Claude Desktop and other MCP hosts. Maintained by the Open Document Alliance. The licence is MIT.
When your agent uses it
- Tasks that involve PDF
Example prompts
- “/pdf-tools”
What it can do on your machine
Read from SKILL.md and the folder at commit f1aaa18. 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
No scripts in the folder and no shell commands in SKILL.md.
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
PDF Tools loads about 1k tokens when it runs. Until then it costs about 50 tokens; SKILL.md has 575 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); files beside SKILL.md are not scanned.
SKILL.md
The full file from Open-Document-Alliance/PDF-Tools at commit f1aaa18, republished under its MIT licence (© Open-Document-Alliance). 575 words, ~1,002 tokens.
Download SKILL.mdSave it as
.claude/skills/pdf-tools/SKILL.md (or your agent's skills folder).- name
- pdf-tools
- description
- Read and search PDFs, turn selected pages into Markdown, fill PDF forms, and create new copies with selected, reordered, rotated or merged pages. Reports source coverage and extraction gaps.
PDF Tools
Use the configured pdf-tools hosted MCP. This processes only documents
explicitly supplied for this task, remotely for one request at a time. It does
not store documents, browse local folders, or provide the local application's
saved workspace, profiles, full viewer or Lumin signing.
Get the supplied file
Prefer the host-provided file attachment input. The host supplies its real
download_url and file_id; never invent them. Tools also accept an authorized
pdf_url or actual pdf_base64, but never more than one input form. merge_pdfs
takes a files array of 2 to 5 real attachments. Never publish a private file
elsewhere just to obtain a public URL. If the host cannot supply the attachment,
explain the unsupported handoff rather than claiming access.
Inputs fetched by URL or attachment are limited to 25 MB and 200 pages. Inline input and returned PDFs are limited to 3 MB. Encrypted PDFs are refused. The assistant host's data terms apply to files and content shared with it.
Read, search and convert
Use get_pdf_info first to establish the source and page count. Reading,
searching and Markdown conversion require explicit inclusive page ranges of
at most 10 pages per call. They default to page 1 only. Track the exact covered
ranges if working through a longer document; never describe an unexamined page
as reviewed. Use read_pdf_pages, search_pdf_text and
convert_pdf_to_markdown for their respective jobs.
Preserve extraction status, truncation and gap warnings in the answer. A no-match result covers only the extracted text in that range. No OCR is performed; image-only content and missing text are not empty-document proof. Markdown conversion is not complete mathematical, table or schema extraction.
Show full SKILL.md (306 more words)Show less
Make and return a new copy
Use select_pdf_pages with exact unique page numbers in the desired order to
split or reorder. Omitted pages are deliberately excluded and must be reported.
Use rotate_pdf_pages for exact pages and 90, 180 or 270 clockwise degrees.
Use merge_pdfs for explicitly supplied attachments in their listed order.
Page selection and merging copy page content, not document-level form
structure, bookmarks or metadata. Do not promise those survived.
For user-facing PDF-producing calls set output_mode: "download". The
result card receives and verifies PDF bytes without placing them in the
model-visible result. The download action is user initiated and depends on
host support. Never call encoded data a download link or say the file has
been saved before the host or user confirms it. Without a working card,
explain the output limitation. output_mode: "inline" is for machine clients
that can actually consume base64; do not echo large base64 to the user.
The source is never overwritten. To run a further operation on the new copy, use an actual host-authorized file handoff. A digest alone is not access to bytes, and the stateless server cannot retrieve a previous result by ID.
Forms and visible stamps
Read read_form_fields and use exact returned field names. Fill only the user's
provided values with fill_form. Report both filled and not_filled. Verify
the new copy when the host can supply it again; otherwise do not claim readback.
Use flatten_form only when the user wants fixed page content rather than
editable fields. A successful fill does not mean complete or ready to submit.
Use detect_signature_zones before a visible stamp. apply_signature needs
the person's own explicit intent statement and actual recent confirmation
time. Never invent consent, timestamp or signature identity. A visible stamp
is not a cryptographic signature or a Lumin signing request. Do not bypass
signature, XFA, encryption, size or private-network refusals.
© Open-Document-Alliance, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
Just SKILL.md in plugins/pdf-tools-hosted/skills/pdf-tools of Open-Document-Alliance/PDF-Tools.
Open the folder on GitHubat commit f1aaa18
Compare with similar skills
PDF Tools 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 Tools this skillOpen-Document-Alliance/PDF-Tools | 160 | — | ~1k | Automated safety check: Pass | MIT | |
| Docsagentdocsagent/docsagent | 625 | — | ~834 | Automated safety check: Pass | None | |
| Nutrient Document Processingaffaan-m/ECC | 275k | 4 repos | ~1.5k | Automated safety check: Pass | MIT | |
| Nano PDFswarmclawai/swarmclaw | 688 | — | ~379 | Automated safety check: Pass | MIT | |
| Nutrient Document Processingaffaan-m/ECC | 275k | 3 repos | ~1.3k | Automated safety check: Pass | MIT | |
| Nutrient Document Processingaffaan-m/ECC | 275k | 2 repos | ~1.3k | Automated safety check: Pass | MIT |
Similar skills
Nutrient Document Processing
affaan-m/ECC
Process, convert, OCR, extract, redact, sign, and fill documents using the Nutrient DWS API.
Nano PDF
swarmclawai/swarmclaw
Edit or create PDFs with natural-language instructions using the nano-pdf CLI.
Nutrient Document Processing
affaan-m/ECC
使用Nutrient DWS API处理、转换、OCR识别、提取、编辑、签名和填写文档。支持PDF、DOCX、XLSX、PPTX、HTML和图像格式。
Nutrient Document Processing
affaan-m/ECC
Nutrient DWS API を使用してドキュメントの処理、変換、OCR、抽出、編集、署名、フォーム入力を行います。PDF、DOCX、XLSX、PPTX、HTML、画像に対応しています。
- Official
PDF Processor
microsoft/waza
WORKFLOW SKILL - Process PDF files including text extraction, rotation, and merging.
More from Open-Document-Alliance/PDF-Tools
PDF Tools Workflow
Open-Document-Alliance/PDF-Tools
Read, compare, fill, stamp, organize, and prepare PDFs for signing with PDF Tools.
PDF Forms
Open-Document-Alliance/PDF-Tools
Help inspect and fill PDF forms, find signature locations, add a visible signature stamp with the person's confirmation, and flatten a reviewed form using the hosted PDF Forms tools.
Related
Works with
Categories
Questions about PDF Tools
What does PDF Tools do?
Read and search PDFs, turn selected pages into Markdown, fill PDF forms, and create new copies with selected, reordered, rotated or merged pages. PDF Tools is an agent skill from Open-Document-Alliance/PDF-Tools. Read and search PDFs, turn selected pages into Markdown, fill PDF forms, and create new copies with selected, reordered, rotated or merged pages.
When should I use PDF Tools?
PDF Tools fits situations like: tasks that involve PDF.
How do I install PDF Tools in Claude Code?
Run `npx skills add Open-Document-Alliance/PDF-Tools --skill pdf-tools -a claude-code`. Or copy the skill folder (plugins/pdf-tools-hosted/skills/pdf-tools in Open-Document-Alliance/PDF-Tools) into .claude/skills/pdf-tools in your project. Claude Code loads it when a task matches its description.
How do I install PDF Tools in Codex?
Run `npx skills add Open-Document-Alliance/PDF-Tools --skill pdf-tools -a codex`. Or copy the skill folder (plugins/pdf-tools-hosted/skills/pdf-tools in Open-Document-Alliance/PDF-Tools) into .agents/skills/pdf-tools in your project. Codex loads it when a task matches its description.
Can I use PDF Tools 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 Open-Document-Alliance/PDF-Tools --skill pdf-tools -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-tools, .gemini/skills/pdf-tools, .github/skills/pdf-tools and .opencode/skills/pdf-tools in your project.
What does PDF Tools need to run?
SKILL.md names no scripts, command-line tools or credentials: PDF Tools is instructions for the agent only.
Does PDF Tools 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 Tools 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 PDF Tools use?
PDF Tools 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 Tools use?
About 1k tokens (SKILL.md is roughly 4k 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 Tools?
Skills that share tags, products or a category with PDF Tools: Docsagent (docsagent/docsagent, 625 stars), Nutrient Document Processing (affaan-m/ECC, 275k stars), Nano PDF (swarmclawai/swarmclaw, 688 stars) and Nutrient Document Processing (affaan-m/ECC, 275k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains PDF Tools?
Open-Document-Alliance (a GitHub organization) maintains it in Open-Document-Alliance/PDF-Tools, which has 160 GitHub stars. The repository holds 3 skills in this directory. The repository was last updated on October 7, 2026.
Source: Open-Document-Alliance/PDF-Tools on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.