Markitdown
aipoch/medical-research-skills
Convert files and Office documents into clean Markdown when you need LLM-friendly, token-efficient text (e.g., for summarization, search, RAG ingestion, or dataset preparation).
Quick reference for wdoc, a command-line and Python tool that summarizes, searches and answers questions over documents of many file types.
Install wdoc Reference
$ npx skills add thiswillbeyourgithub/wdoc --skill wdoc-skill -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install thiswillbeyourgithub/wdoc wdoc-skill --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/thiswillbeyourgithub/wdoc.git skills-src && mkdir -p .claude/skills && cp -r skills-src/wdoc-skill .claude/skills/wdoc-skill && 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 "wdoc-skill" agent skill from https://github.com/thiswillbeyourgithub/wdoc/tree/main/wdoc-skill into .claude/skills/wdoc-skill/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "wdoc-skill", 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/thiswillbeyourgithub/wdoc/tree/main/wdoc-skillType 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 thiswillbeyourgithub/wdoc --skill wdoc-skill -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install thiswillbeyourgithub/wdoc wdoc-skill --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/thiswillbeyourgithub/wdoc.git skills-src && mkdir -p .agents/skills && cp -r skills-src/wdoc-skill .agents/skills/wdoc-skill && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "wdoc-skill" agent skill from https://github.com/thiswillbeyourgithub/wdoc/tree/main/wdoc-skill into .agents/skills/wdoc-skill/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "wdoc-skill", 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 thiswillbeyourgithub/wdoc --skill wdoc-skill -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install thiswillbeyourgithub/wdoc wdoc-skill --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/thiswillbeyourgithub/wdoc.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/wdoc-skill .cursor/skills/wdoc-skill && 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 "wdoc-skill" agent skill from https://github.com/thiswillbeyourgithub/wdoc/tree/main/wdoc-skill into .cursor/skills/wdoc-skill/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "wdoc-skill", 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/thiswillbeyourgithub/wdoc.git --path wdoc-skill--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 thiswillbeyourgithub/wdoc --skill wdoc-skill -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install thiswillbeyourgithub/wdoc wdoc-skill --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/thiswillbeyourgithub/wdoc.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/wdoc-skill .gemini/skills/wdoc-skill && 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 "wdoc-skill" agent skill from https://github.com/thiswillbeyourgithub/wdoc/tree/main/wdoc-skill into .gemini/skills/wdoc-skill/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "wdoc-skill", 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 thiswillbeyourgithub/wdoc wdoc-skillInstalls 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 thiswillbeyourgithub/wdoc --skill wdoc-skill -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/thiswillbeyourgithub/wdoc.git skills-src && mkdir -p .github/skills && cp -r skills-src/wdoc-skill .github/skills/wdoc-skill && 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 "wdoc-skill" agent skill from https://github.com/thiswillbeyourgithub/wdoc/tree/main/wdoc-skill into .github/skills/wdoc-skill/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "wdoc-skill", 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 thiswillbeyourgithub/wdoc --skill wdoc-skill -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install thiswillbeyourgithub/wdoc wdoc-skill --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/thiswillbeyourgithub/wdoc.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/wdoc-skill .opencode/skills/wdoc-skill && 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 "wdoc-skill" agent skill from https://github.com/thiswillbeyourgithub/wdoc/tree/main/wdoc-skill into .opencode/skills/wdoc-skill/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "wdoc-skill", 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
wdoc-skill- GitHub stars
- 545
- Token cost
- ~1.1k tokens
- SKILL.md length
- 341 words
- Files
- 3
- Skills in repo
- 1
- Repo updated
- First seen
- Licence
- AGPL-3.0
At a glance
Quick reference for wdoc, a command-line and Python tool that summarizes, searches and answers questions over documents of many file types.
- Running wdoc to query or summarize a PDF, video or web page
- SKILL.md covers Quick start, The four tasks, Core mechanics worth knowing and Common patterns
- Calls pip and uvx; needs ANTHROPIC_API_KEY
- Looking up a wdoc CLI argument, environment variable or filetype
What it does
wdoc is a retrieval-augmented generation tool that handles more than 20 file types, among them PDF, YouTube, audio, Anki, web pages, Zotero and Karakeep, and sends every model call through LiteLLM. This skill is the orientation for wdoc version 5.1.0, with companion files REFERENCE.md and EXAMPLES.md covering every CLI argument, filetype, loader option, environment variable and the Python API.
It explains four tasks: `query` embeds documents, retrieves chunks and answers with sourced markdown; `search` returns matching documents and metadata without an LLM answer; `summarize` writes a detailed markdown summary; and `summarize_then_query` does both in one run. Other notes cover auto-detected filetypes, two models per run (a strong one to answer and a cheaper one to filter chunks), piped input, and a private mode that blocks outbound traffic for use with local models such as Ollama.
When your agent uses it
- Running wdoc to query or summarize a PDF, video or web page
- Looking up a wdoc CLI argument, environment variable or filetype
- Calling wdoc from Python code
Example prompts
- “Use wdoc to summarize this PDF and give me the result as markdown.”
- “Query my Zotero library with wdoc and ask which papers discuss retrieval evaluation.”
- “Show me how to run wdoc in private mode against a local Ollama model.”
Requirements
- wdoc installed with pip, using the full extras to get every loader, or run through `uvx`
- An API key for an LLM provider, such as `ANTHROPIC_API_KEY`
What it can do on your machine
Read from SKILL.md and the folder at commit 6a6ae50. 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:
pipuvx
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md. Its commands use pip and uvx, which can reach the network depending on how they are called.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names these keys or tokens, usually read from environment variables:
ANTHROPIC_API_KEY
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
wdoc Reference loads about 1.1k tokens when it runs. Until then it costs about 116 tokens; SKILL.md has 341 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 thiswillbeyourgithub/wdoc at commit 6a6ae50, republished under its AGPL-3.0 licence (© thiswillbeyourgithub). 341 words, ~1,106 tokens.
Download SKILL.mdSave it as
.claude/skills/wdoc-skill/SKILL.md (or your agent's skills folder). This skill also uses 2 other files; get the full folder from GitHub.- name
- wdoc-skill
- description
- Comprehensive reference for wdoc, a RAG CLI and Python library that summarizes, searches, and queries documents across 20+ filetypes (PDF, YouTube, audio, Anki, web, Zotero, Karakeep, and more) through LiteLLM (100+ LLM providers). Use when the user runs or asks about the `wdoc` command, imports `from wdoc import wdoc`, or needs help with wdoc tasks (query, search, summarize, parse), CLI arguments, environment variables, filetypes, or the Python API.
wdoc
Written for wdoc v5.1.0. On a different version, some arguments, defaults, or behaviors may differ.
wdoc is a RAG (Retrieval-Augmented Generation) system for summarizing, searching, and querying documents across 20+ file types. It works as a CLI (via Google Fire) and as a Python library (from wdoc import wdoc), routing every LLM call through LiteLLM (100+ providers).
This SKILL.md is the quick orientation. The deep material lives in two companion files:
- REFERENCE.md: every CLI argument, filetype, loader option, environment variable, and the full Python API.
- EXAMPLES.md: copy-pasteable shell and Python examples.
Quick start
pip install -U wdoc[full] # full install: all loaders. Plain `wdoc` ships only PDF + URL.
export ANTHROPIC_API_KEY="your_key" # or whichever provider you use
wdoc query paper.pdf "What are the main findings?" # ask questions (RAG)
wdoc summarize paper.pdf # detailed markdown summary
wdoc parse paper.pdf # parse to text, no LLM
wdoc web "latest on quantum computing" # DuckDuckGo + queryuvx wdoc[full] ... runs it without installing and sidesteps thinking about extras.
The four tasks
| Task | What it does | Pick it when |
|---|---|---|
query | Embeds docs, retrieves chunks, answers with sourced markdown | You have a question about the content |
search | Returns matching docs + metadata, no LLM answer | You only need to locate relevant passages |
summarize | Detailed markdown summary (author's reasoning, not vague takeaways) | You want the gist of a long document |
summarize_then_query | Summarize first, then drop into a query prompt | You want both, in one run |
Core mechanics worth knowing
- Shortcuts:
wdoc query FILE,wdoc summarize FILE,wdoc parse FILE, andwdoc web "q"expand to longer--task=...forms. Positional args work too:wdoc TASK PATH [QUERY]. - Filetype is auto-detected (
--filetype=auto) but can be forced (pdf,youtube,anki,zotero, ...). Recursive filetypes (recursive_paths,zotero,karakeep,ddg, ...) fan one selector out into many documents. - Two models per run: a strong
--modelanswers, a cheap--query_eval_modelfilters chunks. Both take LiteLLMprovider/modelids. - kebab or snake case:
--query-eval-modeland--query_eval_modelare equivalent. - Piped input is auto-detected:
cat file.pdf | wdoc parse --filetype=pdf. - Privacy:
--private(orWDOC_PRIVATE_MODE=true) blocks all outbound traffic and redacts API keys; pair it with local models (Ollama) and--llms_api_bases. - Reuse embeddings:
--save_embeds_as=idx.pklonce, then--load_embeds_from=idx.pklto skip re-indexing. - Cost guard:
--dollar_limit(default 5) stops summaries/embeddings before they get expensive.
Common patterns
# Query every PDF in a tree
wdoc --task=query --path="papers/" --filetype=recursive_paths \
--pattern="**/*.pdf" --recursed_filetype=pdf --query="..."
# Fully local / private
wdoc --private --model="ollama/qwen3:8b" --query_eval_model="ollama/qwen3:8b" \
--embed_model="ollama/snowflake-arctic-embed2" --task=query --path=secret.pdf
# Parse for use elsewhere (text, langchain, langchain_dict, xml, split_text)
wdoc parse document.pdf --format=langchain_dictfrom wdoc import wdoc
instance = wdoc(task="query", path="paper.pdf", model="openai/gpt-4o")
answer = instance.query_task("What are the main contributions?")
print(answer["final_answer"])For anything beyond this page (exact argument types, defaults, every filetype's loader options, all WDOC_* env vars, the full Python API surface, and more examples), read REFERENCE.md and EXAMPLES.md.
© thiswillbeyourgithub, AGPL-3.0. 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 2 other files in wdoc-skill of thiswillbeyourgithub/wdoc.
- SKILL.md
- EXAMPLES.md
- REFERENCE.md
Open the folder on GitHubat commit 6a6ae50
Compare with similar skills
wdoc Reference 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 |
|---|---|---|---|---|---|---|
| wdoc Reference this skillthiswillbeyourgithub/wdoc | 545 | — | ~1.1k | Automated safety check: Pass | AGPL-3.0 | |
| Markitdownaipoch/medical-research-skills | 2k | — | ~1.3k | Automated safety check: Pass | MIT | |
| Sentence Transformers EmbeddingsOrchestra-Research/AI-Research-SKILLs | 13k | 3 repos | ~1.6k | Automated safety check: Pass | MIT | |
| Scholar RAGjoshzyj/open-scholar-skill | 167 | — | ~7.4k | Automated safety check: Notes | Custom licence | |
| Langchain RAGlangchain-ai/langchain-skills | 1.3k | 1 repos | ~3.9k | Automated safety check: Pass | MIT | |
| Neo4j Graphrag Skillneo4j-contrib/neo4j-skills | 114 | — | ~4.2k | Automated safety check: Notes | MIT |
Similar skills
Sentence Transformers Embeddings
Orchestra-Research/AI-Research-SKILLs
Generates text embeddings locally with the sentence-transformers library for RAG, semantic search, clustering and similarity, with model picks for general, multilingual and legal text.
Scholar RAG
joshzyj/open-scholar-skill
Build and query a local vector database + GraphRAG over your entire reference library (Zotero or a PDF folder) for literature review.
- Official
Langchain RAG
langchain-ai/langchain-skills
INVOKE THIS SKILL when building ANY retrieval-augmented generation (RAG) system.
Neo4j Graphrag Skill
neo4j-contrib/neo4j-skills
Build GraphRAG retrieval pipelines on Neo4j using the neo4j-graphrag Python package (v1.22.0+).
Pinecone Vector Database
Orchestra-Research/AI-Research-SKILLs
Shows how to use Pinecone, a managed vector database, for production RAG, semantic search and recommendations: indexes, upserts, queries, filters and namespaces.
Related
Categories
Questions about wdoc Reference
What does wdoc Reference do?
Quick reference for wdoc, a command-line and Python tool that summarizes, searches and answers questions over documents of many file types. wdoc is a retrieval-augmented generation tool that handles more than 20 file types, among them PDF, YouTube, audio, Anki, web pages, Zotero and Karakeep, and sends every model call through LiteLLM.md covering every CLI argument, filetype, loader option, environment variable and the Python API.
When should I use wdoc Reference?
wdoc Reference fits situations like: running wdoc to query or summarize a PDF, video or web page; looking up a wdoc CLI argument, environment variable or filetype; calling wdoc from Python code.
How do I install wdoc Reference in Claude Code?
Run `npx skills add thiswillbeyourgithub/wdoc --skill wdoc-skill -a claude-code`. Or copy the skill folder (wdoc-skill in thiswillbeyourgithub/wdoc) into .claude/skills/wdoc-skill in your project. Claude Code loads it when a task matches its description.
How do I install wdoc Reference in Codex?
Run `npx skills add thiswillbeyourgithub/wdoc --skill wdoc-skill -a codex`. Or copy the skill folder (wdoc-skill in thiswillbeyourgithub/wdoc) into .agents/skills/wdoc-skill in your project. Codex loads it when a task matches its description.
Can I use wdoc Reference 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 thiswillbeyourgithub/wdoc --skill wdoc-skill -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/wdoc-skill, .gemini/skills/wdoc-skill, .github/skills/wdoc-skill and .opencode/skills/wdoc-skill in your project.
What does wdoc Reference need to run?
Going by SKILL.md and its folder, wdoc Reference needs the command-line tools its instructions call (pip and uvx) and credentials named ANTHROPIC_API_KEY. Our summary lists: wdoc installed with pip, using the full extras to get every loader, or run through `uvx`; An API key for an LLM provider, such as `ANTHROPIC_API_KEY`.
Does wdoc Reference access the network?
SKILL.md contains no URLs. Its commands use pip and uvx, which can reach the network depending on how they are called. This is read from the text; nothing was executed.
Is wdoc Reference 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 wdoc Reference use?
wdoc Reference is published under the AGPL-3.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does wdoc Reference use?
About 1.1k tokens (SKILL.md is roughly 4.4k 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 wdoc Reference?
Skills that share tags, products or a category with wdoc Reference: Markitdown (aipoch/medical-research-skills, 2k stars), Sentence Transformers Embeddings (Orchestra-Research/AI-Research-SKILLs, 13k stars), Scholar RAG (joshzyj/open-scholar-skill, 167 stars) and Langchain RAG (langchain-ai/langchain-skills, 1.3k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains wdoc Reference?
thiswillbeyourgithub (a GitHub user) maintains it in thiswillbeyourgithub/wdoc, which has 545 GitHub stars. The repository was last updated on August 24, 2026.
Source: thiswillbeyourgithub/wdoc on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.