Doc Processor
Generic read/convert/generate workflow for PDF, docx, CSV, HTML via pandoc
Test report
- Verdict
- Tested · Didn't pass
- Tested
- Jul 17, 2026
- Environment
- Claude Code 2.x (agent harness)
- Upstream re-checked
- Aug 10, 2026 · 493ca9f
Head-to-head on 'read this PDF, deliver an HTML report': the no-skill baseline read the PDF natively and shipped the HTML in two steps, while the skill's mandated pandoc pipeline hit a missing binary and degraded to a Markdown fallback plus an install-pandoc request. The 22-line body tells Claude nothing it does not already do, and its pdftotext detour is a step backwards from native PDF reading. It was written for the OpenClawX runtime (lowercase read/write/bash tool names) and ships inside that app's preset workspaces, not as a standalone Claude Code skill.
Scored on four weighted criteria — install, triggering, output vs. baseline, docs. How scoring works
- Installs cleanly 5/5
- Triggers reliably 4/5
- Output vs. baseline 4/10
- Docs & honesty 4/5
What Doc Processor does
A minimal 22-line workflow skill that tells Claude to read plaintext files directly, convert binary documents (PDF, docx) with pdftotext or pandoc, and generate output documents by drafting Markdown and converting with pandoc. Part of the OpenClawX preset workspaces rather than a standalone skill; it triggers on requests to read, summarize, or generate documents in Markdown, PDF, docx, CSV, or HTML.
How to install Doc Processor
git clone https://github.com/next-open-ai/openclawx
mkdir -p ~/.claude/skills
cp -r openclawx/presets/workspaces/doc-assistant/skills/doc-processor ~/.claude/skills/doc-processor
Skills live in ~/.claude/skills/ (global) or .claude/skills/
(per-project). Restart Claude Code after installing.
Commands — how to trigger Doc Processor
-
/doc-processorGeneric read/convert/generate workflow for PDF, docx, CSV, HTML via pandoc
It also activates on plain-language prompts like these:
-
Read this PDF and give me an HTML report from it -
Convert this docx file into clean Markdown for me -
Summarize this CSV export into a readable document
Frequently asked questions
- Is the Doc Processor skill free?
- Yes. The skill itself is free from next-open-ai/openclawx. SkillProof publishes the install command and an independent test verdict at no cost.
- Does Doc Processor work with Claude Code?
- We tested it with Claude Code 2.x (agent harness) on Jul 17, 2026. Verdict: Tested · Didn't pass. Head-to-head on 'read this PDF, deliver an HTML report': the no-skill baseline read the PDF natively and shipped the HTML in two steps, while the skill's mandated pandoc pipeline hit a missing binary and degraded to a Markdown fallback plus an install-pandoc request. The 22-line body tells Claude nothing it does not already do, and its pdftotext detour is a step backwards from native PDF reading. It was written for the OpenClawX runtime (lowercase read/write/bash tool names) and ships inside that app's preset workspaces, not as a standalone Claude Code skill.
- How do I install Doc Processor?
- Copy the install command from this page, run it in your terminal, and restart Claude Code. Skills live in ~/.claude/skills/ (global) or .claude/skills/ inside a project.
- Can I use Doc Processor with Cursor, Copilot, Gemini CLI, Codex or other AI tools?
- The SKILL.md format is native to Claude (Claude Code, Desktop, claude.ai). The instructions inside adapt to other assistants: Cursor rules, GitHub Copilot instructions, Windsurf rules, Custom GPTs, AGENTS.md for OpenAI Codex, and GEMINI.md for Google Gemini CLI — our conversion guides cover each, and the free converter on the tools page does the wrapping for you.