OpenParable
Skip to content
← Back to skills

Doc Importer

Documents
doc-importer

Doc Importer is an Agent Skill for documents published in the athola/claude-night-market repository on GitHub: a SKILL.md instruction file an AI agent can load to do this task.

Converts external documents (PDF, DOCX, PPTX, XLSX, HTML) into editable markdown. Use when ingesting external files for rewriting or project integration.

View on GitHub ↗
QUICK START

How to use this skill

Bring this guide into your coding agent with a prompt tailored to the tool you use.

  1. Open your project in Codex.
  2. Copy and paste the prompt below.
  3. Review files and risks before approving any action.
Prompt to paste
Inspect the Agent Skill at https://github.com/athola/claude-night-market/blob/HEAD/plugins/scribe/skills/doc-importer/SKILL.md and all supporting files. Report provenance, permissions, scripts, dependencies, and security risks. Propose an exact installation into .agents/skills/doc-importer, but wait for my approval before writing files or running scripts.

Copying this prompt does not install or run the skill. Review third-party files before use.

Document Importer

Import external documents into editable markdown.

When To Use

  • User provides a DOCX, PPTX, XLSX, PDF, or HTML file to convert into project documentation
  • User wants to extract content from a document for rewriting or remediation
  • User has a slide deck or spreadsheet to turn into markdown documentation

When NOT To Use

  • Academic paper analysis: use tome:papers
  • Web article knowledge intake: use memory-palace:knowledge-intake
  • Content already in markdown: use scribe:doc-generator remediation mode directly

Import Workflow

Step 1: Identify Source

Determine the source document:

  • Local file path: verify it exists with Read tool
  • URL: verify accessibility
  • User description: confirm format and location

Step 2: Convert to Markdown

Apply the leyline:document-conversion protocol:

  1. Construct URI from source (file path or URL)
  2. Try the markitdown MCP tool for best quality
  3. If unavailable, use native tool fallbacks
  4. If format unsupported, inform user

Step 3: Structural Cleanup

After conversion, normalize the markdown:

  • Ensure ATX headings (# style, not setext underlines)
  • Wrap prose lines at 80 characters per leyline:markdown-formatting
  • Fix broken tables (align columns, add headers)
  • Remove conversion artifacts (page numbers, headers/footers, watermarks, repeated logos)
  • Preserve all substantive content

Step 4: Sanitize External Content

Apply the leyline:content-sanitization checklist:

  • Size check (truncate sections over 2000 words)
  • Strip system/instruction tags
  • Wrap in external content boundary markers

Step 5: Write Draft

Write the converted markdown to the target location. Default: same directory as source, with .md extension. Ask the user for target path if ambiguous.

Step 6: Hand Off to Doc-Generator (Optional)

If the user wants polishing or rewriting:

  • Invoke Skill(scribe:doc-generator) in Remediation mode on the imported file
  • The doc-generator handles slop detection, style application, and quality gates

Offer this step. Do not assume the user wants remediation.

Output Quality

The imported markdown should:

  • Have a top-level # Title from the document title
  • Preserve the original heading hierarchy
  • Convert tables to markdown tables
  • Convert images to ![alt](path) references (note: image files may need separate handling)
  • Convert lists faithfully
  • Mark unclear or garbled sections with <!-- REVIEW: conversion artifact -->

Exit Criteria

  • Source document identified and accessible
  • Conversion attempted via document-conversion protocol
  • Structural cleanup applied
  • Sanitization checklist passed
  • Draft written to target path
  • User informed of any conversion limitations