Nm Scribe Doc Importer

Import external documents (PDF, DOCX, PPTX, XLSX, HTML) into editable markdown for rewriting or project integration

Security Scan

The skill's requirements and runtime instructions are coherent with a document-to-markdown converter: it asks for document-conversion and sanitization hooks and instructs reading and writing the source/target files, without requesting unrelated secrets or downloads.

Purpose & Capability

Name/description (import documents to markdown) lines up with the declared config dependencies (document-conversion, content-sanitization, slop-detector, doc-generator). No unrelated environment variables, binaries, or install steps are requested.

Instruction Scope

The SKILL.md instructs the agent to verify local file existence (via a Read tool), construct URIs for URLs, invoke the document-conversion protocol (markitdown MCP or fallbacks), sanitize output, and write the resulting .md to the same directory by default. These steps are within the skill's purpose, but they imply filesystem read/write and potential network activity (downloading remote docs or calling external conversion services) which are not explicitly declared in the manifest.

Install Mechanism

Instruction-only skill with no install spec and no code files — nothing is written to disk by an installer and no external packages are pulled during install.

Credentials

No environment variables, credentials, or sensitive keys are requested. The required config paths are relevant to document conversion/sanitization and align with the stated functionality.

Persistence & Privilege

always:false and normal autonomous invocation allowed (disable-model-invocation:false). This is standard, but because the instructions include reading local file paths and writing output files, users should be aware that autonomous invocation could cause the agent to access filesystem resources when triggered.

Assessment

This skill appears to do what it says: convert external documents to markdown and optionally hand them to a doc-generator. Before installing, check the following: (1) Confirm what agent tools the platform exposes for filesystem Read/Write and what paths they are allowed to access—avoid granting access to sensitive directories. (2) Verify whether the 'markitdown MCP' or other conversion fallbacks perform conversion locally or send files to remote services; if remote, avoid processing sensitive documents or review the remote service's privacy. (3) Since the skill can be invoked autonomously, consider restricting triggers or requiring explicit user confirmation before reading/writing files. (4) If you want more assurance, inspect the referenced GitHub plugin (https://github.com/athola/claude-night-market/tree/master/plugins/scribe) to see how the named protocols/tools are implemented. Test first with non-sensitive files.

Night Market Skill — ported from claude-night-market/scribe. For the full experience with agents, hooks, and commands, install the Claude Code plugin.

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