All skills
oaustegard avatar

/mapping-documents

@9141df6

Generate navigable semantic maps from PDF documents. Extracts section structure via font analysis, then runs LLM extraction per section for claims, symbols, and dependencies — all page-anchored. Produces _MAP.md (progressive disclosure), .symbols.json (definition index), .anchors.json (claim references), and a _USAGE.md snippet for CLAUDE.md. Use when analyzing papers, specs, or legal docs; when asked to "map this document", "index this PDF", "what does this paper say"; or when a coding agent needs grounded reference material from a PDF source. Analogous to tree-sitting but for prose documents.

Use this Skill: https://skilld.dev/gh/oaustegard/claude-skills/mapping-documents

This session only. Nothing lands on disk.

CHANGELOG.md

≈266 tokens on demand. Your agent reads this file only when SKILL.md points to it.

mapping-documents - Changelog

[0.1.2] - 2026-04-17

Added

  • Add/Update skill: mapping-documents (#551)

[0.1.2] - 2026-04-17

Added

  • README.md with consumption model, three-layer stack diagram, example output, quick start

Changed

  • Version bump across SKILL.md, docmap.py usage snippet template

[0.1.1] - 2026-04-17

Added

  • _USAGE.md output: snippet for pasting into CLAUDE.md / AGENTS.md / project instructions
  • Three-layer progressive-disclosure stack documentation in SKILL.md
  • JSON query examples for symbols and anchors
  • --no-usage-snippet CLI flag

Changed

  • SKILL.md rewritten with "After Generating: Wire It Up" section

[0.1.0] - 2026-04-17

Added

  • Initial release: font-based structural parsing, parallel LLM semantic extraction
  • Genre support: paper, spec, legal
  • Outputs: _MAP.md, .symbols.json, .anchors.json

0.1.3 — 2026-07-26

  • Repointed the structural-analogy reference from mapping-codebases (deprecated) to tree-sitting. This skill's own {stem}_MAP.md document maps are unchanged.

Source: SKILL.md on GitHub

No alerts4mo3 checks · Risk SAFE
  • Gen Agent Trust Hub4mo

    The 'mapping-documents' skill is a tool designed to structure and index PDF documents using font analysis and LLM-based semantic extraction. It securely manages API keys through environment variables and utilizes reputable third-party libraries. No malicious behavior or security vulnerabilities were identified.

  • Socket4mo

    No alerts

  • Snyk4mo

    Risk: LOW · No issues

Signed by skilld at 9141df6. This ties the file your Agent reads to that commit on GitHub. It does not review the instructions.

Last checked against GitHub yesterday.

Activeupdated 2 months ago
metadata
{
  "version": "0.1.3"
}

README badge

README badge for oaustegard/claude-skills/mapping-documents