Codex compatibility note:

Invoke $skill-name: load the registered .agents/skills/<name>/SKILL.md and execute it with Codex tools; no separate Skill tool or Claude mode switch is needed. Author .claude/**; mirrors are generated.

Track steps before execution and keep progress/evidence current. Explicit skill requests execute their protocol. Use the native question tool for required questions.

Map foreign tool names to available host capabilities. A name mismatch needs no approval; an actually unavailable required capability stops with its step/evidence and a user question before adaptation.

Subagent authorization: when a skill is user-invoked or AI-detected and its protocol requires subagents, that skill activation authorizes use of the required spawn_agent subagent(s) for that task.

Preserve protocol order unless the user approves a deviation. Workflows use $start-workflow: gates stay fixed; other steps may flex with logged reasons and evidence.

Quick Summary

Goal: Convert PDF to Markdown, or Markdown to PDF, through one entry point.

Summary: Select the required direction → probe its dependencies → install only if missing → convert → check JSON status and the output file. Native text extraction and PDF rendering are supported; scanned-PDF OCR is unavailable.

Workflow:

Pick a direction — --to markdown (PDF in, Markdown out) or --to pdf (Markdown in, PDF out)
Check that direction — probe its dependencies; each has its own package.json, so install only missing dependencies for the selected direction
Convert — run scripts/convert.cjs --to <direction> with the direction's own options
Output — the converter returns JSON with the success status and output path

pdf-convert

Quick Summary