Menu
Read, search, extract, or render PDFs, including page-specific or visual questions.
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Based on SOC occupation classification
Pi extensions and tool policy: extensions/*.ts, hooks, registerTool, promptGuidelines, registerCommand, footer/status UI, tool_result, session hooks, or subprocesses. Not for slash-command placement; use pi-command.
README, CHANGELOG, docs/, RFCs, ADRs, guides, or Markdown structure. Not for prose cleanup or archival work.
Prose cleanup for filler, hype, vague claims, repetition, detection tells, or uncited specifics. Not for Markdown architecture or archival work.
Requirements, user stories, acceptance/verification criteria, or testable outcomes. Not for PRD drafting (/prd) or Pi /goal prompts.
Use for /prd-it or to draft, refine, or review a Product Requirements Document. Not for acceptance criteria, planning, or Pi /goal prompts.
Pi session, trace, metrics, routing, workflow-friction, workflow-telemetry, usage, or local JSONL analysis with DuckDB. Use for aggregating or correlating Pi runtime logs. Not for adding telemetry, generic SQL/database design, or non-Pi logs.
| name | pdf-reader |
| description | Read, search, extract, or render PDFs, including page-specific or visual questions. |
Routing card for hybrid PDF text extraction and rendered-page reading.
Use uv; do not create a persistent virtualenv.
uv run --with pymupdf SKILL_DIR/scripts/pdf_info.py <path>
uv run --with pymupdf SKILL_DIR/scripts/pdf_extract.py <path> --pages 1-5
uv run --with pymupdf SKILL_DIR/scripts/pdf_search.py <path> "theorem 3.2" --context 3
uv run --with pymupdf SKILL_DIR/scripts/pdf_render.py <path> --pages 3 --dpi 150
Page specs are 1-indexed: all, 1-5, 1,3,7, or 3.
pdf_info.py.read tool.