Agent skill
pdf-reader
Reads PDF, DOCX, and image text (OCR) and can pinpoint schedule lines from syllabus documents. Use when the user asks to extract text from docs/images or analyze deadlines and class schedules.
Install this agent skill to your Project
npx add-skill https://github.com/majiayu000/claude-skill-registry/tree/main/skills/other/other/pdf-reader
SKILL.md
PDF + OCR Reader Skill
Use this skill for document extraction and schedule pinpoints.
What it supports
- PDF text extraction (
pdftotext) - DOCX text extraction (
word/document.xml) - Image OCR (
tesseractif available, otherwise macOS Vision OCR via Swift) - Syllabus schedule/deadline pinpoint analysis
Commands
# Legacy PDF-only command
node "{baseDir}/scripts/read_pdf.mjs" --file "/path/to/your/document.pdf"
# Unified reader (PDF/DOCX/Image) + optional schedule analysis
python3 "{baseDir}/scripts/read_docs.py" \
--path "$HOME/Desktop/syllabus" \
--analyze-schedule \
--save "$HOME/Desktop/syllabus/syllabus_schedule_report.md" \
--json-out "$HOME/Desktop/syllabus/syllabus_schedule_report.json"
# Shortcut wrapper for syllabus folder
bash "$HOME/openclaw_pro/workspace/scripts/syllabus_pinpoint.sh" \
"$HOME/Desktop/syllabus"
Output contract
ANALYSIS_STATUS=ok|errorFILES_SCANNED=...EVENTS_FOUND=...REPORT_MD=...REPORT_JSON=...PINPOINT_TOP_START ... PINPOINT_TOP_END
Notes
- OCR quality is highest on clear images (300dpi+).
- For scanned PDFs, OCR fallback uses
pdftoppm+ OCR. - If OCR backend is unavailable, script still returns extracted text from readable PDFs/DOCX.
Recommended Agent Skills
Expand your agent's capabilities with these related and highly-rated skills.
majiayu000/claude-skill-registry
agent-ops-spec
Manage specification documents in .agent/specs/. Use when user provides requirements, acceptance criteria, or feature descriptions that need to be tracked and validated against implementation.
majiayu000/claude-skill-registry
agent-ops-state
Maintain .agent state files. Use at session start, after meaningful steps, and before concluding: read/update constitution/memory/focus/issues/baseline consistently.
majiayu000/claude-skill-registry
agent-ops-spec
Manage specification documents in .agent/specs/. Use when user provides requirements, acceptance criteria, or feature descriptions that need to be tracked and validated against implementation.
majiayu000/claude-skill-registry
agent-ops-testing
Test strategy, execution, and coverage analysis. Use when designing tests, running test suites, or analyzing test results beyond baseline checks.
majiayu000/claude-skill-registry
agent-ops-testing
Test strategy, execution, and coverage analysis. Use when designing tests, running test suites, or analyzing test results beyond baseline checks.
majiayu000/claude-skill-registry
agent-ops-state
Maintain .agent state files. Use at session start, after meaningful steps, and before concluding: read/update constitution/memory/focus/issues/baseline consistently.
Didn't find tool you were looking for?