# timeline-pdf-notes

Extract timeline entries from PDF operator notes via pdfplumber.

- **Kind:** skill
- **Source:** https://github.com/SpecterOps/skills
- **Page:** https://forefy.com/skills/f7be4753-7490-4cfb-931b-1ce575312198
- **API (JSON + files):** https://forefy.com/api/asr/f7be4753-7490-4cfb-931b-1ce575312198

---

## SKILL.md

---
name: timeline-pdf-notes
description: Extract timeline entries from PDF operator notes via pdfplumber.
metadata:
  author: "GhostWorks"
---

# Timeline PDF Notes Parser

Use when provided operator notes are only available as PDFs.

## Input Contract
- Directory `input/notes/` with `.pdf` files representing operator notes.

## Output
- Write `output/pdf_notes_entries.json` with normalized entries (timestamp, source, operator, action, details, raw_timestamp).

## Workflow
1. Use `pdfplumber` to extract text per page and optional tables.
2. Apply the same timestamp patterns as the Markdown parser; use filename-derived dates/operator context when necessary.
3. Normalize timestamps to UTC and drop duplicates flagged by the consolidator.
4. Track page numbers or table origins in `source`/`details` for traceability.
5. Append `source_type = "pdf_notes"` in metadata with counts and errors.
6. Provide guidance to install `pdfplumber` if missing.

## Notes
- Tables are optional; parse them to capture structured timeline rows when available.
- Handle messy text by cleaning repeated headers/footers.

## agents

```

```

## agents/openai.yaml

```yaml
interface:
  display_name: Timeline PDF Notes
  short_description: Extract timeline entries from PDF operator notes via pdfplumber.
  icon_small: ./assets/icon.svg
  icon_large: ./assets/icon.png
  brand_color: '#8E92EB'
  default_prompt: Use $timeline-pdf-notes for this workflow.
policy:
  allow_implicit_invocation: true
```

## assets

```

```

## assets/icon.png

```

```

## assets/icon.svg

```

```