OneResearchClaw: Skill for Cursor

Document Grounding

Convert a raw document into a structured grounding note.

This skill is for document grounding, not a narrative recap. It should produce a stable intermediate note that is easy to read and easy for downstream skills to use.

When to Use

Use this skill when:

• the input is a single document file
• the document may be a PDF, DOCX, Markdown, or TXT file
• you need structured document notes before downstream research or summary work
• the document may contain non-textual evidence such as tables, figures, diagrams, formulas, or code blocks

Do not use this skill when:

• the task is to write a polished final report
• the task is to perform external literature search
• the task is to render output into PDF/DOCX
• the input is a meeting transcript and you want meeting-specific grounding

Input

A single document file.

Supported first-stage formats:

• .pdf
• .docx
• .md
• .txt

The document may contain:

• plain text
• section headings
• tables
• figures / diagrams
• formulas
• code blocks
• captions
• layout / reading-order challenges

Output Bundle

For each input document, create one bundle directory:

data/grounded_notes/<type>-<doc_id>_<timestamp>/

where <type> is the file extension (e.g. pdf, docx, md, txt), <doc_id> is the sanitized filename without extension, and <timestamp> is the Beijing-time execution timestamp (format: YYYYMMDDHHMMSS).

For example:

data/grounded_notes/pdf-paper_name_20260410153022/
data/grounded_notes/docx-notes_001_20260410153100/
data/grounded_notes/md-project_readme_20260410153215/

Inside that bundle, the expected outputs are:

<bundle_dir>/
├─ ground_id.txt       # Ground ID for this unit (reused by all downstream stages)
├─ extracted.md
├─ extracted_meta.json
├─ asset_index.json
├─ grounded.md
└─ assets/
   ├─ tables/
   ├─ figures/
   └─ formulas/

The <ground_id> (e.g. pdf-paper_name_20260410153022) is the single stable identifier for the entire pipeline — all downstream directories (lit_inputs, lit_results, report_inputs, review_outputs, reports, final_outputs) reuse this same <ground_id>.