Quant Paper Extractor

What it does

When your agent uses it

• : adding quant research PDFs to the knowledge base
• Extracting structured data from reports
• : academic paper search (use paper-navigator)
• Idea generation (use research-ideation)

Example prompts

• “/quant-paper-extractor”

Requirements

• Python 3
• Pre-approved tools (allowed-tools): write_file, edit_file, read_file, think_tool, execute

Workflow steps

3 steps, taken from the step headings in SKILL.md.

1. 1PDF → Markdown
2. 2Markdown → JSONL
3. 3Refresh derived artifacts & verify

What it can do on your machine

Read from SKILL.md and the folder at commit ac1c4b8. It shows what the files ask for, not the result of running them.

• Tool permissions

  Pre-approves these tools, so the agent can use them without asking each time:

  • write_file
  • edit_file
  • read_file
  • think_tool
  • execute

  From allowed-tools in the SKILL.md frontmatter.

• Runs code

  Ships 3 files in scripts/ (Python), which the agent can run.

  Shell commands in SKILL.md call:

  • python
  • pip

  From the folder's file list and the shell code blocks in SKILL.md.

• Network

  No URLs in SKILL.md. Its commands use pip, which can reach the network depending on how they are called.

  From URLs in SKILL.md, links to its own repository left out.

• Credentials

  Names no API keys, tokens, secrets or passwords.

  From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Quant Paper Extractor loads about 2.4k tokens when it runs, and up to ~6.7k if it reads all its reference files. Until then it costs about 151 tokens; SKILL.md has 854 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it

~151

When it runs · the whole SKILL.md, loaded when a task matches

~2.4k

With references · SKILL.md plus every file in references/, read only if the agent opens them

~6.7k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.

SKILL.md

The full file from CamusGIT/EvoQuant at commit ac1c4b8, republished under its Apache-2.0 licence (© CamusGIT). 854 words, ~2,367 tokens.

name

quant-paper-extractor

description

Convert quantitative research report PDFs to markdown, then extract structured knowledge (paperId, title, year, source, keywords, tldr, abstract, strategy, method, experiment, result) into JSONL paper cards. Writes into the repo papers directory (papers/raw, papers/markdown, papers/cards) and refreshes context_brief.md + index.jsonl. Use when: adding quant research PDFs to the knowledge base, extracting structured data from reports. Do NOT use for: academic paper search (use paper-navigator), idea generation (use research-ideation), literature surveys (use research-survey).

allowed-tools

write_file, edit_file, read_file, think_tool, execute

metadata.author

quant-research-team

metadata.version

1.0.0

metadata.tags

quant, pdf-extraction, structured-data, jsonl, batch-processing

papers/raw/{paperId}.pdf
      │
      ▼ Phase 1: PDF → Markdown (pdf_to_markdown.py)
papers/markdown/{paperId}.md
      │
      ▼ Phase 2: Markdown → card (agent-driven extraction)
papers/cards/{paperId}.jsonl
      │
      ▼ Phase 3: refresh derived artifacts
papers/context_brief.md + papers/index.jsonl

PAPERS=$(python -c "from EvoQuant.papers.paths import resolve_papers_dir; print(resolve_papers_dir())")

$PAPERS/raw/       ← PDFs, renamed to {paperId}.pdf (see Red Line 8)
$PAPERS/markdown/  ← auto-created; converted markdown
$PAPERS/cards/     ← auto-created; extracted JSONL cards
$PAPERS/manifest.jsonl  ← processing-state ledger

mkdir -p "$PAPERS/cards"

python scripts/pdf_to_markdown.py \
  --rawpaper-dir "$PAPERS/raw" \
  --markdown-dir "$PAPERS/markdown" \
  --manifest-path "$PAPERS/manifest.jsonl"

python scripts/manifest.py list \
  --manifest-path "$PAPERS/manifest.jsonl" --status markdown_done

python scripts/extract.py prepare \
  --markdown-file "$PAPERS/markdown/{paperId}.md"

python scripts/extract.py validate \
  --record "$PAPERS/cards/{paperId}.jsonl"

python scripts/manifest.py rebuild \
  --rawpaper-dir "$PAPERS/raw" \
  --markdown-dir "$PAPERS/markdown" \
  --wiki-dir "$PAPERS/cards" \
  --manifest-path "$PAPERS/manifest.jsonl"

python -m EvoQuant.papers.refresh
python scripts/extract.py validate \
  --wiki-dir "$PAPERS/cards" --manifest-path "$PAPERS/manifest.jsonl"

Extraction complete:
  PDFs scanned:     N
  Markdown created: M (K skipped, already existed)
  JSONL created:    P (Q skipped, already existed)
  Errors:           E
  Warnings:         W (short markdown, empty fields, etc.)

© CamusGIT, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 9 other files (scripts, references, assets) in EvoQuant/skills/quant-paper-extractor of CamusGIT/EvoQuant.

• SKILL.md
• assets/extraction-prompt.md
• assets/jsonl-record-template.json
• references/error-handling.md
• references/field-definitions.md
• references/quant-report-structure.md
• references/two-pass-extraction.md
• scripts/extract.py
• scripts/manifest.py
• scripts/pdf_to_markdown.py

Open the folder on GitHubat commit ac1c4b8