What is quant-paper-extractor?

A tool for turning quantitative research report PDFs into Markdown text and structured JSONL records. Quantitative research reports use data and statistical methods to study topics such as trading strategies.

Use it to process batches of quantitative research PDFs, create searchable knowledge-base records, and capture fields such as title, abstract, method, experiments, and results.

It removes the need to manually convert reports and copy their key information into a consistent format. A manifest tracks which files have been processed.

quant-paper-extractor — Skill by CamusGIT

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods

npx agentmods add skills/camusgit/evoquant/quant-paper-extractor

Any agent

npx skills add CamusGIT/EvoQuant --skill quant-paper-extractor

Clone the repo

git clone --depth 1 https://github.com/CamusGIT/EvoQuant

Made for: Claude Code, Codex.

Per session 105 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,913 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. Scan, not verified.

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5	$0.00105	$0.01913
Opus 5	$0.00053	$0.00957
Sonnet 5	$0.00021	$0.00383
Haiku 4.5	$0.00011	$0.00191

Measured 2d ago against content hash 12da163eb9c0, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

quant-paper-extractor scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.

The scan reads SKILL.md. This mod also ships 3 executable files (scripts/extract.py, scripts/manifest.py, scripts/pdf_to_markdown.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

EvoQuant/skills/quant-paper-extractor/SKILL.md · 219 lines

How it starts

The opening of the file, as written. The whole thing — 219 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Quant Paper Extractor

Batch-convert quantitative research report PDFs (量化研究研报) to structured JSONL records. Two-phase pipeline: PDF → Markdown → JSONL.

rawpaper/*.pdf
      │
      ▼ Phase 1: PDF → Markdown (pdf_to_markdown.py)
markdown/{sha256}.md
      │
      ▼ Phase 2: Markdown → JSONL (agent-driven extraction)
wiki/{sha256}.jsonl

Setup

Scripts at scripts/. Run via python scripts/<name>.py.

Install dependencies:

pip install -e .

Pre-conditions

Working directory must contain these sibling directories:

rawpaper/    ← user places PDF files here
markdown/    ← auto-created; stores converted markdown files
wiki/        ← auto-created; stores extracted JSONL files

Create markdown/ and wiki/ if they don't exist:

mkdir -p markdown/ wiki/

A manifest.jsonl file will be created at the working directory root to track processing state.

Phase 1: PDF → Markdown

Run the conversion script (fully automated, no LLM needed):

python scripts/pdf_to_markdown.py \
  --rawpaper-dir rawpaper/ \
  --markdown-dir markdown/ \
  --manifest-path manifest.jsonl

This script:

Scans all .pdf files in rawpaper/
Computes SHA-256 hash of each PDF's binary content → paperId
Incremental skip: if markdown/{paperId}.md already exists, skip
Extracts text via three-tier fallback:
- pymupdf4llm.to_markdown() — native Markdown output (best quality)
- pymupdf.open() → page.get_text() — plain text with page headers
- pypdf.PdfReader() → page.extract_text() — last resort
Hard-truncates at 120,000 characters
Writes structured Markdown to markdown/{paperId}.md
Updates manifest.jsonl with status

Read the script's stdout for per-file success/failure reports.

Phase 2: Markdown → JSONL

The agent (you) performs the extraction reasoning. The extract.py script prepares context and validates output.

Step 2.1: List unextracted markdowns

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

Read the full file on GitHub · 219 lines

Files

What ships with it

9 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

2d ago First seen · 219 lines · 105 tokens per session scan A 12da163eb9c0

Subscribe to this mod's changes

quant-paper-extractor is a skill published in the GitHub repository CamusGIT/EvoQuant (215 stars, last pushed 15d ago), licensed Apache-2.0. It adds 105 tokens to every session and 1,913 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Memory and context Multi-Agent Research ai-agent alpha auto-research quant quant-research

agent-harness-fault-injection

Use when an agent workflow needs deterministic recovery evidence for sandbox, MCP/tool, worker, checkpoint, memory, or orchestration failures.

sickn33/agentic-awesome-skills · 34 tokens

foundry-config-setup

Resolve missing setup caused by a hardcoded Foundry project endpoint or model in a sample. Use when a sample fails because it uses a placeholder/hardcoded projectendpoint (for example "https://your-project.services.ai.azure.com") or a hardcoded model instead of reading them from the environment.

microsoft/agent-framework · 65 tokens

oma-scholar

Scholarly research companion using Knows sidecar spec (.knows.yaml). Generates, validates, reviews, queries, and compares structured research-paper sidecars, and fetches them from knows.academy. Use for academic literature search, survey synthesis, paper authoring assistance, and peer review with token-efficient…

first-fluke/oh-my-agent · 73 tokens

quant-paper-extractor