Sam-Osian/PFD-toolkit

Analyse Prevention of Future Death (PFD) reports with AI

What's novel

Analyse Prevention of Future Death (PFD) reports with AI

Code Analysis

8 files read · 3 rounds

A Python toolkit that loads, scrapes, screens, and extracts structured insights from UK Prevention of Future Death (coroner's) reports using a combination of web scraping, text normalization, and LLM-powered analysis.

Strengths

Production-quality concurrent LLM orchestration with backoff, semaphores, and structured Pydantic output; genuinely deep domain logic in the three-layer scraping cascade, receiver/area canonicalization, and theme discovery pipeline. The code is well-documented, type-hinted, and architecturally clean with clear separation between data loading, scraping, LLM interaction, and analysis.

Weaknesses

Several core files are monolithic (extractor.py at 60KB, views.py at 227KB, workbench.js at 197KB), and logging configuration is duplicated across modules. The package.json license field (ISC) contradicts the AGPL-3.0 license, and the frontend bundles are unreasonably large.

Score Breakdown

Innovation

6 (25%)

Craft

85 (35%)

Traction

17 (15%)

Scope

81 (25%)

Signal breakdown

Innovation

Not Fork+1

Code Novelty+1

Concept Novelty+2

Craft

Ci+5

Tests+8

Polish+3

Releases+4

Has License+5

Code Quality+24

Readme Quality+15

Recent Activity+7

Structure Quality+4

Commit Consistency+5

Has Dependency Mgmt+5

Traction

Forks+6

Stars+6

Hn Points+0

Watchers+3

Early Traction+0

Devto Reactions+0

Community Contribs+2

Scope

Commits+8

Languages+8

Subsystems+13

Bloat Penalty-10

Completeness+7

Contributors+7

Authored Files+15

Readme Code Match+3

Architecture Depth+7

Implementation Depth+8

Evidence

Commits

567

Contributors

Files

1917

Active weeks

TestsCI/CDREADMELicenseContributing

Repository

Language

Python

Stars

Forks

License

AGPL-3.0