Skills & Report Quality
Claude skills and LLM-backed tools for scoring, checking, and rewriting pathology reports
https://github.com/sbalci/pathology-report-checker-skill
https://github.com/sbalci/pathology-report-colon-QA
https://github.com/sbalci/pathology-report-checker-skill
Skill catalog
| Skill | Purpose | Repo |
|---|---|---|
| Report checker | CAP/ICCR compliance scoring of synoptic elements | pathology-report-checker-skill |
| Colon QA | Narrative-to-synoptic gap analysis for colon resections | pathology-report-colon-QA |
| Pathology skills collection | Summaries, translations, lay-language rewrites | pathology-skills-collection |
| Scientific skills | Literature search, citation, figure generation | claude-scientific-skills |
| n8n pathology | Workflow glue across the skills above | n8n-pathology |
In the research wiki
- LLM Report-Quality Checking — the method page for these skills, and how LLM scoring fails differently from a rule engine.
- LLM Adaptation Techniques — the ladder from a plain prompt to a fine-tuned model, and what each rung costs before it buys anything.
- askLLM — the best-measured example in this wiki of grounding suppressing hallucination: sending the real catalogue instead of letting the model invent one took it from three structural fabrications to 18 of 18 correct. The same trick is what these checkers should try next.
- Synoptic Reporting — the CAP/ICCR structure the checkers score against.
- Model Abstention — a skill that declines to answer changes the denominator; coverage belongs beside every accuracy figure.
- Pathology Report Checker Skills — the repository’s pointer page.