By patolojiAI
Analyzes surgical pathology cancer reports for compliance with CAP and ICCR guidelines. Validates pTNM staging (AJCC 8th edition), checks required-element completeness with severity-based scoring, generates synoptic templates, tumor-board summaries, SNOMED CT / ICD-O-3 codes, free-text→synoptic conversion, and amendments. Breast, colorectal, exocrine pancreas, gastric. English & Turkish.
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
A Claude skill for surgical pathology quality assurance
Analyze cancer pathology reports for compliance with CAP/ICCR guidelines, validate TNM staging, generate synoptic templates, and more. Supports multiple tumor types and languages (English/Turkish).
⬇️ Download .skill · ▶️ Live demo · 🤗 Hugging Face · 🌐 Project website
🎓 Academic project — ECDP2026 oral presentation
This skill is the subject of a study selected for an oral presentation at ECDP2026, the 22nd European Congress on Digital Pathology (Graz, Austria, 17–20 June 2026):
“A Skill for Large Language Models to Evaluate Pathology Report Quality” Balcı P, Ünlü M, Nazlım S, Türkmen İ, Balcı S — Structured Reporting session, 19 June 2026.
100 anonymized Turkish colorectal reports were evaluated with this skill across cloud (Claude) and local (Mistral 7B / Ollama) models, with review by two pathologists. See the abstract, the acceptance notification, and the project website.
| Feature | Description |
|---|---|
| Breast invasive carcinoma | CAP Breast.Invasive + ICCR dataset validation |
| Colorectal resection | CAP ColoRectal + ICCR dataset validation |
| Exocrine pancreas | CAP Panc.Exo + ICCR dataset validation |
| Gastric carcinoma | CAP Stomach + ICCR dataset, HER2/MSI, Laurén/Borrmann |
| Feature | Description |
|---|---|
| Gross description completeness | AAPA guidelines, specimen-specific required elements |
| Gross vs Diagnosis validation | Size, margins, nodes, tumor extent discrepancies |
| Specimen-specific requirements | TME grading, Whipple margins, mastectomy elements |
| Feature | Description |
|---|---|
| Severity scoring | Critical/Major/Minor classification of gaps |
| Empty vs Missing detection | Distinguishes blank fields from absent fields |
| Cross-validation | pT vs size, pN vs node count, margin vs R classification |
| Quality metrics | Completeness, clarity, consistency scores |
| Trend tracking | Historical data for department QA |
| TNM stage calculator | AJCC 8th edition stage verification for all tumor types |
| Synoptic template generator | Generate blank CAP templates with all required fields |
| SNOMED CT / ICD-O-3 coding | Suggest morphology, topography, and procedure codes |
| AAPA Macroscopy | Integrated AAPA protocols in macroscopy files (all 4 tumor types) |
| Tumor board summary | Generate concise 3-5 line MDT summaries from reports |
| Free-text → Synoptic | Convert narrative reports to structured CAP format |
| Auto-fill suggestions | Suggest pT/pN/Stage based on tumor size, node count, findings |
| Amendment generator | Generate addendum/correction/amended report text |
| Watch folder | Auto-process new reports dropped into monitored directory |
| Feature | Description |
|---|---|
| Interactive | Paste report text in chat |
| File mode | Single or multiple report files |
| CLI folder mode | Process folder of images, PDFs, text files |
| CLI spreadsheet mode | Process Excel/CSV with report contents |
| Batch processing | Python script with Claude API |
| Feature | Description |
|---|---|
| Individual QA reports | Detailed per-report analysis |
| Summary statistics | Aggregate compliance metrics |
| CSV export | Structured data for analysis |
| Excel export | Multi-sheet workbook with details |
| Trend history | JSON for longitudinal tracking |
None currently
See .dev/TODO.md for full roadmap.
Coming Soon:
Reports can be in any language. Designed and tested with:
npx claudepluginhub patolojiai/pathology-report-checker-skill --plugin pathology-report-checkerUI/UX design intelligence. 67 styles, 161 palettes, 57 font pairings, 25 charts, 15 stacks (React, Next.js, Vue, Svelte, Astro, SwiftUI, React Native, Flutter, Tailwind, shadcn/ui, Nuxt, Jetpack Compose). Actions: plan, build, create, design, implement, review, fix, improve, optimize, enhance, refactor, check UI/UX code. Projects: website, landing page, dashboard, admin panel, e-commerce, SaaS, portfolio, blog, mobile app. Elements: button, modal, navbar, sidebar, card, table, form, chart. Styles: glassmorphism, claymorphism, minimalism, brutalism, neumorphism, bento grid, dark mode, responsive, skeuomorphism, flat design. Topics: color palette, accessibility, animation, layout, typography, font pairing, spacing, hover, shadow, gradient.
Comprehensive skill pack with 66 specialized skills for full-stack developers: 12 language experts (Python, TypeScript, Go, Rust, C++, Swift, Kotlin, C#, PHP, Java, SQL, JavaScript), 10 backend frameworks, 6 frontend/mobile, plus infrastructure, DevOps, security, and testing. Features progressive disclosure architecture for 50% faster loading.
This skill should be used when users need to generate ideas, explore creative solutions, or systematically brainstorm approaches to problems. Use when users request help with ideation, content planning, product features, marketing campaigns, strategic planning, creative writing, or any task requiring structured idea generation. The skill provides 30+ research-validated prompt patterns across 14 categories with exact templates, success metrics, and domain-specific applications.
Develop, test, build, and deploy Godot 4.x games with Claude Code. Includes GdUnit4 testing, web/desktop exports, CI/CD pipelines, and deployment to Vercel/GitHub Pages/itch.io.
Upstash Context7 MCP server for up-to-date documentation lookup. Pull version-specific documentation and code examples directly from source repositories into your LLM context.
A growing collection of Claude-compatible academic workflow bundles. Covers scientific figures, manuscript writing and polishing, reviewer assessment, citation retrieval, data availability, paper reading, literature search, response letters, paper-to-PPTX conversion, and evidence-grounded Chinese invention patent drafting. Rules are organized as reusable skill folders with explicit workflows and quality checks.