| Dimension | Shared | Only in A | Only in B | Overlap |
|---|---|---|---|---|
| Sections | 0 | 1 | 1 | 0% |
| Commands | 0 | 0 | 0 | — |
| Section tags | 0 | 1 | 1 | 0% |
What each file covers
Sections
0 shared · 1 only in A · 1 only in B- − Supabase Instructions
- + ML Rules
Commands
neither file has anySection tags
0 shared · 1 only in A · 1 only in B- − agent-behaviour
- + do-not
Line diff
Aledon8/OpenLeukemia · .github/instructions/supabase.instructions.md
@@ −1 @@
1---
2applyTo: "supabase/**/*"
3---
4
5# Supabase Instructions
6
7- Use Supabase for auth, CRUD, storage, consent records, RLS, and lightweight Edge Functions.
8- Keep heavy ML, OCR, extraction, parsing, and model workflows in `ai-service`.
9- Treat RLS as a primary protection layer.
10- Pair sensitive tables with narrow, auditable policies.
11- Plan affected data flows and access paths before schema or policy changes.
12
Aledon8/OpenLeukemia · .cursor/rules/ml.mdc
@@ +1 @@
1---
2description: ML workspace rules
3globs:
4 - "ml/**/*"
5alwaysApply: false
6---
7
8# ML Rules
9
10- Keep structured ML workflows separate from LLM explanation workflows.
11- Use measurable criteria: split, metric, threshold, calibration, and known failure modes.
12- Do not commit patient-identifying or sensitive medical data.
13- Model outputs support signals and trends, not diagnosis or treatment guidance.
14- Document label assumptions, cohort limitations, and evaluation caveats near relevant code or reports.
15
@@ −1 +1 @@
11 ---
2−applyTo: "supabase/**/*"
2+description: ML workspace rules
3+globs:
4+ - "ml/**/*"
5+alwaysApply: false
36 ---
47
5−# Supabase Instructions
8+# ML Rules
69
7−- Use Supabase for auth, CRUD, storage, consent records, RLS, and lightweight Edge Functions.
8−- Keep heavy ML, OCR, extraction, parsing, and model workflows in `ai-service`.
9−- Treat RLS as a primary protection layer.
10−- Pair sensitive tables with narrow, auditable policies.
11−- Plan affected data flows and access paths before schema or policy changes.
10+- Keep structured ML workflows separate from LLM explanation workflows.
11+- Use measurable criteria: split, metric, threshold, calibration, and known failure modes.
12+- Do not commit patient-identifying or sensitive medical data.
13+- Model outputs support signals and trends, not diagnosis or treatment guidance.
14+- Document label assumptions, cohort limitations, and evaluation caveats near relevant code or reports.
1215
