tadams95/bma-data-check
.claude/skills/bma-data-check/SKILL.md
Check if enough source_accuracy data has accumulated for BMA Phase 2
testing
Updated Apr 15, 2026
$ install --global
skillsauthnpx skillsauth add tadams95/kardashev-network bma-data-checkInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
Security Scan Results
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
3
Scanners Passed
9
Scanners in report
Clean
TrivyContainer and dependency vulnerability scanner
95%
Clean
SemgrepStatic code analysis for vulnerabilities
95%
Clean
mcp-scan (Snyk)Model Context Protocol security validation
95%
Skipped
Snyk (dep)Open source security scanning
50%
Skipped
Socket.devSupply chain security analysis
50%
Skipped
VirusTotalMulti-engine malware detection
50%
Skipped
CrowdStrikeAdvanced threat intelligence
50%
Skipped
OSV-ScannerOpen Source Vulnerability database check
50%
Skipped
OWASP Dep-Check
50%
Last scanned: Apr 15, 2026, 4:12 AM4.6s1 file scanned
SKILL.md
- name:
- bma-data-check
- description:
- Check if enough source_accuracy data has accumulated for BMA Phase 2
BMA Data Readiness Check
Query production MongoDB to check whether per-source accuracy data is sufficient for BMA (Bayesian Model Averaging) Phase 2 implementation.
Context
BMA requires per-source sigma_i (error standard deviation) per lead-time bucket. Each bucket needs >= 30 events for a reliable estimate. As of 2026-03-13, the <=18h bucket had only 9 events.
Steps
- SSH into the droplet and run the lead-bucket aggregation query:
ssh [email protected] "mongosh '$MONGODB_URI' --quiet --eval '
db.source_accuracy.aggregate([
{ \$match: { absError: { \$exists: true, \$lte: 25 } } },
{ \$addFields: {
leadBucket: {
\$switch: {
branches: [
{ case: { \$lte: [\"\$leadHours\", 18] }, then: \"<=18h\" },
{ case: { \$lte: [\"\$leadHours\", 30] }, then: \"18-30h\" },
{ case: { \$lte: [\"\$leadHours\", 42] }, then: \"30-42h\" }
],
default: \">42h\"
}
}
}},
{ \$group: {
_id: { source: \"\$source\", leadBucket: \"\$leadBucket\" },
count: { \$sum: 1 },
rmse: { \$sqrt: { \$avg: { \$pow: [\"\$absError\", 2] } } },
mae: { \$avg: \"\$absError\" }
}},
{ \$sort: { \"_id.source\": 1, \"_id.leadBucket\": 1 } }
]).forEach(r => print(JSON.stringify(r)))
'"
- Report results in a table: Source | Lead Bucket | Count | MAE | RMSE
- Highlight any bucket with count < 30 (blocking BMA)
- Calculate estimated days until the <=18h bucket reaches 30 events based on current accumulation rate (~82 records/day across all buckets)
- Give a clear verdict: Ready or Not ready (need ~N more days)
Related Skills
tadams95/wagmi-viem
development
VerifiedTrustedCommunity
Web3 integration with wagmi and viem - wallet connection, contract interactions, transactions, RainbowKit. Use when implementing wallet features, reading/writing contracts, or handling blockchain transactions.
SKILL.mdUpdated Apr 15, 2026
tadams95/threejs-textures
content-media
VerifiedTrustedCommunity
Three.js textures - loading, configuration, UV mapping, environment maps. Use when loading images, configuring texture properties, or working with HDR environments.
SKILL.mdUpdated Apr 15, 2026
tadams95/threejs-shaders
data-ai
VerifiedTrustedCommunity
Three.js shaders - GLSL, ShaderMaterial, uniforms, custom effects. Use when creating custom visual effects, modifying vertices, writing fragment shaders, or extending built-in materials.
SKILL.mdUpdated Apr 15, 2026
tadams95/threejs-postprocessing
testing
VerifiedTrustedCommunity
Three.js post-processing - EffectComposer, bloom, depth of field, custom passes. Use when adding visual effects, screen-space effects, or enhancing rendered output.
SKILL.mdUpdated Apr 15, 2026