GitHub
training-resilience
Fix PPO training early-stop issues. Trigger when: (1) impossible drawdown values (>100%), (2) training stops too early, (3) need adaptive recovery instead of hard stop.
smith6jt-cop AI Skills
GitHub ↗Explorez les skills IA publiés de smith6jt-cop et consultez leurs instructions source.
Statistiques de l’auteur
Skills indexés
92Étoiles des dépôts des skills indexés
92Forks du dépôt
0Moyenne des étoiles par skill indexé
1Les étoiles d’un dépôt peuvent se répéter entre ses skills.
Catégories populaires
Indexation récente
Explorer
GitHub
reward-scaling-calibration
Fix phantom MaxDD values in training by calibrating reward_scale. Trigger when: (1) validation MaxDD shows 35-80% values, (2) MaxDD doesn't correlate with training quality, (3) gating thresholds seem too lenien...
GitHub
tile-snake-pattern-stitching
SNAKE vs RASTER tile acquisition patterns for image stitching in KINTSUGI
GitHub
gpu-quality-priority
KINTSUGI processing principles: Never sacrifice quality for speed, always use GPU when available. Trigger: performance optimization, CPU/GPU choice, fast mode, quality vs speed.
GitHub
dashboard-pnl-visualization
Trading dashboard P&L visualization with profit tracker integration, win-rate overlays, R-multiples, and configurable settings
GitHub
conda-multi-account-hipergator
Set up conda with multiple group storage locations on HiPerGator, including cache isolation
GitHub
markov-regime-features
Debugging constant Markov regime features in RL observations - when HMM probabilities show uniform values instead of dynamic regime estimates
GitHub
multiplex-imaging-analysis
Optimizing segmentation feature extraction, SOM clustering, and spatial analysis for multiplex immunofluorescence imaging with cell compartment and ECM features
GitHub
region-aware-matching
Spatial region-aware cell matching for CODEX/scRNAseq integration
GitHub
gpu-memory-cleanup
Preventing Jupyter cell hangs with explicit CuPy GPU memory cleanup
GitHub
per-sector-candidate-filtering
Per-sector candidate limits using yfinance sector data. Trigger when: (1) universe selection has too many candidates, (2) need sector diversity in candidate pool, (3) downloading historical data takes too long.
GitHub
testing-benchmarking-infrastructure
Testing suite with benchmarking for version-to-version performance comparison
GitHub
qc-plot-pdf-export
KINTSUGI quantification plots: Always save QC heatmaps and profiles as PDF
GitHub
large-cell-ratio-matching
MaxFuse parameter tuning for datasets with large protein:RNA cell ratios (>100:1)
GitHub
adaptive-predator-prey
Use when tuning predator-prey dynamics, regime detection coefficients, or cooldown mechanisms
GitHub
parameter-scaling
MaxFuse parameter tuning when protein panel size changes (26 → 59+ markers)
GitHub
cross-modal-normalization
Scale alignment for RNA-protein cross-modal integration - BOTH modalities must be z-scored
GitHub
reward-function-v330
Use when tuning RL reward function weights, fixing reward hacking, or addressing P&L gradient issues
GitHub
integrated-risk-manager
Use when implementing unified position sizing, Kelly criterion, or combining GARCH+Capital+Portfolio risk systems
GitHub
slurm-workflow-integration
Integrating SLURM job submission with kintsugi init for HPC clusters. Trigger: adding SLURM support to projects, auto-detecting HPC settings, CLI batch submission
Le classement utilise les étoiles du dépôt GitHub indexé. Plusieurs skills peuvent partager ce nombre : ce n’est ni un nombre d’installations ni une note de qualité.