GitHub
dataclass-optimization
Python dataclass best practices: slots, frozen, validation. Trigger when optimizing dataclasses or creating config classes.
Skills IA Documentation
Découvrez les skills Documentation, comparez leurs dépôts et consultez leurs instructions.
Catégories: Documentation
Documentation Effacer les filtres
Explorer
GitHub
multi-agent-integration
Integrate Claude agents into training and live trading (v3.0). Trigger when: (1) setting up multi-agent training, (2) adding agent consultation to live trading, (3) configuring orchestrator, (4) understanding a...
GitHub
network-architecture-sizing
PPO network architecture sizing for trading models. Trigger: (1) model files are unexpectedly small/large, (2) choosing hidden_dims for training, (3) balancing model capacity vs inference speed.
GitHub
skills-registry-organization
Pattern for organizing Skills Registry as a shared submodule across projects
GitHub
persistence-layer-audit
Audit SQLite persistence layer for unused tables and broken integrations. Trigger when: (1) checking database usage, (2) cleaning up schema, (3) finding missing methods.
GitHub
dependency-deprecation
Pattern for deprecating external dependencies while maintaining backward compatibility. Trigger: removing Java/FIJI/MATLAB, deprecating optional deps
GitHub
plotly-figurewidget-interactive
Fix for Plotly FigureWidget KeyError: 'uid' when updating shapes with sliders. Trigger: interactive Plotly dashboard errors, FigureWidget batch_update issues
GitHub
dotted-symbol-exclusion
Exclude ALL dotted symbols from yfinance sector lookups and training. Trigger when: (1) yfinance errors on warrants/units/class shares, (2) training notebook fails on excluded symbol types, (3) adding new symbo...
GitHub
notebook-config-audit
Audit Jupyter notebooks for hardcoded values that contradict configuration cells. Trigger when: (1) notebook behavior differs from documented settings, (2) updating notebook version, (3) finding inconsistent va...
GitHub
basic-caching-evaluation
Evaluation of BaSiC illumination correction caching - NOT RECOMMENDED for sparse markers. Trigger: optimizing BaSiC, caching illumination correction
GitHub
training-archive-gating
Mandatory training archive with model gating (APPROVED/REVIEW/DROP). Trigger when: (1) training run completes, (2) need to decide which models to deploy, (3) want historical training reference, (4) need checkpo...
GitHub
gpu-parallel-scheduling
GPU-safe parallel processing patterns for KINTSUGI to prevent OOM crashes and ensure Jupyter-compatible progress output
GitHub
multi-timeframe-training
Train RL models across multiple timeframes with resampling. Trigger when: (1) multi-timeframe training, (2) resampling data, (3) creating 1Hour/4Hour models.
GitHub
selection-progress-reporting
Progress reporting for universe selection phases. Trigger when: (1) selection appears to stall/hang, (2) no output after data fetching, (3) need visibility into hard filter or scoring phases.
GitHub
position-sizing-action-space
7-action space with position sizing (25/50/75%) + small account simulation. Trigger when: (1) model needs sizing decisions, (2) training for 5900.
GitHub
alpaca-algo-plus-data
Use Alpaca Algo Trader Plus for 4+ years of historical data. Trigger when: (1) increasing lookback, (2) data source selection, (3) yfinance comparison.
GitHub
gpu-correlation-caching
GPU-accelerated correlation matrix computation with persistent SQLite caching to eliminate bottleneck at correlation calculation during symbol selection
GitHub
github-copilot-pr-review
Review and apply GitHub Copilot suggestions on pull requests. Trigger when reviewing PRs with Copilot suggestions.
GitHub
project-data-separation
Pattern for separating repository code from user data and notebooks. Trigger: organizing scientific pipelines, separating code from data
GitHub
notebook-module-refactoring
Safe refactoring of Jupyter notebook code into Python modules
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.
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.
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.