pytorch-common-pitfalls
Fix common PyTorch bugs: percentile calculations, LayerNorm for Conv1d, buffer edge cases. Trigger when writing PyTorch code for RL or neural networks.
浏览 smith6jt-cop 维护的已发布 AI 技能,比较用途与说明,并通过来源仓库了解安装方式。
已收录技能
92收录技能的仓库 Stars 合计
92仓库 Forks
0平均每个技能的仓库 Stars
1同一仓库中的多个技能可能共享 Stars,合计包含重复仓库数据。
Fix common PyTorch bugs: percentile calculations, LayerNorm for Conv1d, buffer edge cases. Trigger when writing PyTorch code for RL or neural networks.
Persistent data cache with gap-filling for historical market data. Trigger when: (1) cache re-downloads complete data unnecessarily, (2) time-based cache expiry wastes API calls, (3) historical data needs incre...
Consistent drawdown control pattern for trading systems - backtests, live trading, and training
FAIL LOUDLY pattern for selection constraints. Trigger when: (1) correlated stocks selected together, (2) min_crypto_positions ignored, (3) constraints violated silently.
Correct import patterns and file paths for maxfuse Jupyter notebooks
KINTSUGI deconvolution: Output scaling must preserve original intensity relationships for quantitative analysis. Trigger: deconvolution saturates at 65535, channel intensity ratios inverted, hist_clip scaling i...
Cache yfinance sector data permanently to avoid Yahoo Finance rate limits. Trigger when: (1) 401 errors during sector fetching, (2) sector updates take too long, (3) need selective sector refresh.
Specific description with trigger conditions
When editing KINTSUGI notebook modules (Kdecon, Kstitch, Kreg, etc.), always edit the main repo first then sync to project folders
Statistical analysis for selecting trading symbols compatible with mean-reversion/momentum strategies, GARCH risk models, and Markov regime detection
Save backtest results to SQLite database for comparison. Trigger when: (1) tracking backtest history, (2) comparing model performance, (3) querying best backtests.
Fix HOLD bias in RL reward function. Trigger when: (1) model learns to always HOLD, (2) trade rate is too low (
Fix PyPI package name collisions when local package name exists on PyPI
Analysis of crypto-to-crypto vs crypto-to-fiat (USD) trading on Alpaca for fee optimization and risk considerations
Risk managers should SIZE trades, not BLOCK them. Trigger when: (1) capital manager blocks trades, (2) risk manager rejects orders, (3) trades fail due to 'exceeds limit', (4) components don't work in harmony.
SUPERSEDED by persistent-cache-gap-filling (v2.8.0). Cache data during symbol selection for instant repeat runs.
Efficient development testing workflow for HPC environments with VS Code tunneling. Trigger: testing code changes on HPC, development workflow with external data directories, VS Code Remote SSH development
Converting backtest visualizations from bar indices/timesteps to actual datetime axes for clearer time context
Ensure Alpaca API is used for quality data, not yfinance fallback. Trigger when: (1) crypto volume filter fails unexpectedly, (2) zero-volume bars in data, (3) API key configuration issues.
Pattern for connecting Jupyter notebooks in a pipeline via checkpoint files. Trigger: connecting notebooks, saving outputs, multi-notebook pipelines
Model-trader version compatibility protocol: Embed version metadata in checkpoints, validate at load time. Trigger when: (1) training and live trading versions diverge, (2) models fail to load, (3) action inter...
Pattern filter normalization and multi-gate order entry system
Critical fix for backtest capital accounting when equity curves are inflated or drawdown metrics are meaningless
Training improvements: LR warmup, validation intervals, reward weights. Trigger when: (1) training unstable in early epochs, (2) need more validation visibility, (3) model too conservative.
默认按已收录数据中的 GitHub 仓库 Stars 排序。Stars 属于来源仓库,同一仓库的多个技能可能共享相同数值;它反映仓库关注度,不代表单个技能的安装量或质量评分。