code
Generate code using coder agents. Use /code for standard tasks, /code --complex for advanced.
发现 部署与运维 相关 Skills,比较来源仓库和用途,查看适合你工作流的技能说明。
Generate code using coder agents. Use /code for standard tasks, /code --complex for advanced.
Workflow for private repos + Colab training. Trigger when: (1) training on Colab with private repo, (2) separating dev from production, (3) avoiding untested code in production.
Low-risk Python performance optimization patterns with verified speedups
Broker position reconciliation pattern for live trading systems
Visualization patterns for sparse single-cell gene expression data. Trigger: boxplots flat at zero, single-cell expression plots, sparse data visualization
Derive selection thresholds from market data instead of hardcoding. Trigger when: (1) reviewing hardcoded parameters, (2) volume/price thresholds seem arbitrary, (3) selection returns too many/few candidates.
GPU-aware PPO training configuration for A100/H100. Trigger when training is slow or GPU utilization is low.
Add account state (P&L, win rate, drawdown) to RL observations + drawdown penalty in rewards. Trigger when: (1) model needs account awareness, (2) training should penalize drawdowns, (3) upgrading obs_dim 5300→...
Remove pattern filters that second-guess RL model predictions. Trigger when: (1) signals show past threshold but status is HOLD, (2) pattern filter blocks model signals, (3) external gates contradict trained mo...
Checklist for editing training code. Trigger when: (1) modifying training notebook, (2) changing GPUEnvConfig, (3) changing reward functions, (4) ANY training-related code changes.
Record prediction outcomes when positions close. Trigger when: (1) predictions logged but outcomes missing, (2) calculating prediction accuracy, (3) tracking model performance.
Fix symbol selection failing due to asset-type filter mismatch. Trigger when: (1) '0/N passed hard filter' error, (2) crypto selection fails unexpectedly, (3) assets filtered by wrong price/volume thresholds.
Fix F821 undefined name errors for optional dependencies using TYPE_CHECKING
Auto-discover dashboard symbols from loaded RL models. Trigger when: (1) dashboard shows old/wrong symbols, (2) symbols mismatch between live trader and dashboard, (3) adding new models to system, (4) dashboard...
Parallel processing for universe selection with 3-4x speedup. Trigger when: (1) selection takes too long, (2) 'No data returned' warnings for cached symbols, (3) need to process 100+ candidates.
Reorganize scattered modules into subpackages while maintaining backwards compatibility via shims. Trigger when: (1) too many root-level files, (2) need to group related functionality, (3) cleaning up codebase...
Use percentage-based capital limits, not hard-coded dollar amounts. Trigger when: (1) trades blocked on small accounts, (2) min_cash_buffer is absolute dollars, (3) capital allocation doesn't scale with account...
KINTSUGI deconvolution: True lightsheet PSF calculation to fix horizontal banding artifacts. Trigger: deconvolution artifacts, horizontal banding, PSF issues, fcyl, slitwidth, lightsheet, LsDeconv.
Example skill demonstrating the registry structure and format
Fix CuPy NVRTC compilation errors on Windows. Trigger: NVRTC_ERROR_BUILTIN_OPERATION_FAILURE, nvrtc-builtins64 not found
Safely review and merge remote branches into stable. Trigger when: (1) reviewing open PRs, (2) integrating feature branches, (3) checking for stale branches with potential conflicts.
Alpaca broker limitations: crypto shorts blocked (broker doesn't support), stock shorts allowed. Trigger when: (1) shorting gate blocks wrong assets, (2) SELL signals blocked, (3) order type confusion.
Multi-format channel name parsing for KINTSUGI CHANNELNAMES.txt files
Colab file paths after unzipping repo. Trigger when: (1) API key file not found, (2) file path errors in Colab, (3) configuring notebook paths, (4) 'yfinance fallback' despite keys existing.
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。