en un clic
DoclingDotNet
DoclingDotNet contient 9 skills collectées depuis sparkeh9, avec une couverture métier par dépôt et des pages de détail sur le site.
Skills dans ce dépôt
Run the one-command Docling upstream upgrade workflow: fetch latest upstream, port local delta, validate, and record baseline metadata.
Keep docs lean: append concise iteration summaries, and only update docs/changelog for milestone or contract/workflow changes.
Recover from hung command sessions using targeted process discovery/termination and add anti-hang guards.
Enforce concise iteration logging: summary entry in docs/operations/progress.md, minimal docs/changelog churn.
Enforce bottom-up vertical-slice completion checks before advancing to higher-layer features.
Break repeated debug loops by enforcing hypothesis-driven attempts, loop budgets, and evidence logging.
Prevent PowerShell/native command false failures by capturing stdout/stderr explicitly and gating on exit code.
Reference guide and workflow for highly optimized image-to-tensor preprocessing for ONNX models (specifically RT-DETR) in .NET.
Strict workflow for porting Python algorithms (numpy, pandas, rtree, dict manipulation) to high-performance, zero-allocation C# equivalents.