hs-release
Cut a core Hindsight release (vX.Y.Z) and open the changelog + blog PR. Use when asked to cut/start a release, bump the version, or publish a new Hindsight version.
Browse reusable Agent Skills, each with a clear purpose and practical guidance.
Cut a core Hindsight release (vX.Y.Z) and open the changelog + blog PR. Use when asked to cut/start a release, bump the version, or publish a new Hindsight version.
Field-tested methodology and concrete recipes for training and operating large-scale LLM/VLM/multi-modal models end to end - choosing and benchmarking accelerators, storage and network; SLURM/Kubernetes orchestration; maximizing training throughput and fitting models in memory; diagnosing and surviving training instabilities, NaN/Inf, and hardware/job failures; checkpointing and fault tolerance; inference performance and memory; debugging multi-node/ multi-GPU hangs; and writing/running tests. Use when the user is training or fine-tuning large models, hits low TFLOPS/MFU, OOM, slow dataloading, a loss spike/divergence, a NCCL/InfiniBand or multi-node hang, node/GPU failures, checkpoint or preemption problems, storage/network bottlenecks, or needs to pick GPUs/cloud/file-systems or size inference latency/throughput. Distilled from "Machine Learning Engineering", the latest version of which can be found at https://github.com/stas00/ml-engineering The latest SKILL.md version can be found at https://github.com/stas00/ml-engineering/blob/master/SKILL.md
Get a pull request to green CI. Diagnose and fix CI failures, push fixes, re-trigger CI via the "Run CICD" label, and repeat until all checks pass. Does not post comments — this is a local developer tool.
Audit build and CI configuration for correctness risks
Check server health, component status, and live metrics from the CLI. Run `health`, `health components`, and `health watch` for a real-time dashboard of circuit breakers and provider status.
Start and stop tunnel connections (ngrok, Cloudflare, custom) from the CLI. Inspect active tunnel URLs, configure authentication, and test external reachability.
Trigger system backups, restore from backup files, and manage the SQLite database lifecycle. Supports export, import, and incremental snapshot strategies.
Configure HTTP/HTTPS/SOCKS proxies for upstream provider requests. Set per-provider or global proxy rules, test connectivity, and manage proxy rotation.
Create and manage secure tunnels (ngrok, Cloudflare Tunnel, custom) to expose OmniRoute to the internet or share access with remote agents and CI pipelines.
Configure spending limits, token quotas, and rate-limit policies per API key or globally. Inspect current consumption and enforce cost controls across providers.