evsys-sdk
01Plugin Claude Code
EvolvingSystems training tooling: evsys-sdk usage skills for the autoresearch loop.
Plugin Claude Code
EvolvingSystems training tooling: evsys-sdk usage skills for the autoresearch loop.
Plugin Claude Code
evsys-sdk usage skills for the autoresearch loop: read a project's goal and experiment history, decide the next experiment, scaffold and launch it, and read/write experiments, datasets, benchmarks, and metrics via the SDK.
Command Claude Code
You are helping the user train an LLM locally using the evsys-sdk. Follow these steps carefully.
Hook Claude Code
Runs when a session starts on startup and resume, executing claude-session-start.sh. From ev-sys/evsys-sdk.
Settings file Claude Code
Agent settings declaring 1 hook event (SessionStart).
Skill Claude CodeCodex
How to pull history of past experiments, generations, eval results, predictions, and rendered training data from the EvolvingSystems dashboard backend — so you can build on prior runs instead of starting cold. Use before proposing a new hypothesis or recipe.
Skill Claude CodeCodex
Scaffold or migrate a repo to the evsys-sdk research-project layout (data/, src/, experiments/, .evsys/). Use when starting a new project that will use the SDK, or when the user has an existing ad-hoc evsys-sdk project (loose training/ scripts, scattered data files) they want to bring into the standard shape.
Skill Claude CodeCodex
How to push training runs (SFT/RL/distillation) to the EvolvingSystems dashboard. Use when writing experiment scripts that should appear in the dashboard, or when wiring metrics/predictions/conclusions into an existing training loop.
Instructions file
Claude Code instructions for ev-sys/evsys-sdk, covering working in this repo, two skills directories (deliberately not synced), dev workflow and useful entry points.
Skill Claude CodeCodex
Decide which training experiment to run next for a project and launch it. Use when the user floats a training idea ("is a smaller model as good as a larger one on this benchmark?", "should we try more SFT data?", "what should we run next?") or asks to design/launch/continue experiments. Reads the project goal + past…
Skill Claude CodeCodex
Push and browse project HTML reports on the EvolvingSystems dashboard via the evsys CLI / EvsysStore. Use when an agent (or researcher) needs to write or upload a static HTML report, name it, inspect the project's report filesystem tree, pick a path, or share a viewer URL with a logged-in project member. Reports are…
Skill Claude CodeCodex
How to use the evsys-sdk SDK to read project goals + experiment history and to create/launch experiments: EvsysStore (backend-routed data access) and Workspace (local dataset cache). Use when writing code that reads or writes experiments/runs/datasets/benchmarks/metrics, or materializes data for training.