report
The report skill renders a colored terminal scatter plot of experiment scores across all runs in the workspace, mirroring the web dashboard's visualization with status-based dot colors, best-path highlighting, and a cumulative-best stair line. Use it when the user requests a quick score chart inline in chat, invokes /evo:report, or needs the scatter plot output without opening the dashboard interface.
git clone --depth 1 https://github.com/evo-hq/evo /tmp/report && cp -r /tmp/report/plugins/evo/skills/report ~/.claude/skills/reportSKILL.md
# Report Render the dashboard's scatter plot as a colored terminal block, one chart per run, sized to the current terminal. ## What it shows Mirrors the web dashboard's score scatter (left rail of `evo dashboard`): - X = experiment creation order, Y = score - Dot color by status: green = committed, red = failed, purple = active, grey = pending / evaluated / discarded / pruned - ★ marks the current best committed experiment - Yellow ring on dots that sit on the best-path spine (root → best) - Yellow stair line traces cumulative-best across committed experiments - ○ at the baseline for experiments that have no score yet (active / pending) Every run in the workspace is rendered, stacked top-to-bottom, with a header line showing `run_id · target · metric`. ## How to invoke Run: ```bash evo report ``` That is it. Print the output verbatim in your reply so the user sees the chart. Do not summarize the chart in prose — the visual is the point. Flags: - `--color always|never|auto` — force or suppress ANSI color. Default `auto` (color when stdout is a TTY). Pass `--color always` if you are piping through a host that strips TTY but renders ANSI in chat. - `--watch [SECONDS]` — live-refresh mode (like `nvidia-smi -l`). Re-reads the workspace every N seconds (default 2) and redraws in place. Ctrl-C to exit. Use this when you want to babysit a running optimization without manually re-invoking the report. ## When not to use - For one-off score lookups, `evo status` or `evo show <id>` is faster. - For navigating the tree shape, `evo tree` is the right command. - For interactive exploration (click a dot, open a drawer), point the user at `evo dashboard` instead.
Initialize evo for the current repository by exploring the codebase, proposing unexplored optimization dimensions, constructing the benchmark inside a baseline worktree, and running the first experiment. Use when the user invokes /evo:discover, mentions setting up evo, wants to instrument a codebase for autonomous optimization, or asks to start a new evo run on a project.
Non-user-invocable provider/setup reference for evo backend switching, prerequisite checks, and auth/install guidance.
Run the evo optimization loop with parallel subagents until interrupted.
Protocol that evo optimization subagents follow when dispatched from /optimize. Auto-loaded by spawned subagents via their host's skill loader. The orchestrator may also invoke this skill to understand the brief shape its dispatched subagents expect + what they're required to emit -- useful when writing briefs or debugging a subagent's behavior.
This skill should be used when picking or diagnosing a training move (SFT, LoRA, DPO/KTO/ORPO, RFT, GRPO/PPO/RLOO, RLHF), or when the user mentions fine-tuning, post-training, training recipe, reward design, or weight updates. Decision tree by reward shape, smoke-run gate, three failure diagnostics, five false-progress patterns. Provider recipes and I/O contract in references/.