Report

Inline scatter plot of your optimization runs, printed straight to the terminal. You get score over time, status colors (green for committed, red for failed), a yellow stair tracing your cumulative best, and a star on the current winner. It's the left rail of the web dashboard but rendered as a text block you can paste into chat or watch live with a refresh flag. Useful when you want a quick visual gut check without switching contexts or when you're already in the terminal and just need to see if the last few experiments moved the needle. Not for detailed inspection, just fast situational awareness.

skills.sh installs: 102
GitHub stars: 1.5K
last updated: Jun 11, 2026

View on GitHub

Install

$ npx -y skills add evo-hq/evo --skill report --agent claude-code

Installs into .claude/skills of the current project.

Files

Report

Report the current evo workspace from recorded state only. A report request is read-only, even if the user phrases it casually as "what happened?", "what got better?", "what should I pay attention to?", or "I just woke up".

Do not spend compute while reporting:

Do not run evo run, evo gate check, benchmark commands, or project eval scripts.
Do not run python bench.py, python slurm_eval.py, sbatch, srun, squeue, sacct, or scancel to verify a result.
Do not create launcher, monitor, parsing, or analysis scripts.
Do not edit files.

Use stored evo state instead: evo report, evo status, evo tree, evo frontier, evo show <id>, evo diff <id>, and immutable artifacts under .evo/run_*/experiments/<exp>/attempts/<NNN>/.

For chart requests, render the dashboard's scatter plot as a colored terminal block, one chart per run, sized to the current terminal.