Summary
Bootstraps autonomous optimization on your codebase by exploring the repo, identifying what's worth optimizing, building a benchmark harness in a separate worktree, and kicking off the first baseline run. The whole setup stays out of your main branch. You'd reach for this when you want to instrument a project for iterative experimentation without polluting git history with test infrastructure. It handles the orchestration layer: proposing optimization dimensions when they're not obvious, wiring up instrumentation via SDK or inline fallback, and spawning the right subagents for verification and ideation. Works well when you have a metric to chase but aren't sure where the headroom is. The skill enforces CLI version sync to avoid silent breakage from drift.
Install to Claude Code
npx -y skills add evo-hq/evo --skill discover --agent claude-codeInstalls into .claude/skills of the current project.
Connect Claude to +800M contacts, +150M companies. Find & Enrich leads in chat.
Try For Free →
Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →
On Capafy, your Skill runs online 24/7 as an agent product, and you get paid every time someone uses it.
Start earning →
An agent that runs the SEO playbooks that move rankings and ships PRs you control.
Get founding access →Files
SKILL.md
Select a file.
Featured
Connect Claude to +800M contacts, +150M companies. Find & Enrich leads in chat.
Try For Free →Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →On Capafy, your Skill runs online 24/7 as an agent product, and you get paid every time someone uses it.
Start earning →An agent that runs the SEO playbooks that move rankings and ships PRs you control.
Get founding access →First SeenJun 11, 2026
