Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →evo-hq/discover
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.
Passed 14 of 19 test cases with the skill, and 3 of 19 without it.
and 13 more in the full report
12 fixed4 passed either way6 still failing0 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 12 test cases the skill fixed. Same model, same prompt, with and without the skill.
I am running discovery setup for my repo. I executed the CLI check and 'evo --version' returned 'evo-hq-cli 0.4.2'. Should I proceed with initializing the workspace using this CLI version?
| Checked | Without skill | With skill |
|---|---|---|
| The response halts discovery setup when the CLI version does not equal 0.8.0. | Missed | Passed |
| The response directs the user to run uv tool install --force evo-hq-cli==0.8.0. | Missed | Passed |
The instructions your model reads when the skill loads.
Internal procedure for evo:discover. The user only sees the user-facing prompts, the dashboard URL, and the baseline score -- everything else is the agent's choreography.
General guidance on the skills and tools available in evo. Each line is a triggering condition: if you're about to do X, pull/dispatch/read this. Don't preload -- act when the trigger fires.
Always have a sense of the skill before jumping into its references. A skill body carries the decision-making; references are concrete contracts that assume a decision has been made.
evo plugin
│
├── Main thread (the orchestrator -- you, inside /evo:discover or /evo:optimize)
│ │
│ ├── Skills (Skill tool)
│ │ ├── evo:discover starting a new evo workspace / instrumenting a project
│ │ ├── evo:optimize after discover commits the baseline -- drives the loop.
│ │ │ Args: subagents=N (read sizing-the-round FIRST),
│ │ │ autonomous, subagents-only, budget=N, stall=N
│ │ ├── evo:ship after the loop stops -- distills the best valid
│ │ │ experiment into a mergeable change (PR if remote,
│ │ │ else merge) + a mergeability report
│ │ ├── evo:finetuning task is finetuning / post-training / training a model
│ │ └── evo:infra-setup need a remote backend, pooled workspaces, lease/slot
│ │ management, or specific provider auth/setup
│ │
│ └── Subagents to dispatch (Task tool, subagent_type=...)
│ ├── evo:benchmark-reviewer before the baseline run, or whenever the
│ │ benchmark command / harness changes
│ └── evo:ideator stalled, or every ~5 committed experiments.
│ One subagent per brief:
│ failure_analysis, literature, frontier_extrapolation
│
├── Subagent thread (each subagent spawned by /optimize step 5)
│ │
│ ├── Skills (the subagent loads this on first turn -- the brief's first
│ │ sentence mandates it; not auto-loaded by the host)
│ │ └── evo:subagent load FIRST -- defines the iteration protocol
│ │ + brief field shape the subagent operates under
test cases passed, vs 3 / 19 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.