Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →evo-hq/subagent
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.
Passed 11 of 19 test cases with the skill, and 2 of 19 without it.
and 12 more in the full report
12 fixed1 passed either way8 still failing2 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.
In a workspace configured with commit_strategy=tracked-only, you added new file src/helpers.py to your worktree and ran git add src/helpers.py. When you invoke evo run exp_0033, what specific CLI flag must you pass to confirm you staged new source files?
| Checked | Without skill | With skill |
|---|---|---|
| Passes --i-staged-new-files yes flag to evo run command | Missed | Passed |
The instructions your model reads when the skill loads.
Orchestrators reading for context: this is the protocol your dispatched subagents follow. You don't act on it yourself -- write briefs that satisfy the four required fields described below, and rely on each spawned subagent to drive the loop on its end. Stop reading at "Host conventions" if you only need the brief shape; the rest is for the subagent.
What you can pull/dispatch/read as a subagent. Each line is a triggering condition.
skills you may pull (Skill tool)
└── evo:finetuning before writing or changing any train.py -- technique
choice, training recipe, observability, retry discipline.
subagents you dispatch (Task tool, subagent_type=...)
├── evo:verifier MANDATORY pre AND post every `evo run`.
│ Pre: static analysis before the experiment runs
│ (block on failure -- fix and retry).
│ Post: result-validity audit after it commits.
└── evo:benchmark-reviewer POST-COMMIT only, mode=review-experiment --
per-task failure classification + annotations.
Skip on evaluated/discarded/failed outcomes.
references (Read tool, on demand)
├── discover/references/
│ ├── sdk_python.py / sdk_node.js wiring per-task instrumentation -- preferred
│ ├── inline_instrumentation.py inline fallback. Copy as-is; do not reimplement
│ └── instrumentation-contract.md the format evo reads (result + traces shapes)
│
├── references/evo-wait.md any time you need to wait -- training, eval,
│ any long-running condition. Use this instead
│ of `sleep N`; doesn't burn context.
│
└── finetuning/references/
├── glue.md train.py I/O contract evo expects
├── observability.md wandb/trackio/mlflow wiring -- env-driven
│ detection, TRL report_to options, custom-loop
│ patterns. Read when writing a training script.
├── diagnostics.md per-failure-mode diagnostics
├── false-progress.md what doesn't count as improvement
├── trace-schema.md per-task trace JSON schema
test cases passed, vs 2 / 19 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.