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. 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.

Quality

90%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Quality

Content

81%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A thorough, highly actionable orchestration skill with excellent workflow sequencing and validation feedback loops. Its main weakness is verbosity from repeated explanations and emphasis that could be trimmed, plus a cited reference file (evo-wait.md) absent from the local bundle.

Suggestions

Consolidate the SDK-vs-inline instrumentation explanation: state it once in step 5 and reference it from step 10c instead of re-explaining the same rationale twice.

Tighten step 10c by collapsing the repeated per-task-emission paragraphs into a single rule plus a pointer to the anti-pattern block in the reference files.

Resolve the references/evo-wait.md reference — either add the file to this skill's references/ directory or re-point the citation to the shared references location so the link is not broken.

Dimension	Reasoning	Score
Conciseness	Mostly efficient procedural guidance, but the SDK-vs-inline explanation in step 5 and the per-task-emission message in step 10c are repeated across several paragraphs, and repeated emphatic "Do NOT / Never / Not optional" lines add padding that could be tightened.	3 / 5
Actionability	Dense with concrete, copy-paste-ready commands (evo init, evo gate add, evo run --check, evo wait) showing exact flags, placeholders, and realistic examples covering the common cases.	5 / 5
Workflow Clarity	Steps 0–14 are explicitly sequenced with validation checkpoints and feedback loops: the 6a dirty-tree audit, the mandatory benchmark-reviewer gate (10d), the cheap validation run (10e) with "fix and re-validate", and gate-check-before-proceed rules.	5 / 5
Progressive Disclosure	Good one-level-deep reference structure (constructing-benchmark.md, instrumentation-contract.md, proposing-dimensions.md, sizing-the-round.md, sdk_.py, inline_instrumentation. all exist) mapped in the Evo surface tree, but the body itself is large with some inline content that could live in references, and references/evo-wait.md is cited but not present in this skill's bundle.	4 / 5
	Total	17 / 20 Passed

Description

100%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong, third-person description that concretely enumerates capabilities and provides explicit, natural trigger guidance. It cleanly answers both what the skill does and when to use it with minimal conflict risk.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — "exploring the codebase, proposing unexplored optimization dimensions, constructing the benchmark inside a baseline worktree, and running the first experiment" — giving comprehensive coverage of what the skill does.	5 / 5
Completeness	Explicitly answers both what (explore, propose dimensions, construct benchmark, run first experiment) and when ("Use when the user invokes /evo:discover, mentions setting up evo...") with concrete trigger phrases.	5 / 5
Trigger Term Quality	Natural trigger phrases users would say are present: "invokes /evo:discover", "setting up evo", "instrument a codebase for autonomous optimization", "start a new evo run", covering synonyms and the command form.	5 / 5
Distinctiveness Conflict Risk	Tightly scoped to the /evo:discover niche with evo-specific triggers, making conflict with unrelated skills minimal.	5 / 5
	Total	20 / 20 Passed

Validation

81%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 13 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (612 lines); consider splitting into references/ and linking	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
referenced_paths_exist	Referenced path issues: 3 missing	Warning

	Total	13 / 16 Passed

Repository: evo-hq/evo
Path: plugins/evo/skills/discover/SKILL.md
Commit: ab5fbd6

Reviewed: 5 days ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.