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

92%

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

85%Weight 40%Scale 1-3

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 procedure with strong workflow sequencing, validation checkpoints, and well-structured one-level-deep references. Its main weakness is conciseness: a few blocks and rules are duplicated or belabored across steps.

Suggestions

De-duplicate the git-exclude / .gitignore block: define it once (e.g. in step 6b) and reference it from step 10f rather than reproducing it verbatim.

Consolidate the repeated 'do not run experiments outside /evo:optimize' guidance into a single rules entry instead of restating it in steps 5, 11, and 14.

Tighten the lengthy instrumentation-mode exposition in step 5 by moving the SDK-vs-inline rationale detail into references and keeping only the decision rule inline.

Dimension	Reasoning	Score
Conciseness	The body is dense and operational and avoids explaining concepts Claude already knows, but it is not 'every token earns its place': the .git/.gitignore exclude block is duplicated verbatim in steps 6b and 10f and several rules ('do not run outside /evo:optimize', package-install confirmation) are restated multiple times, so it could be tightened.	2 / 3
Actionability	Provides fully executable, copy-paste-ready bash commands with exact flags (evo init, evo gate add, evo run) plus concrete code-shaped instrumentation guidance, matching the level-3 anchor rather than the pseudocode of level 2.	3 / 3
Workflow Clarity	A clearly numbered 0–14 sequence with explicit validation checkpoints (6a dirty-tree audit, 10d benchmark-reviewer gate, 10e --check validation) and error-recovery feedback loops ('if gates failed… fix… re-run'), meeting the level-3 anchor.	3 / 3
Progressive Disclosure	The 'Evo surface' tree gives a clear overview and signals one-level-deep references (e.g. 'See references/constructing-benchmark.md for the full procedure'); all locally referenced files (constructing-benchmark.md, inline_instrumentation.{py,js}, instrumentation-contract.md, proposing-dimensions.md, sizing-the-round.md, sdk_{python,node}) are real and appropriately split out.	3 / 3
	Total	11 / 12 Passed

Description

100%Weight 40%Scale 1-3

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

The description is concise, third-person, and explicitly pairs concrete capabilities with a 'Use when' trigger clause covering natural phrasings. It is distinct to the evo:discover workflow and unlikely to conflict with other skills.

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' — matching the level-3 anchor rather than the partial coverage of level 2.	3 / 3
Completeness	Explicitly answers both what (the initialize/propose/construct/run sequence) and when via a 'Use when...' clause with concrete triggers, satisfying the level-3 anchor; it is not the level-2 case where 'when' is only implied.	3 / 3
Trigger Term Quality	Covers natural trigger phrasings users would say — 'invokes /evo:discover', 'mentions setting up evo', 'wants to instrument a codebase for autonomous optimization', 'start a new evo run' — rather than jargon or a single generic term.	3 / 3
Distinctiveness Conflict Risk	Occupies a clear niche (evo discovery workflow) with distinct '/evo:discover'/'setting up evo' triggers unlikely to fire for unrelated skills, unlike the generic overlap risk at level 2.	3 / 3
	Total	12 / 12 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/npm/skills/discover/SKILL.md
Commit: ab5fbd6

Reviewed: 12 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.