best-of

This skill should be used when the user asks to "compare code", "compare worktrees", "compare solutions", "which solution is better", "compare branches", "best of", "diff worktrees", "evaluate solutions", "pick the better implementation", "compare implementations", "review both solutions", or wants a structured, criteria-driven comparison of code across two git worktrees. Also triggered by the /best-of command.

Quality

81%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

67%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 well-structured, actionable workflow for a complex multi-agent review skill, with real bundled references and concrete commands. The main weakness is conciseness: the agent prompts re-teach Claude concepts it already knows and partially duplicate the reference file.

Suggestions

Trim the three agent prompts to action lists only — drop definitions of SOLID, OWASP top 10, and error-handling that Claude already knows, since the detailed criteria already live in references/evaluation-criteria.md.

Replace the inline 15-row criteria table in Step 5 with a pointer to references/evaluation-criteria.md to remove duplication and tighten the body.

Add a brief error-recovery note for when a dispatched agent returns no findings or errors (e.g., re-dispatch or fall back to direct analysis) to close the workflow-clarity feedback-loop gap.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient workflow guidance, but the three agent prompts re-explain concepts Claude already knows (SOLID principles, OWASP top 10, error-handling definitions) and the 15-criteria table duplicates content already in the bundled reference file.	3 / 5
Actionability	Provides concrete, executable git commands, fully specified parallel-agent dispatch prompts, and a copy-paste verdict template; minor gaps are the placeholder paths (<worktree-A>, <path-A>) that must be substituted before execution.	4 / 5
Workflow Clarity	A clear six-step sequence with explicit validation checkpoints (invalid path stops, missing path prompts the user, 200-line truncation warning) and checklists (Project Rules Checklist, File Comparison Manifest), though no explicit error-recovery feedback loop for agent failures.	4 / 5
Progressive Disclosure	Good structure with one real, clearly-signaled, one-level-deep reference (references/evaluation-criteria.md) verified to exist; the inline 15-criteria summary table lightly duplicates the reference, a minor organization gap.	4 / 5
	Total	15 / 20 Passed

Description

95%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 description that clearly states the skill's purpose and gives rich, natural trigger phrases plus a command invocation. The only weakness is that the enumerated actions are variations on a single comparison theme rather than a diverse set of capabilities.

Dimension	Reasoning	Score
Specificity	Lists several specific comparison actions ("compare code", "compare worktrees", "diff worktrees", "evaluate solutions", "pick the better implementation"), but they are largely synonyms of one capability rather than diverse distinct actions, leaving minor coverage gaps.	4 / 5
Completeness	Explicitly answers both what ("structured, criteria-driven comparison of code across two git worktrees") and when ("This skill should be used when the user asks to..." with concrete trigger phrases and a command).	5 / 5
Trigger Term Quality	Comprehensive coverage of natural phrases users would actually say, including synonyms ("compare code", "best of", "diff worktrees", "which solution is better", "review both solutions") plus the /best-of command trigger.	5 / 5
Distinctiveness Conflict Risk	Occupies a clear niche (side-by-side comparison across two git worktrees) with distinct triggers and minimal overlap risk with other skills.	5 / 5
	Total	19 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: pmatos/skills
Path: best-of/SKILL.md
Commit: c6681ab

Reviewed: 3 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.