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

—

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Passed

No known issues

Quality

Content

77%

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

A well-structured, highly actionable comparison workflow with clear sequencing and validation, though it leans verbose by inlining full agent prompts and a complete 15-criterion scoring table that could partly live in the bundled reference. Progressive disclosure is functional but not maximally split.

Suggestions

Move the full 15-row criteria scoring table and detailed per-criterion definitions into references/evaluation-criteria.md, keeping only the weighted-tiers summary inline.

Compress the three blockquoted agent prompts into a parameterized template or relocate them to a references file to reduce token weight.

Trim the long explicit guideline-file glob list in Step 2 to the most common conventions and reference a fuller list in the bundle.

Dimension	Reasoning	Score
Conciseness	The skill is ~220 lines with substantial blockquoted agent prompts and repeated tables; while accurate and not padded with beginner concepts, the inline verbatim agent prompts and full 15-row scoring table could be tightened or moved to the reference file to better respect the token budget.	2 / 3
Actionability	Provides concrete, executable git commands (rev-parse, merge-base, diff --stat, diff -rq), specific agent dispatch instructions with subagent_type, an explicit scoring weighting table, and a copy-ready verdict template.	3 / 3
Workflow Clarity	A clear six-step sequence with validation checkpoints — path validation in Step 1, truncation warnings in Step 3, parallel agent dispatch, and an explicit weighted-synthesis step — with feedback for invalid inputs and proportional-depth guidance.	3 / 3
Progressive Disclosure	It references references/evaluation-criteria.md (a real, one-level-deep bundle file), but the bulk of the detailed criteria and agent prompts remain inline in SKILL.md rather than being split out, so the overview is heavier than ideal.	2 / 3
	Total	10 / 12 Passed

Description

100%

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, specific description with excellent natural trigger-term coverage and a clearly defined niche around two-worktree comparison. It answers both what and when explicitly and uses third-person voice throughout.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'compare code', 'compare worktrees', 'compare solutions', 'best of', 'diff worktrees', 'evaluate solutions', 'pick the better implementation' — and a clear deliverable of a structured, criteria-driven comparison across two git worktrees.	3 / 3
Completeness	Explicitly answers what (a structured, evidence-based verdict on which solution is better) and when ('Use when the user asks to compare code...') with a clear trigger clause and command reference.	3 / 3
Trigger Term Quality	Strong coverage of natural phrases a user would say ('compare code', 'which solution is better', 'best of', 'pick the better implementation') plus the explicit /best-of command trigger.	3 / 3
Distinctiveness Conflict Risk	Has a clear niche — git worktree comparison with structured scoring — with distinct two-worktree triggers unlikely to conflict with single-worktree review or general diff skills.	3 / 3
	Total	12 / 12 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
Commit: 67de981

Reviewed: 4 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.