roborev-design-review

Request a design review for a commit and present the results

Quality

—

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Passed

No known issues

Quality

Content

85%

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

The body is highly actionable and well-sequenced, with concrete executable commands, validation checkpoints, and error-recovery guidance, plus clean self-contained organization. The main weakness is redundancy: the command block is repeated across two steps rather than referenced, which lightly hurts token efficiency.

Suggestions

Eliminate the duplicated command block: in step 3 reference 'the command built in step 2' instead of re-pasting the full heredoc and no-commit variants.

Consider condensing the 'IMPORTANT' preamble, since the execute-bash and present-when-complete points are already implied by the numbered workflow.

Dimension	Reasoning	Score
Conciseness	The body is mostly lean and avoids explaining concepts Claude already knows, but the full heredoc command block (the commit-specified and no-commit variants) is duplicated verbatim in both 'Build the command' and 'Run the review in the background', which is unnecessary padding that could be tightened by referencing the earlier block.	2 / 3
Actionability	It provides fully executable shell commands (the git rev-parse validation heredoc and 'roborev review' invocations), concrete Task tool parameters (run_in_background: true, subagent_type), and worked examples, making the guidance copy-paste ready rather than pseudocode.	3 / 3
Workflow Clarity	The five steps are clearly sequenced with an explicit validation checkpoint in step 1 ('If validation fails... Do not proceed') and an error-recovery feedback loop in step 4 (daemon not running, repo not initialized, re-run), matching the clear-sequence-with-validation anchor.	3 / 3
Progressive Disclosure	No bundle files exist, so the skill is appropriately self-contained; it is organized into clearly signaled sections (Usage, When NOT to invoke, Instructions, Examples, See also) with only one-level-deep cross-skill links and no nested references, giving easy navigation.	3 / 3
	Total	11 / 12 Passed

Description

50%

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 cleanly states what the skill does but omits any 'Use when...' trigger guidance, leaving the 'when' side implicit and capping completeness at 2. Trigger terms and distinctiveness are adequate but limited, with no keyword variations or explicit triggers.

Suggestions

Add an explicit 'Use when...' clause naming natural triggers, e.g. 'Use when the user asks for a design review of a commit or staged changes'.

Expand trigger terms with common phrasings like 'review my commit', 'design review', or 'check this change' to improve keyword coverage.

Tighten distinctiveness by contrasting with sibling skills (e.g. 'for a single commit, not a whole branch') to reduce overlap with the roborev review family.

Dimension	Reasoning	Score
Specificity	Names two concrete actions ('Request a design review' and 'present the results') plus the domain (a commit), but they are high-level rather than a comprehensive list of specific actions, matching the 'names domain and some actions' anchor rather than the multiple-specific-actions level.	2 / 3
Completeness	It states what the skill does but never says when to use it; per the judging guidelines a missing 'Use when...' clause caps completeness at 2, so it is not a 3 and clearly above the missing-both level of 1.	2 / 3
Trigger Term Quality	'design review' and 'commit' are terms a user might say, but coverage is thin with no common variations ('review my commit', 'check this change'); closest to 'some relevant keywords but missing common variations' and below the good-coverage anchor.	2 / 3
Distinctiveness Conflict Risk	'design review for a commit' is a specific niche, but without explicit triggers and given the broader roborev review family, it could overlap with sibling review skills rather than being unmistakably distinct.	2 / 3
	Total	8 / 12 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: roborev-dev/roborev
Commit: be9921f

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.