roborev-review

Use only when the user explicitly invokes /roborev-review

Quality

68%

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

Fix and improve this skill with Tessl

tessl review fix ./internal/skills/droid/roborev-review/SKILL.md

Quality

Content

88%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.

The body is a strong, well-sequenced operational procedure: concrete commands, an explicit ref-validation checkpoint, error-recovery paths, and clear presentation guidance including the panel/synthesis nuance. Its only weaknesses are minor redundancy (panels explained twice, examples restating steps) that could be trimmed for token efficiency.

Dimension	Reasoning	Score
Conciseness	The body is instruction-dense with no explanations of concepts Claude already knows, but has minor padding: panel behavior is explained in both step 3 and the Panels subsection, the usage syntax is repeated in the Instructions header, and the Examples restate the numbered steps. It fits 'efficient; minor instances of over-explanation that could be trimmed' rather than 5's 'every token earns its place'.	4 / 5
Actionability	Commands are fully executable and copy-paste ready: 'roborev review --wait [--type <type>] [--panel <name>\|none]', the git rev-parse validation snippet with heredoc, and concrete error-recovery suggestions ('roborev status', 'roborev init'). Specific examples (HEAD default, security review of abc123) cover the common cases, matching the top anchor.	5 / 5
Workflow Clarity	A clear 4-step sequence (validate inputs → build and run the command → present results → offer next steps) with an explicit validation checkpoint ('If validation fails, inform the user the ref is invalid. Do not proceed.') and error-recovery feedback loops (daemon not running, repo not initialized). This is a read-only review operation, so the destructive/batch cap does not apply; it matches the anchor requiring explicit validation and error-recovery loops.	5 / 5
Progressive Disclosure	No bundle files exist and the skill is a single cohesive CLI procedure, appropriately self-contained with clean section headers and a See-also list of sibling skills. It fits 'good structure; most content appropriately placed; minor organization gaps' — the Panels content and Examples duplicate each other somewhat, which keeps it just below the top anchor.	4 / 5
	Total	18 / 20 Passed

Description

31%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.

The description is highly distinctive but severely incomplete: it functions purely as a trigger guard with no statement of what the skill does. A user (or Claude) scanning descriptions could not learn that this skill runs a code review on a commit and presents the verdict and findings.

Suggestions

Lead with a brief 'what' clause, e.g. 'Request a code review of a commit via the roborev daemon and present the verdict, findings grouped by severity, and next-step fix suggestions.'

Include the natural domain terms (code review, commit, verdict, findings) so the skill is discoverable and distinguishable by content, not just by its literal command name.

State the invocation contract compactly, e.g. 'Use only when the user explicitly invokes /roborev-review (or requests it via structured skill selection); never for generic review requests.'

Dimension	Reasoning	Score
Specificity	The description states only "Use only when the user explicitly invokes /roborev-review" — no capabilities or actions are named, and even the domain (code review) is unstated. This matches the anchor 'entirely vague; no concrete actions' rather than 2, which requires naming the domain.	1 / 5
Completeness	The 'when' is explicit and precise (explicit invocation only), but no 'what' is present anywhere — the description never says the skill requests a code review and presents results. This exactly matches the anchor 'only when is present without what'; a 3 would require a clear 'what'.	2 / 5
Trigger Term Quality	The only keyword is the literal command "/roborev-review"; natural phrases a user would say ("review this commit", "code review", "security review") are entirely absent. It fits 'one or two generic keywords; missing the natural phrases users say' rather than 3, which requires broader relevant keyword coverage.	2 / 5
Distinctiveness Conflict Risk	"Use only when the user explicitly invokes /roborev-review" carves out a clear niche with a distinct trigger, making accidental firing for the wrong skill essentially impossible. This matches the top anchor 'clear niche with distinct triggers; minimal conflict risk'.	5 / 5
	Total	10 / 20 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: kenn-io/roborev
Path: internal/skills/droid/roborev-review/SKILL.md
Commit: a87c9af

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.