roborev-design-review-branch

Use only when the user explicitly invokes /roborev-design-review-branch

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/grok/roborev-design-review-branch/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 tight, executable runbook: concrete commands, explicit validation with failure handling, and worked examples for both invocation variants. Its only flaws are mild redundancy in the invocation sections and slightly buried panel details.

Dimension	Reasoning	Score
Conciseness	The body is command-forward with no concept explanations Claude already knows, but invocation rules are spread across three sections (Usage, Explicit invocation only, When NOT to invoke) and the base-branch flow appears both in Instructions and again in Examples. This matches 'efficient; minor instances of over-explanation that could be trimmed' — not 5 because of that duplication.	4 / 5
Actionability	Both command variants are fully executable, the base-branch heredoc snippet is copy-paste ready ("read -r branch <<'ROBOREV_REF' ... git rev-parse --verify --end-of-options \"$branch\" \|\| exit 1"), and Examples walk through concrete cases with real job IDs (1042, 1043). Matches 'fully executable; copy-paste ready commands; specific examples cover the common cases'.	5 / 5
Workflow Clarity	The four-step sequence (validate inputs → build and run → present results → offer next steps) has an explicit validation checkpoint ("git rev-parse --verify ... \|\| exit 1", "If validation fails ... Do not proceed") plus error-recovery guidance (sandbox retry, roborev status/init suggestions) and panel-synthesis handling. This matches the top anchor: clear sequence, explicit validation, feedback loops for error recovery.	5 / 5
Progressive Disclosure	A single self-contained file with clear section headers and no bundle files — nothing requires splitting, matching 'good structure; most content appropriately placed; minor organization gaps'. Not 5: the Panels subsection is nested two levels under "Present the results", and invocation guidance scattered across three sections plus a See-also list could be better consolidated.	4 / 5
	Total	18 / 20 Passed

Description

32%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 succeeds at its narrow goal — constraining invocation to the explicit slash command — but omits any statement of what the skill does. As a standalone description it leaves a reader (or model) with trigger-only information and no capability summary.

Suggestions

State the capability before the trigger, e.g. "Requests a design review for all commits on the current branch and presents the verdict and findings. Use only when the user explicitly invokes /roborev-design-review-branch."

Add one or two natural trigger phrases that disambiguate intent when the command is used (e.g. "branch design review") so the description carries some keyword coverage beyond the literal command token.

Briefly note the distinction from sibling commands (e.g. "for a single commit use /roborev-design-review") to reduce overlap risk within the roborev skill family.

Dimension	Reasoning	Score
Specificity	"Use only when the user explicitly invokes /roborev-design-review-branch" names the domain solely through the command name (design review, branch) but states no concrete action the skill performs. It fits 'Names the domain but actions are minimal or generic' — not 1 because nothing is vague, not 3 because no capability is listed.	2 / 5
Completeness	The 'when' is fully explicit ("Use only when the user explicitly invokes..."), but the 'what' is entirely absent — the description never says the skill requests a design review of branch commits and presents results. This matches the anchor 'only when is present without what'; score 3 requires a clear what.	2 / 5
Trigger Term Quality	The only trigger is the literal slash command; there are no natural phrases or synonyms a user would say (e.g. "design review my branch"), matching 'one or two keywords; missing the natural phrases users say'. The narrowness is intentional (explicit-invocation design), but the description offers no keyword coverage beyond the command token.	2 / 5
Distinctiveness Conflict Risk	The unique literal command trigger makes mis-triggering extremely unlikely, but the description does not articulate what separates this skill from the closely related sibling command (/roborev-review-branch --type design is equivalent per the body), fitting 'mostly distinct; minor overlap risk with closely related skills'.	4 / 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/grok/roborev-design-review-branch/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.