roborev-design-review

Use only when the user explicitly invokes $roborev-design-review

Quality

71%

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/codex/roborev-design-review/SKILL.md

Quality

Content

92%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 an exemplar of a thin CLI-wrapper skill: exact, executable commands for every invocation variant, an input-validation checkpoint with an explicit stop condition, layered error recovery (sandbox retry, daemon diagnostics, panel-synthesis disambiguation), and two concrete worked examples. The only weakness is slight meta-redundancy that could be trimmed without losing information.

Suggestions

Trim the "IMPORTANT" section's restatement that the skill requires executing bash commands; it duplicates the intent already clear from the Instructions and Examples sections.

The sentence "These instructions are guidelines, not a rigid script..." could be compressed or merged into the intro to save tokens.

Dimension	Reasoning	Score
Conciseness	The body is lean: exact commands, no explanations of concepts Claude already knows, and each section (validation, error handling, panels, next steps) earns its place. Minor trimmable redundancy — the "IMPORTANT" section restates that bash execution is required and "These instructions are guidelines, not a rigid script" is meta-guidance — keeps it just below 'every token earns its place'.	4 / 5
Actionability	Fully executable commands are given for both cases ("roborev review --wait --type design" and the heredoc-based "git rev-parse --verify --end-of-options \"$commit^{commit}\"" validation), with concrete error responses ("Suggest `roborev status`... `roborev init`") and two worked examples covering the common cases. This matches 'fully executable; copy-paste ready; examples cover the common cases'.	5 / 5
Workflow Clarity	Clear 4-step sequence (validate inputs → build and run → 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 for daemon/sandbox failures and panel synthesis output. This matches the top anchor's explicit validation steps and feedback loops for error recovery.	5 / 5
Progressive Disclosure	The skill is a single-purpose CLI wrapper with no bundle files (no references/, scripts/, or assets/ exist) and no content that belongs in separate files; the body is organized into well-labeled sections with a "See also" cross-reference list. Per the simple-skill guidance, well-organized sections with no need for external references warrant the top score.	5 / 5
	Total	19 / 20 Passed

Description

36%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 deliberately minimal and highly conflict-safe, but it omits the 'what' entirely: a reader scanning descriptions cannot learn that this skill requests a design review for a commit and presents the results. Adding a one-line capability statement before the trigger clause would raise specificity and completeness substantially without weakening the explicit-invocation guard.

Suggestions

Lead with the 'what': e.g., "Request a design review for a commit and present the results. Use only when the user explicitly invokes $roborev-design-review."

Include a few natural capability terms ("design review", "commit", "verdict and findings by severity") so the skill remains discoverable and self-describing even though invocation is explicit-only.

Avoid relying on the invocation token alone to convey the domain; the body already contains a concise capability sentence that could be mirrored in the description.

Dimension	Reasoning	Score
Specificity	The description states only "Use only when the user explicitly invokes $roborev-design-review" — no concrete capability is named; the domain (design review) appears solely inside the invocation token. This is more than pure abstract fluff (anchor 1) but lists no concrete actions, so it sits at 'names the domain but actions are minimal or generic'.	2 / 5
Completeness	It explicitly answers 'when' ("Use only when the user explicitly invokes") but says nothing about what the skill does — the 'what' (request a design review for a commit and present results) exists only in the body. This matches anchor 2: only 'when' present without 'what', and the explicit-invocation design cannot lift it to anchor 3's 'clear what'.	2 / 5
Trigger Term Quality	The only trigger token is "$roborev-design-review"; there are no natural phrases a user would say (e.g., "design review", "review this commit's design"). It is not entirely generic jargon (anchor 1), but it misses nearly all natural keyword coverage, matching anchor 2.	2 / 5
Distinctiveness Conflict Risk	"Use only when the user explicitly invokes $roborev-design-review" defines a unique explicit trigger that no other skill shares, making accidental triggering for the wrong skill essentially impossible — a clear niche with distinct triggers and minimal conflict risk.	5 / 5
	Total	11 / 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/codex/roborev-design-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.