roborev-review

Use only when the user explicitly invokes $roborev-review

Quality

53%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

High

Do not use without reviewing

Fix and improve this skill with Tessl

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

Quality

Content

100%Weight 40%Scale 1-3

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, actionable operational guide: executable commands, a sequenced workflow with input validation and error recovery, and clean sectioning. It does not pad with concepts Claude already knows and needs no external bundle files.

Dimension	Reasoning	Score
Conciseness	The body is lean and command-driven (e.g. "roborev review --wait [--type <type>] [--panel <name>\|none]") with no explanations of concepts Claude already knows; every section earns its place, matching the 'lean and efficient' anchor rather than level 2 which flags unnecessary explanation.	3 / 3
Actionability	It provides fully executable bash including the commit-validation snippet ("git rev-parse --verify -- "$commit^{commit}" \|\| exit 1") and copy-paste-ready review commands with explicit placeholder substitution, satisfying the 'fully executable code/commands' anchor.	3 / 3
Workflow Clarity	Steps are explicitly sequenced (1. Validate inputs, 2. Build and run, 3. Present results, 4. Offer next steps) with a concrete validation checkpoint ("If validation fails, inform the user the ref is invalid. Do not proceed.") and error-recovery guidance, matching the 'clear sequence with explicit validation steps' anchor.	3 / 3
Progressive Disclosure	No bundle files exist and none are needed; the single-file skill is organized into clear sections (Usage, Explicit invocation, Instructions with numbered subsections, Examples, See also) with one-level cross-links and no nested references, satisfying the well-organized single-file case.	3 / 3
	Total	12 / 12 Passed

Description

7%Weight 40%Scale 1-3

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 functions as an invocation guard but fails as a skill description: it conveys when to trigger yet never says what the skill does or what domain it covers. It scores at the bottom on specificity, trigger terms, and completeness.

Suggestions

Lead with what the skill does, e.g. 'Request a code review for a commit and present the verdict and findings', so the 'what' is explicit.

Add natural trigger language users would say, such as 'code review', 'review this commit', or 'security/design review', rather than relying solely on the literal $roborev-review token.

Combine what and when into one clause, e.g. 'Request and present a roborev code review for a commit. Use only when the user explicitly invokes $roborev-review.' to satisfy both completeness anchors.

Dimension	Reasoning	Score
Specificity	The description ("Use only when the user explicitly invokes $roborev-review") names no concrete actions or domain at all — it states only a trigger condition, matching the 'vague or no actions' anchor rather than the level-2 anchor which requires naming a domain and some actions.	1 / 3
Completeness	It answers 'when' (explicit invocation only) but entirely omits 'what' the skill does (requesting/presenting a code review), and the level-1 anchor explicitly covers 'Missing what OR when'; it does not reach level 2 because level 2 requires the 'what' to be present.	1 / 3
Trigger Term Quality	The only 'keyword' is the literal skill token "$roborev-review"; there are no natural-language terms a user would actually say, so it falls at the 'no natural keywords' anchor rather than level 2 which expects some relevant keywords.	1 / 3
Distinctiveness Conflict Risk	The strict explicit-invocation gate makes wrong-skill triggering unlikely, but no domain niche is described, so it is only 'somewhat specific' (level 2) rather than a 'clear niche with distinct triggers' (level 3).	2 / 3
	Total	5 / 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
Path: internal/skills/codex/roborev-review/SKILL.md
Commit: d121b1a

Reviewed: 2 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.