CtrlK
BlogDocsLog inGet started
Tessl Logo

roborev-review

Use only when the user explicitly invokes $roborev-review

55

Quality

61%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Medium

Suggest reviewing before use

Fix and improve this skill with Tessl

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

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 well-structured, actionable workflow with executable commands, explicit input validation, and error-recovery guidance. It is concise and appropriately self-contained, with only minor organization density in the Panels section.

DimensionReasoningScore

Conciseness

The body is lean and assumes Claude's competence (no explaining what a code review is), with executable commands and tight sections; minor trims possible in the overlapping 'Explicit invocation only' and 'When NOT to invoke' sections.

4 / 5

Actionability

Provides copy-paste-ready commands (roborev review --wait, the git rev-parse --verify validation snippet, heredoc commit ref) and concrete worked examples for the default-HEAD and security-review cases.

5 / 5

Workflow Clarity

A clear 4-step sequence (validate → run → present → offer next steps) with an explicit validation checkpoint (git rev-parse, 'do not proceed' on failure) and error-feedback loops that suggest roborev status/init on failure.

5 / 5

Progressive Disclosure

Well-organized single file with clear section headers and no need for external bundle files (none present); the somewhat dense Panels subsection keeps it just short of the 'perfectly split, easy navigation' anchor.

4 / 5

Total

18

/

20

Passed

Description

35%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 functions almost entirely as an invocation guard, answering 'when' clearly but omitting 'what' the skill does and naming no concrete capabilities. It is distinctive but underspecified.

Suggestions

Add a 'what' clause stating the skill requests a code review for a commit and presents the results, e.g. 'Request a code review for a commit and present the verdict and findings. Use only when the user explicitly invokes $roborev-review.'

Include a couple of natural trigger synonyms (e.g. 'code review', 'review this commit') while still requiring explicit invocation, to improve trigger-term coverage.

Name concrete actions (run roborev review, group findings by severity, offer to fix) so the description conveys capability, not just a trigger.

DimensionReasoningScore

Specificity

The description ("Use only when the user explicitly invokes $roborev-review") states a trigger condition but names no concrete actions or even the skill's domain, matching the 'entirely vague; no concrete actions' anchor.

1 / 5

Completeness

Only the 'when' is present (explicit invocation) with no 'what' — it never says the skill requests and presents a code review, matching the 'only when present without what' anchor.

2 / 5

Trigger Term Quality

"explicitly invokes $roborev-review" is a natural, specific trigger a user would actually type, but coverage is a single term with no synonyms or variations like 'review this commit'.

3 / 5

Distinctiveness Conflict Risk

Requiring literal explicit invocation of a unique command name makes accidental triggering very unlikely; not a 5 only because no domain niche is described.

4 / 5

Total

10

/

20

Passed

Validation

100%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
roborev-dev/roborev
Reviewed

Table of Contents

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.