CtrlK
BlogDocsLog inGet started
Tessl Logo

pleaseai/cubic

AI-powered code review using Cubic CLI. Detects bugs, security vulnerabilities, and style issues before commits.

74

Quality

93%

Does it follow best practices?

Impact

No eval scenarios have been run

SecuritybySnyk

Passed

No known issues

Overview
Quality
Evals
Security
Files

Quality

Content

85%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A lean, actionable CLI skill body with executable commands, a concrete output contract, and a workflow that includes approval and verification checkpoints. The only weakness is mild redundancy between the description's triggers and the body's "When to Use" section.

Suggestions

Trim the "When to Use" list since the same triggers already appear in the frontmatter description, or repurpose it to cover edge cases not in the description.

The closing pointer "use `/cubic:review`" is ambiguous as a navigation aid; clarify whether it is a slash command or a bundled reference file.

DimensionReasoningScore

Conciseness

Mostly efficient and free of concept over-explanation, but the "When to Use" section largely restates the trigger scenarios already in the description, so it could be tightened.

2 / 3

Actionability

Provides copy-paste-ready CLI commands (`cubic review --json`, `--base main`, `--commit HEAD~1`) plus a concrete JSON output schema and a constraint note, fully executable.

3 / 3

Workflow Clarity

Seven clearly sequenced steps include an approval checkpoint (present fixes before applying) and a validation feedback loop (re-run `cubic review --json` to verify fixes).

3 / 3

Progressive Disclosure

A compact, well-organized body under 50 lines with no bundle files; sections (Prerequisites, CLI Quick Reference, JSON Output, Workflow) are clearly signaled and easy to navigate.

3 / 3

Total

11

/

12

Passed

Description

100%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong, third-person description that pairs concrete capabilities with an explicit trigger clause and tool-specific anchors. It closely matches the rubric's good examples and is unlikely to misfire.

DimensionReasoningScore

Specificity

Names three concrete actions — "detect bugs, security vulnerabilities, and style issues in local changes" — mirroring the score-3 anchor that lists multiple specific actions.

3 / 3

Completeness

Explicitly answers both what (AI-powered code reviews via Cubic CLI detecting bugs/vulnerabilities/style) and when (an explicit "Use when the user says..." trigger clause).

3 / 3

Trigger Term Quality

Includes many natural phrases users would say ("review my code," "check my changes for bugs," "pre-commit check," "find issues before I push," "code quality check") giving strong keyword coverage.

3 / 3

Distinctiveness Conflict Risk

Tied to a specific tool (Cubic CLI) with distinct triggers like "run cubic review" and "cubic," making conflict with other skills unlikely.

3 / 3

Total

12

/

12

Passed

Validation

93%

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

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

allowed_tools_field

'allowed-tools' contains unusual tool name(s)

Warning

Total

15

/

16

Passed

Reviewed

Table of Contents