CtrlK
BlogDocsLog inGet started
Tessl Logo
PluginPublic

pleaseai/cubic

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

Quality

88%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

Overview
Quality
Evals
Security
Files

Quality

Content

82%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.

A lean, highly actionable skill body: concrete CLI commands, a worked JSON example, and a sequenced workflow with approval and verification checkpoints. The main gaps are minor — a redundant 'When to Use' section, no explicit error-recovery loop after the verification re-run, and an ambiguous closing pointer to '/cubic:review'.

Suggestions

Trim the 'When to Use' section (and the opening line that repeats the title) since the frontmatter description already carries the trigger information, saving tokens without losing clarity.

Close the feedback loop in the Workflow: after step 7 (re-run cubic review to verify), state what to do if issues remain (e.g., 'If issues persist, repeat steps 4-7 or report unresolved issues to the user').

Clarify or remove the closing line 'For the full command reference and step-by-step workflow, use `/cubic:review`' — no such bundle file or command exists in this skill, so the pointer is circular and misleading.

DimensionReasoningScore

Conciseness

The body is command-focused with no explanation of concepts Claude already knows, but the 'When to Use' section and opening line largely duplicate the frontmatter description, matching anchor 4 ('minor instances of over-explanation that could be trimmed') rather than 5's every-token-earns-its-place.

4 / 5

Actionability

Copy-paste-ready commands cover all four review modes (`cubic review --json`, `--base main`, `--commit HEAD~1`, `--prompt`), plus install commands, a concrete JSON output sample, and explicit tool assignments (Bash, Read, Edit) — fully executable guidance covering the common cases, matching anchor 5.

5 / 5

Workflow Clarity

The 7-step sequence includes checkpoints (user approval before applying fixes; re-run to verify) and auth-error handling, but lacks an explicit branch for when verification still finds issues, fitting anchor 4 ('clear sequence with most checkpoints present; minor validation gaps') rather than 5's explicit error-recovery feedback loop.

4 / 5

Progressive Disclosure

The short body is well-organized into clear sections (Prerequisites, CLI Quick Reference, JSON Output Format, Workflow), but the closing pointer 'use `/cubic:review`' references a command outside this bundle (no references/scripts/assets files exist) and is near-circular with the skill's own name — a minor navigation gap matching anchor 4.

4 / 5

Total

17

/

20

Passed

Description

91%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.

A strong description that clearly states what the skill does and when to use it, with an unusually rich set of natural trigger phrases. The only weaknesses are minor: capability coverage stops short of the fix workflow, and a few generic trigger phrases could collide with general code-review skills.

DimensionReasoningScore

Specificity

The description names the tool and three concrete actions ("detect bugs, security vulnerabilities, and style issues in local changes"), but omits fix-proposal/application capabilities the body covers, matching anchor 4 ('several specific actions; minor gaps in coverage') rather than 5's comprehensive coverage.

4 / 5

Completeness

It explicitly answers both 'what' ("Run AI-powered code reviews using Cubic CLI to detect bugs, security vulnerabilities, and style issues") and 'when' ("Use when the user says...") with concrete trigger phrases, exactly matching the anchor-5 example structure.

5 / 5

Trigger Term Quality

Eight quoted natural user phrases ("review my code," "pre-commit check," "find issues before I push," "analyze my branch changes") plus a synonym 'Triggers on' list including the tool name give comprehensive natural-term coverage with variations, matching anchor 5.

5 / 5

Distinctiveness Conflict Risk

The Cubic CLI tool name and "run cubic review" trigger give a clear niche, but generic phrases like "review my code" and "code quality check" overlap with general code-review skills, fitting anchor 4 ('minor overlap risk with closely related skills') rather than 5's minimal conflict risk.

4 / 5

Total

18

/

20

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.

Validation — 15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

allowed_tools_field

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

Warning

Total

15

/

16

Passed

Reviewed

On this page