cursor-review

Run a Cursor Composer review as an advisory second opinion while keeping the primary review verdict on the host brain. Use when user invokes cursor:review, asks Cursor to review, or wants composer to sanity-check a diff. Cursor never owns APPROVE/REQUEST_CHANGES.

Quality

81%

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

Quality

Content

75%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, mostly-executable review workflow with a clear sequenced flow and well-organized sections. It earns 4s across the board: actionable code with a few placeholders, an explicit error checkpoint, and good structure with minor trimming/splitting opportunities.

Suggestions

Fill or parameterize the placeholder fields in the Cursor prompt template ("<original request and completion criteria>", "<relevant paths and observed results>") so the guidance is fully copy-paste ready.

Move the verbose HARNESS_PLUGIN_ROOT probe into a shared helper script and reference it, reducing inline boilerplate.

Trim the Rules section so it does not restate the advisory-verdict point already covered in the description and intro prose.

Dimension	Reasoning	Score
Conciseness	The body is mostly executable bash with minimal prose and assumes Claude's competence, but the HARNESS_PLUGIN_ROOT probe block and the Rules section (which restates the advisory point already in the description) could be trimmed.	4 / 5
Actionability	Quick Reference, routing, and the full Flow provide concrete copy-paste bash, but the Cursor prompt template contains unfilled placeholders like "<original request and completion criteria>" and relies on external scripts assumed present.	4 / 5
Workflow Clarity	A clear four-step sequence (resolve root, determine scope, ask Cursor, host primary review) with an explicit error exit in step 1 and severity-ordering guidance in step 4; minor validation gaps but the operation is read-only so no destructive-batch cap applies.	4 / 5
Progressive Disclosure	Well-organized into Quick Reference, Rules, Flow, and Output with inline script references that are clearly signaled; no bundle files exist, and the inlined env-resolution block is a minor organization gap that keeps it just below 5.	4 / 5
	Total	16 / 20 Passed

Description

87%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 tight, well-scoped description that clearly answers both what the skill does and when to use it, with concrete natural-language triggers and a distinct Cursor-only niche. It is single-purpose so specificity falls just short of a comprehensive multi-action 5.

Dimension	Reasoning	Score
Specificity	"Run a Cursor Composer review as an advisory second opinion", "keeping the primary review verdict on the host brain", and "Cursor never owns APPROVE/REQUEST_CHANGES" name several specific behaviors with boundary detail, but the skill is single-purpose rather than a comprehensive multi-action list.	4 / 5
Completeness	It explicitly states what ("Run a Cursor Composer review as an advisory second opinion...") and when ("Use when user invokes cursor:review, asks Cursor to review, or wants composer to sanity-check a diff") with concrete trigger phrases.	5 / 5
Trigger Term Quality	"user invokes cursor:review", "asks Cursor to review", and "wants composer to sanity-check a diff" are natural phrases a user would say, with good though not exhaustive coverage.	4 / 5
Distinctiveness Conflict Risk	The Cursor-lane niche and distinct triggers ("cursor:review", "composer to sanity-check a diff") give it a clear scope with minimal overlap risk against other review skills.	5 / 5
	Total	18 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
referenced_paths_exist	Referenced path issues: 2 missing	Warning

	Total	15 / 16 Passed

Repository: Chachamaru127/claude-code-harness
Path: opencode/skills/cursor-review/SKILL.md
Commit: 2b2b748

Reviewed: 3 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.