cursor-composer-workflows

Master Cursor Composer for multi-file AI editing, scaffolding, and refactoring. Triggers on "cursor composer", "multi-file edit", "cursor generate files", "composer workflow", "cursor scaffold", "Cmd+I".

Quality

—

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Passed

No known issues

Quality

Content

77%

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

The body is highly actionable with clear, validated workflows, but it is somewhat verbose and fails to leverage its own reference bundle — none of the six reference files are linked, undermining progressive disclosure.

Suggestions

Link the existing reference files from the body (e.g., add an 'Advanced' section pointing to advanced-composer-techniques.md and an 'Errors' pointer to errors.md) so the bundle is discoverable and the overview stays lean.

Trim the ASCII Composer-interface mockup and the explanatory Agent-mode paragraph; replace with a one-line summary since Claude already understands multi-step agent execution.

Consider moving the BAD/GOOD prompting examples into examples.md, keeping only a brief best-practices summary inline.

Dimension	Reasoning	Score
Conciseness	Mostly efficient with concrete prompt templates, but the ASCII Composer-interface mockup and explanatory Agent-mode prose ("which autonomously executes multi-step tasks") add tokens Claude does not need, keeping it below the lean/efficient anchor.	2 / 3
Actionability	Delivers copy-paste-ready prompt templates for scaffolding, refactoring, test generation, and migration, plus concrete diff examples and BAD/GOOD prompting contrasts — fully executable guidance.	3 / 3
Workflow Clarity	Multi-step processes are explicitly sequenced (four numbered workflow patterns, a 5-step incremental plan) with validation checkpoints in the review workflow ("run your build/tests before committing", "Cmd+Z undoes the last applied change").	3 / 3
Progressive Disclosure	Sections are well-organized, but the six provided bundle files (advanced-composer-techniques.md, best-practices.md, common-use-cases.md, composer-workflow-patterns.md, errors.md, examples.md) are never referenced from the body, so navigation to them is missing and content that should be split stays inline.	2 / 3
	Total	10 / 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 description: concrete capabilities, a rich set of natural trigger terms, explicit when-to-use guidance, and a well-scoped niche that minimizes conflict risk. It uses appropriate imperative/third-person voice throughout.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — "multi-file AI editing, scaffolding, and refactoring" — rather than vague language, matching the 'lists multiple specific concrete actions' anchor.	3 / 3
Completeness	Explicitly answers both what ("multi-file AI editing, scaffolding, and refactoring") and when via an explicit "Triggers on..." clause, satisfying the both-what-and-when anchor.	3 / 3
Trigger Term Quality	Provides good coverage of natural terms users would say: "cursor composer", "multi-file edit", "cursor generate files", "composer workflow", "cursor scaffold", "Cmd+I".	3 / 3
Distinctiveness Conflict Risk	Scoped to a clear niche ("Master Cursor Composer") with distinct triggers unlikely to fire for unrelated skills.	3 / 3
	Total	12 / 12 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
allowed_tools_field	'allowed-tools' contains unusual tool name(s)	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	14 / 16 Passed

Repository: jeremylongshore/claude-code-plugins-plus-skills
Commit: 3022dd3

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.