cursor-advanced-composer

Advanced Cursor Composer techniques: agent mode, parallel agents, complex refactoring, and multi-step orchestration. Triggers on "advanced composer", "composer patterns", "multi-file generation", "composer refactoring", "agent mode", "parallel agents".

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.

Highly actionable content with clear, validated workflows, but it is a monolithic single-file dump that ignores its own reference bundle and carries some explanation Claude does not need.

Suggestions

Link the existing references from the body (e.g. under an "Advanced features" section: "**Complex refactoring**: See [complex-refactoring.md](references/complex-refactoring.md)") and move the corresponding inline detail out of SKILL.md.

Cut knowledge Claude already has, such as the "Agent Tool Capabilities" approval table and the explanatory sentence about the agent loop, leaving only the patterns and constraints.

Dimension	Reasoning	Score
Conciseness	Mostly efficient with actionable code blocks, but includes content Claude already knows such as the "Agent Tool Capabilities" table and prose like "It operates in a loop until the task is complete"; could be trimmed, so it sits at the anchor-2 "mostly efficient but could be tightened" rather than the lean anchor-3.	2 / 3
Actionability	Provides copy-paste-ready prompt templates (e.g. the Migrate/Constraints block, Phase 1-4 checkpoints) and concrete commands (npm run build/lint/test, git checkout --), matching the anchor-3 fully-executable standard.	3 / 3
Workflow Clarity	Multi-step processes are explicitly sequenced with validation checkpoints ("Run `npm test` after each file", "Stop after each phase and show me a summary") plus a pre-apply checklist and build/lint/test feedback loop, meeting the anchor-3 standard.	3 / 3
Progressive Disclosure	Seven reference files exist in references/ (advanced-patterns.md, complex-refactoring.md, etc.) but the body never links to or signals any of them, and detail that belongs in those files is inline; this matches the anchor-2 "references present but not clearly signaled; content that should be separate is inline" rather than a 1 because section headers provide reasonable structure.	2 / 3
	Total	10 / 12 Passed

Description

90%

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 with explicit trigger guidance and a clear, distinctive niche. Its only weakness is that capabilities are stated as feature labels rather than concrete verb-actions.

Suggestions

Reword capability areas as concrete verb-actions (e.g. "orchestrate parallel agents", "refactor across multiple files", "chain agent-mode tool calls") to match the specificity of the anchor-3 example.

Dimension	Reasoning	Score
Specificity	Quotes "agent mode, parallel agents, complex refactoring, and multi-step orchestration" name the domain and several capability areas, but these are feature labels/categories rather than the concrete verb-actions (e.g. "extract text", "fill forms") of the anchor-3 example; not below 2 because the domain and multiple capabilities are explicitly named.	2 / 3
Completeness	Clearly states what it does ("Advanced Cursor Composer techniques: ...") and explicitly answers when via the "Triggers on ..." clause, satisfying both halves required for a 3.	3 / 3
Trigger Term Quality	Explicit trigger list "advanced composer", "composer patterns", "multi-file generation", "composer refactoring", "agent mode", "parallel agents" gives good coverage of natural terms a user would actually say, matching the anchor-3 example.	3 / 3
Distinctiveness Conflict Risk	The clear niche "Cursor Composer" plus distinct, specific trigger phrases make it unlikely to fire for the wrong skill, matching the anchor-3 example.	3 / 3
	Total	11 / 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.