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".
85
83%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Quality
Discovery
89%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is a solid description with explicit trigger terms and a clear niche around advanced Cursor Composer usage. Its main weakness is that the capabilities listed are somewhat categorical rather than describing concrete actions (e.g., 'complex refactoring' rather than specifying what kind of refactoring operations). Overall it performs well for skill selection purposes.
Suggestions
Replace abstract capability categories with concrete actions, e.g., 'Configure agent mode for autonomous code changes, orchestrate parallel agents across multiple files, perform complex multi-file refactoring workflows.'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (Cursor Composer) and lists some capabilities like 'agent mode, parallel agents, complex refactoring, multi-step orchestration,' but these are more like feature categories than concrete actions. It doesn't describe specific actions like 'configure agent mode workflows' or 'set up parallel agent pipelines.' | 2 / 3 |
Completeness | Answers both 'what' (advanced Cursor Composer techniques including agent mode, parallel agents, complex refactoring, multi-step orchestration) and 'when' (explicit 'Triggers on' clause listing specific trigger terms). The trigger guidance is explicit. | 3 / 3 |
Trigger Term Quality | Includes a good set of natural trigger terms that users would likely say: 'advanced composer', 'composer patterns', 'multi-file generation', 'composer refactoring', 'agent mode', 'parallel agents'. These cover multiple natural variations a user might use. | 3 / 3 |
Distinctiveness Conflict Risk | Clearly scoped to 'Advanced Cursor Composer techniques' which is a very specific niche. The trigger terms like 'agent mode', 'parallel agents', and 'composer patterns' are distinctive and unlikely to conflict with other skills. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
77%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a solid, actionable skill with well-structured workflows and concrete prompt templates that Claude can directly use. Its main weakness is length — it tries to cover too many topics in a single file (agent mode, parallel agents, refactoring patterns, quality control, enterprise considerations) without leveraging bundle files for progressive disclosure. Some sections explain concepts Claude already understands (what agent tools do, general security advice) which inflates token cost.
Suggestions
Split detailed refactoring patterns, enterprise considerations, and the agent tool capabilities table into separate bundle files (e.g., REFACTORING_PATTERNS.md, AGENT_REFERENCE.md) and reference them from the main SKILL.md.
Remove or significantly trim the Agent Tool Capabilities table and Enterprise Considerations section — Claude already knows what file reading and security auditing are; focus on Cursor-specific behaviors and constraints only.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is reasonably efficient but includes some unnecessary explanations Claude would already know (e.g., explaining what Agent mode does, what each tool does in the table, general advice like 'review generated code for license compliance'). The enterprise considerations and some contextual framing could be trimmed significantly. | 2 / 3 |
Actionability | The skill provides numerous concrete, copy-paste-ready prompt templates and command examples. Each pattern (Extract and Replace, Interface-First Migration, Test-Driven Refactoring, Checkpoint Pattern) includes specific, executable prompts with realistic file paths and code structures. Terminal commands for validation and rollback are explicit. | 3 / 3 |
Workflow Clarity | Multi-step processes are clearly sequenced with explicit phases and validation checkpoints. The Checkpoint Pattern explicitly includes 'stop after each phase' instructions, the Test-Driven Refactoring pattern includes 'run tests after each change,' and the Post-Apply Validation section provides a clear build→lint→test sequence with rollback instructions for failure cases. | 3 / 3 |
Progressive Disclosure | The content is well-structured with clear headers and logical sections, but it's a long monolithic document (~200 lines) with no bundle files to offload detailed content. The agent tool capabilities table, enterprise considerations, and detailed refactoring patterns could be split into separate reference files. External links are provided but no internal bundle references exist. | 2 / 3 |
Total | 10 / 12 Passed |
Validation
81%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 9 / 11 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 | 9 / 11 Passed | |
- Commit
3a2d27d
- Reviewed
Table of Contents
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.