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".
76
72%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./plugins/saas-packs/cursor-pack/skills/cursor-composer-workflows/SKILL.mdQuality
Discovery
72%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
The description effectively identifies its niche (Cursor Composer) and provides good trigger terms that users would naturally use. However, it lacks an explicit 'Use when...' clause and could benefit from more specific concrete actions beyond the general categories of editing, scaffolding, and refactoring.
Suggestions
Add an explicit 'Use when...' clause, e.g., 'Use when the user asks about Cursor Composer workflows, multi-file editing in Cursor, or generating/scaffolding projects with Cmd+I.'
Expand the capability list with more specific concrete actions, e.g., 'Generate boilerplate project structures, apply bulk refactors across multiple files, create new components from natural language prompts.'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (Cursor Composer) and some actions ('multi-file AI editing, scaffolding, and refactoring'), but these are somewhat general categories rather than multiple specific concrete actions like 'generate boilerplate project structures, rename symbols across files, apply bulk code transformations'. | 2 / 3 |
Completeness | The 'what' is partially addressed (multi-file AI editing, scaffolding, refactoring) and trigger terms are listed, but there is no explicit 'Use when...' clause explaining when Claude should select this skill. The trigger terms serve a similar purpose but the guidance on when to use it is implicit rather than explicit. | 2 / 3 |
Trigger Term Quality | Includes a strong set of natural trigger terms users would actually say: 'cursor composer', 'multi-file edit', 'cursor generate files', 'composer workflow', 'cursor scaffold', and 'Cmd+I'. These cover multiple natural variations of how users would refer to this feature. | 3 / 3 |
Distinctiveness Conflict Risk | The description is clearly scoped to Cursor Composer specifically, with distinct trigger terms like 'cursor composer', 'Cmd+I', and 'composer workflow' that are unlikely to conflict with other skills. The niche is well-defined. | 3 / 3 |
Total | 10 / 12 Passed |
Implementation
72%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 skill that provides highly actionable prompt templates and clear workflow patterns for Cursor Composer. Its main strengths are the concrete examples with good/bad comparisons and the well-organized progressive structure. Weaknesses include some verbosity (the ASCII diagram, explanations of concepts Claude knows) and missing explicit validation checkpoints between multi-step operations.
Suggestions
Remove or significantly compress the ASCII interface diagram—it consumes ~15 lines of tokens for information that could be conveyed in 2-3 lines of text.
Add explicit validation checkpoints in the 'Incremental Over Monolithic' workflow, e.g., 'Verify prisma generate succeeds before proceeding' and 'Run tests after each step before continuing to the next.'
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is generally well-structured but includes some unnecessary verbosity. The ASCII art interface diagram, while visually appealing, consumes significant tokens for information that could be conveyed more concisely. Some sections like 'Enterprise Considerations' contain advice Claude already knows (e.g., 'always review diffs'). The Agent Mode section explains concepts at a level Claude doesn't need. | 2 / 3 |
Actionability | The skill provides concrete, copy-paste-ready prompt templates for each workflow pattern (scaffolding, refactoring, test generation, migration). The examples include specific file paths, exact prompt text with @-mentions, and clear before/after patterns. The diff review workflow and prompting best practices with good/bad comparisons are highly actionable. | 3 / 3 |
Workflow Clarity | The review workflow (review diffs → apply → run build/tests → undo if wrong) is present but lacks explicit validation checkpoints. The 'Incremental Over Monolithic' section provides a good sequence but doesn't include validation steps between stages (e.g., verify prisma generate succeeded before creating the service layer). For multi-file operations that can introduce errors, the feedback loops are implicit rather than explicit. | 2 / 3 |
Progressive Disclosure | The content is well-organized with clear sections progressing from interface overview to core patterns to best practices. External references to Cursor docs are provided at the end. The content is appropriately scoped for a single SKILL.md file without needing to split into sub-files, and sections are clearly delineated with descriptive headers. | 3 / 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
3e83543
- 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.