cursor-reference-architecture
Reference architecture for Cursor IDE projects: directory structure, rules organization, indexing strategy, and team configuration patterns. Triggers on "cursor architecture", "cursor project structure", "cursor best practices", "cursor file structure".
67
61%
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-reference-architecture/SKILL.mdQuality
Discovery
57%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 identifies a clear niche (Cursor IDE project architecture) with good distinctiveness, but falls short on specificity of actions and completeness. It reads more like a topic summary than an actionable skill description—it lists subject areas without specifying what Claude actually does (e.g., generates templates, recommends structures, reviews configurations). The trigger terms are helpful but presented as a flat list rather than integrated into a 'Use when...' clause.
Suggestions
Add concrete action verbs describing what the skill does, e.g., 'Generates directory structures, creates .cursorrules files, recommends indexing strategies, and configures team settings for Cursor IDE projects.'
Add an explicit 'Use when...' clause, e.g., 'Use when the user asks about setting up, organizing, or optimizing a Cursor IDE project, or mentions .cursorrules, cursor configuration, or cursor workspace setup.'
Expand trigger term coverage to include natural variations like 'cursor setup', 'cursor rules', '.cursorrules', 'cursor workspace', 'cursor config'.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (Cursor IDE projects) and lists some areas (directory structure, rules organization, indexing strategy, team configuration patterns), but these are more like topic areas than concrete actions. It doesn't specify what actions are performed (e.g., 'generates', 'creates', 'recommends'). | 2 / 3 |
Completeness | The 'what' is partially addressed (reference architecture for Cursor IDE projects), and trigger terms are listed, but there is no explicit 'Use when...' clause. The triggers are stated as a flat list rather than as guidance for when Claude should select this skill. | 2 / 3 |
Trigger Term Quality | Includes explicit trigger terms like 'cursor architecture', 'cursor project structure', 'cursor best practices', 'cursor file structure', which are reasonable. However, it misses natural variations users might say such as 'set up cursor', 'organize cursor project', 'cursor rules', 'cursor config', or '.cursorrules'. | 2 / 3 |
Distinctiveness Conflict Risk | The description is clearly scoped to Cursor IDE project architecture specifically, which is a distinct niche. The trigger terms all include 'cursor' which makes it unlikely to conflict with other skills about general project structure or other IDEs. | 3 / 3 |
Total | 9 / 12 Passed |
Implementation
64%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 reference architecture skill with excellent actionability — the concrete .mdc rule examples, directory structures, and ignore file contents are immediately usable. Its main weaknesses are moderate verbosity (some sections explain what Claude can infer) and the lack of a step-by-step setup workflow with validation checkpoints. The monolithic structure works acceptably for a reference document but could benefit from splitting detailed examples into supporting files.
Suggestions
Add a brief step-by-step 'Quick Setup' workflow at the top (e.g., 1. Create .cursor/rules/, 2. Add project.mdc, 3. Verify rules load by testing in Chat, 4. Add glob-scoped rules) with validation checkpoints.
Trim the 'Why This Structure Helps Cursor' section and enterprise considerations — these explain concepts Claude can reason about from the examples alone.
Split the detailed rule examples (Layer 1-4) and monorepo patterns into a separate RULES-EXAMPLES.md reference file, keeping SKILL.md as a concise overview with links.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is fairly well-structured but includes some unnecessary verbosity. The 'Why This Structure Helps Cursor' section explains things Claude can infer, and the enterprise considerations section is somewhat generic. However, most content is practical and directly useful. | 2 / 3 |
Actionability | Provides fully concrete, copy-paste ready examples throughout: complete .mdc rule files with proper frontmatter, specific .cursorignore contents, directory structures with annotations, and a monorepo configuration. Every section gives executable, specific guidance rather than abstract descriptions. | 3 / 3 |
Workflow Clarity | The layered rules architecture (Layer 1-4) provides a clear organizational hierarchy, and the configuration summary table is helpful. However, there's no sequenced workflow for setting up a project from scratch, no validation steps (e.g., how to verify rules are being applied correctly), and no troubleshooting guidance for common issues. | 2 / 3 |
Progressive Disclosure | The content is well-organized with clear section headers and a logical progression from basic to advanced (single project → monorepo → enterprise). However, at ~200 lines it's a monolithic document that could benefit from splitting detailed rule examples into separate reference files, and the external resource links at the end are minimal. | 2 / 3 |
Total | 9 / 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.