cursor-custom-prompts
Create effective custom prompts for Cursor AI using project rules, prompt engineering patterns, and reusable templates. Triggers on "cursor prompts", "prompt engineering cursor", "better cursor prompts", "cursor instructions", "cursor prompt templates".
80
77%
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-custom-prompts/SKILL.mdQuality
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 that clearly identifies its niche (Cursor AI prompt creation) and provides explicit trigger terms for skill selection. Its main weakness is that the 'what' portion could be more specific about the concrete actions performed (e.g., generating .cursorrules files, structuring system prompts, etc.). Overall it performs well for disambiguation purposes.
Suggestions
Add more specific concrete actions to the capability description, e.g., 'Generate .cursorrules files, structure system prompts, create role-based instruction sets' to improve specificity.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (Cursor AI prompts) and mentions some actions like 'create effective custom prompts' and references 'project rules, prompt engineering patterns, and reusable templates,' but doesn't list multiple concrete discrete actions (e.g., doesn't specify what creating a prompt entails, what templates look like, etc.). | 2 / 3 |
Completeness | Clearly answers both 'what' (create effective custom prompts for Cursor AI using project rules, prompt engineering patterns, and reusable templates) and 'when' (explicit trigger terms listed with 'Triggers on...' clause serving as the equivalent of a 'Use when' clause). | 3 / 3 |
Trigger Term Quality | Includes a good set of natural trigger terms that users would actually say: 'cursor prompts', 'prompt engineering cursor', 'better cursor prompts', 'cursor instructions', 'cursor prompt templates'. These cover common variations of how a user might phrase their request. | 3 / 3 |
Distinctiveness Conflict Risk | Highly specific to Cursor AI prompt creation, which is a clear niche. The trigger terms are all Cursor-specific and unlikely to conflict with general prompt engineering or other IDE-related skills. | 3 / 3 |
Total | 11 / 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, actionable skill with excellent concrete templates and examples that are immediately usable. Its main weaknesses are moderate verbosity (explaining concepts like chain-of-thought and few-shot that Claude already understands), lack of validation/feedback loops for iterating on prompt quality, and a monolithic structure that could benefit from splitting templates and rules into separate referenced files.
Suggestions
Add a brief validation/feedback loop section: how to evaluate whether a prompt produced good output, and specific steps to refine it if not (e.g., 'If output misses constraints, extract the missed constraint into a numbered requirement and re-prompt').
Trim or remove explanations of well-known prompting concepts (chain of thought, few-shot, negative constraints) and instead just show the Cursor-specific examples directly—Claude already knows these techniques.
Consider splitting the templates and .cursor/rules examples into separate referenced files (e.g., TEMPLATES.md, RULES-EXAMPLES.md) to improve progressive disclosure and reduce the main file's length.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is reasonably well-structured but includes some unnecessary content that Claude already knows—like explaining what chain-of-thought prompting is, what few-shot examples are, and the 'Enterprise Considerations' section which is generic advice. The anti-patterns table and some template commentary could be tightened. | 2 / 3 |
Actionability | The skill provides concrete, copy-paste-ready prompt templates with realistic examples for feature implementation, bug fixes, code review, test generation, and refactoring. The .cursor/rules examples are complete YAML files ready to use. Every section gives specific, actionable guidance rather than abstract descriptions. | 3 / 3 |
Workflow Clarity | The iterative refinement section shows a multi-step workflow, and the prompt anatomy provides a clear structure. However, there are no validation checkpoints—no guidance on how to verify a prompt worked well, how to iterate when output is poor, or feedback loops for refining prompts. For a skill about crafting prompts, a 'validate and refine' step would strengthen the workflow. | 2 / 3 |
Progressive Disclosure | The content is well-organized with clear headers and logical sections, but it's a long monolithic file (~180 lines of substantive content) with no references to supporting files. The templates, project rules examples, and advanced techniques could each be split into separate referenced files. The external resource links at the end are helpful but don't compensate for the lack of internal bundle structure. | 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.