cursor-ai-chat
Master Cursor AI Chat with @-mentions, inline edit, and conversation patterns. Triggers on "cursor chat", "cursor ai chat", "ask cursor", "cursor conversation", "chat with cursor", "Cmd+L", "inline edit".
53
61%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Advisory
Suggest reviewing before use
Optimize this skill with Tessl
npx tessl skill review --optimize ./plugins/saas-packs/cursor-pack/skills/cursor-ai-chat/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 has strong trigger term coverage and clear distinctiveness for Cursor AI chat functionality. However, it lacks concrete action verbs describing what the skill actually teaches (e.g., composing prompts, referencing files, managing conversations) and would benefit from an explicit 'Use when...' clause to guide skill selection.
Suggestions
Replace 'Master Cursor AI Chat with @-mentions, inline edit, and conversation patterns' with specific actions like 'Compose effective prompts in Cursor AI chat, reference files and symbols with @-mentions, perform inline code edits, and manage multi-turn conversations'.
Add an explicit 'Use when...' clause, e.g., 'Use when the user asks about Cursor's chat features, needs help with @-mentions, inline editing, or wants to improve their Cursor AI conversation workflow'.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description names the domain (Cursor AI Chat) and mentions some features like '@-mentions, inline edit, and conversation patterns', but these are more feature labels than concrete actions. It doesn't list specific actionable tasks like 'compose prompts', 'reference files with @-mentions', or 'edit code inline'. | 2 / 3 |
Completeness | The 'what' is partially addressed ('Master Cursor AI Chat with @-mentions, inline edit, and conversation patterns') and trigger terms are listed, but there is no explicit 'Use when...' clause. The triggers are listed but not framed as guidance for when Claude should select this skill. | 2 / 3 |
Trigger Term Quality | Good coverage of natural trigger terms including 'cursor chat', 'cursor ai chat', 'ask cursor', 'cursor conversation', 'chat with cursor', and the keyboard shortcut 'Cmd+L'. These are terms users would naturally say when seeking help with Cursor's chat features. | 3 / 3 |
Distinctiveness Conflict Risk | The description is clearly scoped to Cursor AI's chat functionality specifically, with distinct trigger terms like 'Cmd+L' and 'cursor chat' that are unlikely to conflict with other skills. The niche is well-defined. | 3 / 3 |
Total | 10 / 12 Passed |
Implementation
50%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a competent reference guide for Cursor AI Chat features that covers the major interfaces, @-mentions, prompting patterns, and tool selection. Its main weaknesses are moderate verbosity (ASCII diagrams, enterprise section, model tables with potentially outdated info), lack of validation/feedback loops in workflows, and a monolithic structure that would benefit from splitting detailed reference content into separate files. The prompting pattern examples are the strongest section, providing concrete, actionable templates.
Suggestions
Remove the ASCII chat panel diagram and enterprise considerations section—these don't add actionable value for Claude and consume tokens on UI description and organizational policy.
Add validation/feedback guidance: what to do when inline edit produces incorrect code (e.g., reject with Esc, refine prompt, add more context), and how to verify chat suggestions before applying them.
Split the @-symbol reference table and model selection table into separate bundle files (e.g., AT_SYMBOLS.md, MODEL_GUIDE.md) and reference them from the main skill to improve progressive disclosure.
Remove or condense the model recommendation table—specific model names (GPT-5, o3) are time-sensitive and may become outdated; focus on the principle (use reasoning models for complex tasks, fast models for simple ones).
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is reasonably well-organized but includes some unnecessary content Claude already knows (enterprise considerations, model recommendation tables with specific model names that may become outdated, and the ASCII diagram of the chat panel UI). The @-symbol table and comparison tables add value but could be tighter. | 2 / 3 |
Actionability | The prompting patterns provide concrete examples of how to structure chat messages, and keyboard shortcuts are specific. However, there's no executable code—the skill is instruction-oriented, which is appropriate, but the guidance is more descriptive than prescriptive. The inline edit section shows a conceptual flow rather than precise step-by-step actions. | 2 / 3 |
Workflow Clarity | The multi-turn conversation management section provides useful heuristics for when to start fresh vs continue, and the comparison table clarifies which tool to use when. However, there are no validation checkpoints or feedback loops—e.g., no guidance on what to do when chat responses degrade, how to verify a suggestion is correct, or how to recover from a bad inline edit. | 2 / 3 |
Progressive Disclosure | The content is well-structured with clear headers and sections, and external resource links are provided at the bottom. However, the skill is quite long (~150 lines of substantive content) with no bundle files to offload detail into. The @-symbol reference table, model selection table, and enterprise considerations could be split into separate reference files for better progressive disclosure. | 2 / 3 |
Total | 8 / 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
6e9558f
- 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.