cursor-context-management
Optimize context window usage in Cursor with @-mentions, context pills, and conversation strategy. Triggers on "cursor context", "context window", "context limit", "cursor memory", "context management", "@-mentions", "context pills".
64
77%
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-context-management/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 skill description with excellent trigger term coverage and clear distinctiveness for Cursor context management. Its main weakness is that the 'what' portion is somewhat vague—'optimize context window usage' doesn't enumerate specific concrete actions or techniques the skill teaches. Adding more specific capabilities would strengthen it.
Suggestions
Expand the capability description with more concrete actions, e.g., 'Teaches techniques for scoping @-mentions to relevant files, managing context pill selections, splitting long conversations, and reducing token waste in Cursor's context window.'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (Cursor context window usage) and mentions some specific features like @-mentions, context pills, and conversation strategy, but doesn't list concrete actions beyond 'optimize'. It lacks detail on what specific optimizations or techniques are covered. | 2 / 3 |
Completeness | Answers both 'what' (optimize context window usage in Cursor with @-mentions, context pills, and conversation strategy) and 'when' (explicit trigger terms listed). The 'Triggers on' clause serves as an explicit 'Use when' equivalent. | 3 / 3 |
Trigger Term Quality | Includes a good range of natural trigger terms that users would actually say: 'cursor context', 'context window', 'context limit', 'cursor memory', 'context management', '@-mentions', 'context pills'. These cover common variations of how users would phrase their needs. | 3 / 3 |
Distinctiveness Conflict Risk | Highly specific to Cursor IDE's context management features. The combination of 'Cursor' + 'context window' + specific features like 'context pills' and '@-mentions' creates a clear niche that is unlikely to conflict with other 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 reference skill for Cursor context management with strong actionability — concrete examples, real @-mention patterns, and executable configuration snippets. Its main weaknesses are moderate verbosity (ASCII diagrams, model token tables, enterprise section) and lack of a structured diagnostic workflow connecting overflow symptoms to remediation steps. The content would benefit from splitting into a concise overview plus supporting reference files.
Suggestions
Create a feedback loop workflow for context overflow: detect signs → inspect context pills → remove/restructure → verify response quality improves.
Move the model context window table and enterprise considerations into separate reference files to reduce the main skill's token footprint.
Replace the ASCII box diagrams with a more compact bulleted list format to save tokens while preserving the same information.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Generally well-organized but includes some unnecessary content Claude already knows (e.g., explaining what context is, the enterprise considerations section, the table of model context windows with specific token counts that may become outdated). The ASCII box diagrams are visually nice but consume significant tokens for information that could be conveyed more compactly. | 2 / 3 |
Actionability | Provides concrete, copy-paste-ready examples for every major use case: @-mention patterns with actual prompts, .cursorignore file content, .mdc rule files with proper YAML frontmatter, and specific keyboard shortcuts. Each section gives executable guidance rather than abstract descriptions. | 3 / 3 |
Workflow Clarity | The mitigation strategies are listed clearly and the task-based @-mention examples provide good guidance. However, there's no explicit workflow for diagnosing and resolving context overflow (e.g., check signs → identify culprit pills → remove/restructure → verify improvement). The 'Signs of Context Overflow' and 'Mitigation Strategies' sections are disconnected rather than forming a feedback loop. | 2 / 3 |
Progressive Disclosure | The content is well-sectioned with clear headers, but it's a long monolithic file with no bundle files to offload detailed content. The enterprise considerations, advanced rules section, and the full context sources diagram could be split into separate reference files. The external resource links at the bottom are helpful but the skill itself could benefit from internal progressive disclosure. | 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
8a9cd04
- 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.