cursor-context-management
tessl i github:jeremylongshore/claude-code-plugins-plus-skills --skill cursor-context-managementOptimize context window usage in Cursor. Triggers on "cursor context", "context window", "context limit", "cursor memory", "context management". Use when working with cursor context management functionality. Trigger with phrases like "cursor context management", "cursor management", "cursor".
Validation
81%| Criteria | Description | Result |
|---|---|---|
allowed_tools_field | 'allowed-tools' contains unusual tool name(s) | Warning |
metadata_version | 'metadata' field is not a dictionary | Warning |
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 13 / 16 Passed | |
Implementation
35%This skill provides a reasonable structure but fails to deliver actionable guidance. The instructions are abstract directives without concrete examples, specific @-mention syntax, or actual commands. The content defers too much to external files while the main body lacks the substance needed to be immediately useful.
Suggestions
Add concrete @-mention examples showing exact syntax (e.g., '@file.ts', '@folder', '@codebase') with when to use each
Include a specific example of context overflow symptoms and how to diagnose/fix them
Replace abstract instructions like 'Use specific @-mentions' with executable patterns like '@src/utils.ts for utility functions, avoid @codebase for focused questions'
Move at least one practical example from examples.md into the main skill body for immediate actionability
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Reasonably brief but includes some unnecessary padding like the 'Prerequisites' section listing things Claude would know, and the 'Output' section describing expected outcomes rather than actionable content. | 2 / 3 |
Actionability | Instructions are vague and abstract ('Understand your model's context limit', 'Use specific @-mentions') with no concrete examples, specific commands, or executable guidance. Describes what to do without showing how. | 1 / 3 |
Workflow Clarity | Steps are listed in sequence but lack specificity and validation checkpoints. No concrete examples of what 'specific @-mentions' look like or how to 'monitor response quality' - just abstract directives. | 2 / 3 |
Progressive Disclosure | References external files for errors and examples (good structure), but the main content is too thin to justify the split. The skill body should contain at least one concrete example rather than deferring everything to external files. | 2 / 3 |
Total | 7 / 12 Passed |
Activation
40%This description suffers from vague capability statements and circular trigger guidance. While it attempts to provide trigger terms, the core 'what does this do' is essentially undefined beyond 'optimize', and some trigger terms like 'cursor' are too generic to be useful for skill selection.
Suggestions
Replace 'Optimize context window usage' with specific concrete actions (e.g., 'Summarize conversation history, prune irrelevant context, compress code references, manage token budgets').
Remove overly generic triggers like 'cursor' that could conflict with other skills; keep only Cursor IDE-specific terms like 'cursor context', 'context window limit'.
Rewrite the 'Use when' clause to describe actual user scenarios rather than restating the skill name (e.g., 'Use when the user mentions running out of context space, hitting token limits, or needing to manage long conversations in Cursor').
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description uses vague language like 'Optimize context window usage' without listing any concrete actions. It doesn't specify what optimization means or what specific tasks can be performed. | 1 / 3 |
Completeness | Has a 'Use when' clause but the 'what' is extremely weak - it only says 'optimize' without explaining what that entails. The when clause is present but circular ('Use when working with cursor context management functionality'). | 2 / 3 |
Trigger Term Quality | Includes some relevant keywords like 'cursor context', 'context window', 'context limit', but the final trigger suggestions ('cursor management', 'cursor') are overly generic and could conflict with unrelated cursor/pointer functionality. | 2 / 3 |
Distinctiveness Conflict Risk | The term 'cursor' alone is highly generic and could conflict with skills related to mouse cursors, database cursors, or text cursors. The 'context window' terms provide some distinction but 'cursor' as a trigger is problematic. | 2 / 3 |
Total | 7 / 12 Passed |
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.