Use when working with context management context save
Overall
score
30%
Does it follow best practices?
Validation for skill structure
Install with Tessl CLI
npx tessl i github:sickn33/antigravity-awesome-skills --skill context-management-context-saveActivation
22%This description is severely lacking in substance. It fails to explain what the skill actually does (the 'what') and provides only a circular, vague trigger condition. The description reads more like a label than a useful guide for skill selection.
Suggestions
Add concrete actions describing what the skill does (e.g., 'Saves conversation context to a file, exports chat history, preserves session state for later retrieval').
Expand the 'Use when' clause with natural trigger terms users would say (e.g., 'Use when the user wants to save the conversation, export context, preserve session, or mentions saving/storing chat history').
Remove the redundant 'context management context save' phrasing and replace with clear, distinct language that explains the skill's purpose.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description contains no concrete actions - it doesn't explain what the skill actually does. 'Context management context save' is abstract and circular, not describing any specific capabilities. | 1 / 3 |
Completeness | The 'what' is completely missing - there's no explanation of what this skill does. While it has a 'Use when' clause, the trigger condition is vague and circular ('context management context save'). | 1 / 3 |
Trigger Term Quality | Contains some relevant keywords ('context', 'save') that users might say, but 'context management' is somewhat technical jargon and there's no coverage of variations or natural phrases users would actually use. | 2 / 3 |
Distinctiveness Conflict Risk | The term 'context' is fairly generic and could overlap with many skills. However, 'context save' provides some specificity that narrows the scope somewhat. | 2 / 3 |
Total | 6 / 12 Passed |
Implementation
7%This skill content is heavily padded with conceptual explanations, marketing language, and abstract descriptions that provide no actionable guidance. The code examples are non-functional pseudocode, and the workflows lack concrete steps or validation. The content reads more like a product specification document than an executable skill for Claude.
Suggestions
Replace pseudocode with actual executable Python code that Claude can run, including real library imports and working function implementations
Remove all marketing language ('elite', 'sophisticated', 'advanced') and conceptual explanations - focus only on what Claude needs to do
Add concrete validation steps to workflows with specific commands (e.g., 'Run `python validate_context.py output.json` to verify schema compliance')
Delete the 'Future Roadmap' and 'Limitations and Considerations' sections - these don't help Claude perform the task
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely verbose with extensive explanations of concepts Claude already knows (what vector databases are, compression algorithms, JSON Schema). Contains marketing-style language ('elite context engineering specialist', 'sophisticated solution') and a 'Future Roadmap' section that adds no actionable value. | 1 / 3 |
Actionability | Code examples are pseudocode with undefined functions (extract_project_metadata, analyze_architecture, etc.) that cannot be executed. Workflows are abstract descriptions without concrete commands or actual implementation details. No copy-paste ready solutions. | 1 / 3 |
Workflow Clarity | Workflows are vague numbered lists without validation checkpoints or error handling. 'Analyze project structure' and 'Generate semantic embeddings' provide no concrete steps. No feedback loops for error recovery despite dealing with complex operations. | 1 / 3 |
Progressive Disclosure | References implementation-playbook.md for detailed examples (good), but the main content is a monolithic wall of text with many sections that could be split into separate files. Lists of supported databases and formats could be in reference files. | 2 / 3 |
Total | 5 / 12 Passed |
Validation
88%Validation — 14 / 16 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
metadata_version | 'metadata' field is not a dictionary | Warning |
license_field | 'license' field is missing | Warning |
Total | 14 / 16 Passed | |
Reviewed
Table of Contents
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.