context-management-context-restore
Use when working with context management context restore
39
Quality
11%
Does it follow best practices?
Impact
87%
1.70xAverage score across 3 eval scenarios
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./skills/context-management-context-restore/SKILL.mdQuality
Discovery
0%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 description is critically deficient across all dimensions. It provides no concrete actions, uses circular technical jargon instead of natural language, and fails to explain what the skill actually does. The 'Use when' clause is present but meaningless without any capability description.
Suggestions
Add specific concrete actions describing what the skill does (e.g., 'Saves conversation state to disk, restores previous sessions, manages working context across conversations').
Replace technical jargon with natural trigger terms users would actually say (e.g., 'save my progress', 'restore session', 'pick up where I left off', 'load previous context').
Rewrite the 'Use when' clause with meaningful triggers (e.g., 'Use when the user wants to save their current work, restore a previous session, or continue from where they left off').
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description contains no concrete actions whatsoever. 'Working with context management context restore' is abstract and circular, providing no information about what the skill actually does. | 1 / 3 |
Completeness | The description completely fails to answer 'what does this do' - there are no capabilities listed. While it has a 'Use when' clause, the trigger condition is meaningless without explaining the skill's purpose. | 1 / 3 |
Trigger Term Quality | The terms 'context management' and 'context restore' are technical jargon that users would not naturally say. There are no natural keywords like 'save session', 'restore conversation', or 'load previous work'. | 1 / 3 |
Distinctiveness Conflict Risk | The description is so vague that it's impossible to distinguish from any other skill that might involve 'context'. The circular phrasing 'context management context restore' provides no clear niche. | 1 / 3 |
Total | 4 / 12 Passed |
Implementation
22%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill is overly verbose, explaining concepts Claude already understands while failing to provide truly executable guidance. The code examples are incomplete pseudocode referencing undefined functions, and the workflows lack concrete validation steps. The content reads more like a product specification document than actionable instructions for Claude.
Suggestions
Remove conceptual explanations (Role Statement, Context Overview, Future Roadmap, Integration Patterns) and focus only on actionable instructions Claude needs
Replace pseudocode with complete, executable examples or clearly indicate these are interface patterns requiring project-specific implementation
Add explicit validation steps to workflows with concrete commands and error handling (e.g., 'If validation fails, check X and retry Y')
Move the 8 advanced retrieval strategies to a separate reference file and keep only the most essential quick-start content in SKILL.md
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely verbose with unnecessary conceptual explanations Claude already knows (what vector databases are, what cosine similarity is, what RAG is). The 'Role Statement', 'Context Overview', 'Future Roadmap', and 'Integration Patterns' sections add no actionable value and waste tokens. | 1 / 3 |
Actionability | Contains Python code examples that appear executable, but they reference undefined functions (VectorDatabase, calculate_composite_score, prioritize_components) making them pseudocode in practice. The bash examples reference a 'context-restore' tool without explaining how to install or access it. | 2 / 3 |
Workflow Clarity | The 'Reference Workflows' section lists high-level steps without concrete commands or validation checkpoints. No feedback loops for error recovery. Steps like 'Validate context against current codebase' provide no actual validation method or what to do if validation fails. | 1 / 3 |
Progressive Disclosure | References 'resources/implementation-playbook.md' for detailed examples, which is good progressive disclosure. However, the main content is a monolithic wall of text with 8 numbered sections that could be split into separate reference files. The structure exists but content organization is poor. | 2 / 3 |
Total | 6 / 12 Passed |
Validation
90%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 10 / 11 Passed | |
- Repository
- sickn33/antigravity-awesome-skills
- Commit
9c177eb
- 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.