context-management-context-restore
Use when working with context management context restore
17
3%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./skills/context-management-context-restore/SKILL.mdQuality
Discovery
7%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 extremely weak across all dimensions. It fails to explain what the skill does, provides no concrete actions or capabilities, and uses repetitive jargon ('context management context restore') instead of natural language triggers. It reads more like a label than a functional description.
Suggestions
Add concrete actions describing what the skill does, e.g., 'Saves and restores conversation context, session state, and working memory across interactions.'
Replace jargon with natural trigger terms users would actually say, such as 'resume session', 'pick up where I left off', 'reload context', 'restore previous conversation'.
Expand the 'Use when' clause with specific scenarios, e.g., 'Use when the user wants to resume a previous session, restore lost context, or manage long-running conversation state.'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description contains no concrete actions whatsoever. It does not describe what the skill does—only vaguely references 'context management context restore' without specifying any capabilities. | 1 / 3 |
Completeness | The 'what does this do' is entirely missing—there is no explanation of capabilities. While there is a 'Use when' clause, it merely restates the skill name rather than providing meaningful trigger guidance. | 1 / 3 |
Trigger Term Quality | The terms 'context management' and 'context restore' are technical jargon that users are unlikely to naturally say. There are no common variations or natural language keywords included. | 1 / 3 |
Distinctiveness Conflict Risk | The phrase 'context management context restore' is somewhat niche and unlikely to conflict with many other skills, but the lack of specificity about what it actually does makes it hard to confidently distinguish from other context-related skills. | 2 / 3 |
Total | 5 / 12 Passed |
Implementation
0%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill is a verbose, abstract document that reads more like a product vision whitepaper than actionable instructions for Claude. It describes hypothetical systems and APIs that don't exist, provides pseudocode rather than executable code, and explains concepts Claude already knows. The content fails on all dimensions: it wastes tokens on unnecessary context, provides no actionable guidance, lacks clear workflows with validation, and dumps everything into a single monolithic file.
Suggestions
Replace all pseudocode with executable code targeting real tools/libraries, or if this is a conceptual skill, provide concrete step-by-step instructions with specific file paths, commands, and expected outputs.
Remove the Role Statement, Context Overview, Integration Patterns, and Future Roadmap sections entirely — they consume tokens without adding actionable value.
Define a clear, concrete workflow with explicit validation checkpoints (e.g., 'Run X command, verify output contains Y, if not then Z') instead of abstract steps like 'Validate context against current codebase'.
Either provide the referenced `resources/implementation-playbook.md` bundle file or remove the reference, and restructure the 8 strategy sections into a concise overview with details in separate referenced files.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely verbose with extensive explanations of concepts Claude already understands (vector search, cosine similarity, context management). The 'Role Statement', 'Context Overview', 'Future Roadmap', and 'Integration Patterns' sections add no actionable value. The code examples are pseudocode for hypothetical APIs that don't exist, consuming tokens without providing executable guidance. | 1 / 3 |
Actionability | The code examples are pseudocode referencing non-existent libraries (VectorDatabase, context-restore CLI). The bash commands reference a tool that doesn't appear to exist. Nothing is copy-paste executable. The workflows are abstract descriptions ('Retrieve most recent project context') rather than concrete steps with real commands or APIs. | 1 / 3 |
Workflow Clarity | The two 'Reference Workflows' are vague 4-step abstractions with no validation checkpoints, no error recovery, and no concrete commands. Steps like 'Validate context against current codebase' and 'Selectively restore relevant components' are hand-wavy descriptions, not actionable instructions. No feedback loops exist for any operation. | 1 / 3 |
Progressive Disclosure | The content is a monolithic wall of text with 8 numbered strategy sections, most containing abstract descriptions. It references `resources/implementation-playbook.md` but no bundle files exist to support this. The content that could be split into reference files (advanced strategies, future roadmap) is all inline, making the skill overwhelming and poorly organized. | 1 / 3 |
Total | 4 / 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
f5dc9e3
- 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.