context-management-context-restore

Use when working with context management context restore

Quality

14%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./plugins/antigravity-awesome-skills-claude/skills/context-management-context-restore/SKILL.md

Quality

Content

7%Scale 1-3

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 conceptual overview document masquerading as actionable guidance. It explains general software architecture patterns (vector search, context merging, caching) that Claude already understands, using pseudocode with undefined functions that cannot be executed. The content lacks any concrete, real-world tool integration, validation steps, or executable workflows, making it essentially unusable as a skill.

Suggestions

Replace pseudocode with executable code that uses real libraries/tools, or if this is a conceptual framework, provide concrete CLI commands and file paths that Claude can actually use.

Remove the Role Statement, Context Overview, Future Roadmap, and Integration Patterns sections — these consume tokens without adding actionable value.

Add explicit validation checkpoints to workflows (e.g., 'Verify restored context contains expected keys', 'Check token count does not exceed budget') with concrete verification commands.

Either provide the referenced 'resources/implementation-playbook.md' bundle file or remove the reference and inline the essential actionable content.

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 Python code examples are pseudocode that explain general concepts rather than providing specific, usable implementations.	1 / 3
Actionability	The code examples are illustrative pseudocode calling undefined functions (VectorDatabase, calculate_composite_score, prioritize_components, etc.) that cannot be executed. The CLI examples reference a non-existent 'context-restore' tool with no installation or setup instructions. The skill describes concepts rather than providing concrete, executable guidance.	1 / 3
Workflow Clarity	The two 'Reference Workflows' are high-level 4-step summaries with no concrete commands, validation checkpoints, or error recovery steps. The 8 numbered strategies are topic headers with vague descriptions rather than sequenced, actionable workflows. No feedback loops or verification steps are present despite the complexity and risk of context restoration operations.	1 / 3
Progressive Disclosure	There is a reference to 'resources/implementation-playbook.md' for detailed examples, but no bundle files exist to support it. The content itself is a monolithic wall of text that mixes overview, strategies, code, workflows, and roadmap all in one file without clear navigation hierarchy. Some structural organization exists via headers.	2 / 3
	Total	5 / 12 Passed

Description

22%Scale 1-3

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 minimal and fails to communicate what the skill actually does. It only provides a 'Use when' clause that essentially restates the skill's name without adding any useful information. The lack of concrete actions and meaningful trigger terms makes it nearly useless for skill selection among a large set of options.

Suggestions

Add concrete actions describing what the skill does, e.g., 'Saves, loads, and restores conversation context and session state across interactions.'

Expand the 'Use when' clause with natural trigger terms users would say, e.g., 'Use when the user asks to save context, restore a previous session, resume a conversation, or manage conversation history.'

Include specific file types, commands, or scenarios to improve distinctiveness, e.g., 'Works with .context files, session snapshots, or memory persistence.'

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 operations or capabilities.	1 / 3
Completeness	The 'what does this do' component is entirely missing—there is no explanation of capabilities. While there is a 'Use when' clause, it only restates the skill name without providing meaningful trigger guidance, making both halves very weak.	1 / 3
Trigger Term Quality	It includes the terms 'context management' and 'context restore,' which are somewhat relevant keywords a user might use, but they are repetitive ('context' appears twice) and miss common variations or natural phrasing users might employ.	2 / 3
Distinctiveness Conflict Risk	The terms 'context management' and 'context restore' provide some specificity to a niche, but without concrete actions or clearer scope, it could overlap with other skills related to session management, memory, or state restoration.	2 / 3
	Total	6 / 12 Passed

Validation

90%

Warnings & errors only

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: popey/claude-code-skills
Path: plugins/antigravity-awesome-skills-claude/skills/context-management-context-restore/SKILL.md
Commit: a5a6601

Reviewed: 5 days ago

Table of Contents

Discovery Implementation Validation

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.