context-manager

Elite AI context engineering specialist mastering dynamic context management, vector databases, knowledge graphs, and intelligent memory systems. Orchestrates context across multi-agent workflows, enterprise AI systems, and long-running projects with 2024/2025 best practices. Use PROACTIVELY for complex AI orchestration.

Overall
score

38%

Review — 29%

Does it follow best practices?

Validation — 13 / 16 Passed

Validation for skill structure

Install with Tessl CLI

npx tessl i github:sickn33/antigravity-awesome-skills --skill context-manager

Activation

50%

The description relies heavily on impressive-sounding buzzwords ('Elite', 'mastering', '2024/2025 best practices') without specifying concrete actions Claude would perform. It lacks natural trigger terms users would actually say and provides only a vague 'Use PROACTIVELY' guidance that doesn't help Claude distinguish when to select this skill over others.

Suggestions

Replace vague buzzwords with specific actions (e.g., 'Manages context windows, implements RAG pipelines, configures vector database queries, builds knowledge graph schemas').

Add a proper 'Use when...' clause with natural trigger phrases (e.g., 'Use when user mentions context limits, RAG, embeddings, semantic search, or asks about managing AI memory').

Remove marketing language ('Elite', 'mastering', '2024/2025 best practices') and use third-person action verbs describing what the skill actually does.

Dimension	Reasoning	Score
Specificity	Names domain (context engineering) and lists some areas (vector databases, knowledge graphs, memory systems), but uses vague buzzwords like 'Elite', 'mastering', 'orchestrates' rather than concrete actions. No specific operations are described.	2 / 3
Completeness	The 'what' is partially addressed through domain listing, but the 'when' clause ('Use PROACTIVELY for complex AI orchestration') is vague and unhelpful. No explicit trigger scenarios or user request patterns are provided.	2 / 3
Trigger Term Quality	Includes some relevant technical terms (vector databases, knowledge graphs, multi-agent workflows) but these are jargon-heavy. Missing natural user phrases like 'manage context', 'AI memory', 'context window'. 'Use PROACTIVELY' is not a natural trigger.	2 / 3
Distinctiveness Conflict Risk	Terms like 'multi-agent workflows', 'enterprise AI systems', and 'AI orchestration' are broad and could overlap with many AI-related skills. The description lacks specific file types, commands, or unique identifiers.	2 / 3
	Total	8 / 12 Passed

Implementation

This skill content is essentially a persona/role description rather than an actionable skill. It extensively lists capabilities and knowledge areas that Claude already possesses, without providing any concrete implementation guidance, code examples, or specific workflows. The content would be more appropriate as a system prompt for role-playing than as a skill teaching Claude how to perform specific tasks.

Suggestions

Replace capability lists with concrete, executable code examples for key tasks like vector database setup, RAG implementation, or context window optimization

Add specific tool commands and validation steps (e.g., 'Run `pinecone.describe_index()` to verify index creation')

Remove the extensive 'Capabilities', 'Behavioral Traits', and 'Knowledge Base' sections - Claude already knows these concepts

Transform 'Example Interactions' into actual worked examples with input/output pairs and implementation code

Dimension	Reasoning	Score
Conciseness	Extremely verbose with extensive lists of capabilities, behavioral traits, and knowledge areas that Claude already knows. The content reads like a persona description rather than actionable instructions, with massive padding that doesn't add operational value.	1 / 3
Actionability	No concrete code, commands, or executable examples. The entire skill describes capabilities and concepts abstractly ('Dynamic context assembly', 'Vector database implementation') without providing any actual implementation guidance or copy-paste ready solutions.	1 / 3
Workflow Clarity	The 'Response Approach' section lists 10 vague steps like 'Analyze context requirements' and 'Design context architecture' without any concrete validation checkpoints, specific tools, or actionable sequences. No feedback loops or error recovery mechanisms are defined.	1 / 3
Progressive Disclosure	References `resources/implementation-playbook.md` for detailed examples, which is appropriate progressive disclosure. However, the main content is a monolithic wall of capability lists that could be better organized, and it's unclear what the referenced file actually contains.	2 / 3
	Total	5 / 12 Passed

Validation

81%

Warnings & errors only

Validation — 13 / 16 Passed

Validation for skill structure

Criteria	Description	Result
description_trigger_hint	Description may be missing an explicit 'when to use' trigger hint (e.g., 'Use when...')	Warning
metadata_version	'metadata.version' is missing	Warning
license_field	'license' field is missing	Warning

	Total	13 / 16 Passed

Reviewed

20 days ago

Table of Contents

Activation 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.