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.

Quality

35%

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 ./skills/context-manager/SKILL.md

Quality

Content

20%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is an over-long, buzzword-heavy catalog of capability areas and known concepts with essentially no concrete, executable guidance or validation-bearing workflow, and it fails to offload detail into reference files.

Suggestions

Cut the 'Behavioral Traits' and 'Knowledge Base' sections entirely and trim the capability bullet lists to only what Claude would not already know; aim for a lean overview under ~50 lines.

Add concrete, copy-paste-ready guidance for at least the core tasks (e.g., a minimal RAG retrieval snippet, a vector-index setup command, a context-handoff protocol template).

Move detailed catalogs and examples into reference files under references/ and link to them one level deep from SKILL.md, and add explicit validate-then-fix checkpoints to the Response Approach.

Dimension	Reasoning	Score
Conciseness	The body is a ~170-line monolith listing ~70 capability bullets plus 'Behavioral Traits' and 'Knowledge Base' sections that restate concepts Claude already knows ('Vector database technologies', 'Information retrieval theory'), directly violating the token-efficiency guideline against padding and explaining known concepts.	1 / 3
Actionability	There is no executable code, commands, or concrete how-to anywhere; 'Instructions' and 'Response Approach' offer only abstract direction ('Apply relevant best practices', 'Design context architecture') and the Capabilities are bullet lists of areas rather than instructions.	1 / 3
Workflow Clarity	A numbered 'Response Approach' sequence exists, but its ten steps are high-level phases with no validation checkpoints, no commands, and no error-recovery feedback loops for the risky multi-step operations the skill claims to cover.	2 / 3
Progressive Disclosure	Content is organized under heading sections, but no bundle files exist and the large capability catalogs, knowledge base, and examples that should live in separate reference files are all inlined into SKILL.md, making it a monolith rather than an overview with one-level-deep references.	2 / 3
	Total	6 / 12 Passed

Description

50%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description names a recognizable domain and includes an explicit trigger clause, but it is heavy on buzzwords and over-claims ('Elite', 'mastering') and its trigger condition is too generic to reliably distinguish the skill from other AI-orchestration skills.

Suggestions

Replace abstract verbs ('mastering', 'Orchestrates') with concrete actions the skill performs (e.g., 'Designs vector retrieval pipelines', 'Builds multi-agent context handoff protocols').

Sharpen the 'Use when...' trigger to concrete situations users would describe, e.g. 'Use when designing RAG pipelines, knowledge graphs, multi-agent context handoff, or context-window optimization'.

Drop puffery ('Elite', '2024/2025 best practices') that adds tokens without clarifying capability or triggers.

Dimension	Reasoning	Score
Specificity	Names the domain and several concrete sub-areas ('vector databases, knowledge graphs, and intelligent memory systems'), but the stated actions are abstract gerunds ('mastering', 'Orchestrates') rather than concrete operations, and the text is padded with buzzwords like 'Elite' and 'best practices'.	2 / 3
Completeness	It states what the skill does and includes an explicit 'Use PROACTIVELY for complex AI orchestration' trigger, but the when is vague rather than tied to concrete, observable situations, so it does not clearly answer when with explicit triggers.	2 / 3
Trigger Term Quality	It includes relevant technical keywords ('context management', 'multi-agent workflows', 'knowledge graphs') that a user might say, but the actual trigger clause ('complex AI orchestration') is generic and omits common natural variations like 'RAG' or 'context window'.	2 / 3
Distinctiveness Conflict Risk	The 'context engineering' niche is somewhat specific, but the broad 'complex AI orchestration' framing and enterprise AI language would overlap with many general AI skills rather than carving a clearly distinct trigger space.	2 / 3
	Total	8 / 12 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_version	'metadata.version' is missing	Warning

	Total	15 / 16 Passed

Repository: rmyndharis/antigravity-skills
Path: skills/context-manager/SKILL.md
Commit: e63f7dd

Reviewed: about 5 hours 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.