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

25%Weight 40%Scale 1-5

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

The body is a verbose capability catalog heavy on abstract bullets and concepts Claude already knows, with no executable code, no validation checkpoints, and no progressive disclosure via reference files. It describes what the skill knows rather than telling Claude concretely what to do.

Suggestions

Cut the abstract 'Behavioral Traits' and 'Knowledge Base' bullet lists that restate concepts Claude already knows, and replace with concise, actionable guidance.

Add concrete, executable examples or commands for the core tasks (e.g., a minimal RAG pipeline snippet, a vector index setup, a knowledge-graph modeling pattern) and explicit validation checkpoints in the Response Approach.

Move the large capability and reference catalogs into separate one-level-deep reference files (e.g., CAPABILITIES.md, RAG.md) and link to them from a concise overview, improving progressive disclosure and token efficiency.

Dimension	Reasoning	Score
Conciseness	The body is a ~185-line catalog of 70+ abstract capability bullets plus 'Behavioral Traits' and 'Knowledge Base' sections restating AI concepts Claude already knows, matching the 'noticeably verbose; several unnecessary explanations or padded sections' anchor.	2 / 5
Actionability	It provides only abstract descriptions like 'Dynamic context assembly' and 'Optimize RAG performance' with no concrete code, commands, or specific executable steps, sitting between the 'entirely vague' and 'minimal concrete guidance' anchors but closer to minimal high-level hints.	2 / 5
Workflow Clarity	The 'Response Approach' gives a rough 10-step sequence but steps are high-level with no concrete commands and no validation checkpoints, and the remaining sections are unstructured catalogs, matching 'rough sequence present but many gaps; validation absent'.	2 / 5
Progressive Disclosure	It is a single monolithic file with no bundle files or external references and no navigation, while large reference-style catalogs (capabilities, knowledge base) that belong in separate files are inlined, matching the 'minimal structure; content that clearly belongs in separate files is inlined' anchor.	2 / 5
	Total	8 / 20 Passed

Description

46%Weight 40%Scale 1-5

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 is domain-rich and grammatically clear but leans on abstract claims and buzzwords ('Elite', 'mastering') with weak, non-natural trigger phrasing and a missing explicit 'Use when...' clause. Its very broad scope creates significant conflict risk with adjacent AI skills.

Suggestions

Replace abstract verbs ('mastering', 'orchestrates') with several concrete actions the skill actually performs (e.g., 'designs vector indexes', 'builds RAG retrieval pipelines', 'models knowledge graphs').

Add an explicit 'Use when...' clause with natural user trigger phrases (e.g., 'Use when the user asks to design a RAG system, build a knowledge graph, or manage multi-agent context').

Narrow the scope or sharpen the niche to reduce overlap with general AI/agent-orchestration skills and improve distinctiveness.

Dimension	Reasoning	Score
Specificity	The description names the domain richly (vector databases, knowledge graphs, intelligent memory systems) but the actions are abstract verbs like 'mastering' and 'orchestrates' rather than a list of several specific concrete actions, fitting the 'names domain and 1-2 concrete actions' anchor.	3 / 5
Completeness	It gives a clear 'what' (context engineering specialist mastering dynamic context management, etc.) but the 'when' is only weakly implied via 'complex AI orchestration' with no explicit 'Use when...' clause, which per the judging guidelines caps completeness at 3.	3 / 5
Trigger Term Quality	Relevant domain terms (context management, RAG, memory, vector databases) appear, but the only trigger phrasing is 'Use PROACTIVELY for complex AI orchestration', a system keyword rather than natural user utterances, leaving common natural trigger phrases missing.	3 / 5
Distinctiveness Conflict Risk	The scope is very broad, spanning RAG, memory, knowledge graphs, vector DBs, and multi-agent orchestration, creating high overlap risk with many related AI skills, matching the 'very broad; high overlap risk' anchor.	2 / 5
	Total	11 / 20 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: 3eff4af

Reviewed: 1 day 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.