memory-systems

Design short-term, long-term, and graph-based memory architectures. Use when building agents that must persist across sessions, needing to maintain entity consistency across conversations, or implementing reasoning over accumulated knowledge.

Quality

48%

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/memory-systems/SKILL.md

Quality

Content

17%Scale 1-5

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

This skill reads like a textbook chapter or survey paper on memory architectures rather than an actionable skill for Claude. It is severely verbose, repeating concepts multiple times, explaining things Claude already knows (what vector stores are, what knowledge graphs are), and providing benchmark data without actionable implementation guidance. The code examples use undefined abstractions rather than concrete, executable implementations, and there are no validation steps or clear workflows for building any of the described memory systems.

Suggestions

Cut content by 60-70%: remove all conceptual explanations Claude already knows (what vector stores are, what knowledge graphs are, the context-memory spectrum), eliminate the duplicate description of the spectrum, and remove the benchmark table unless tied to a specific decision point.

Replace pseudocode examples with concrete, executable implementations using specific libraries (e.g., Neo4j for graph memory, ChromaDB for vector memory, SQLite for temporal tracking) with actual setup and query code.

Add a clear step-by-step workflow: 'To build a memory system: 1. Choose architecture based on [decision matrix] 2. Set up storage with [specific commands] 3. Implement write path 4. Implement read path 5. Validate with [specific test] 6. Add consolidation'.

Create bundle files for detailed implementation patterns (e.g., VECTOR_MEMORY.md, GRAPH_MEMORY.md, TEMPORAL_MEMORY.md) and reduce SKILL.md to a concise overview with clear references to these files.

Dimension	Reasoning	Score
Conciseness	Extremely verbose with extensive repetition (the context-memory spectrum is described twice nearly verbatim), lengthy explanations of concepts Claude already knows (what vector stores are, what knowledge graphs are, what working memory is), and heavy padding throughout. The 'When to Use' section repeats the description. The content could be reduced by 60-70% without losing actionable information.	1 / 5
Actionability	The skill is overwhelmingly conceptual and descriptive rather than actionable. The two code examples are pseudocode-like snippets using undefined abstractions (memory.store, memory.retrieve_entity, temporal_graph.query) with no concrete implementation. There are no executable commands, no specific library recommendations with installation steps, no concrete database setup instructions, and no copy-paste ready implementations.	2 / 5
Workflow Clarity	While the content describes layers and patterns, there is no clear step-by-step workflow for actually building a memory system. The 'Memory Consolidation' section lists a process but without concrete steps or validation. The 'Memory System Selection' section provides a decision tree but no implementation sequence. No validation checkpoints exist for any of the described operations.	2 / 5
Progressive Disclosure	The content is a monolithic wall of text with no bundle files to support it. References to 'Implementation Reference - Detailed implementation patterns' and related skills appear to be non-existent files. The 300+ lines of conceptual content should be split into separate files for each memory pattern, with the SKILL.md serving as a concise overview. Section headers exist but the content within them is excessively inlined.	2 / 5
	Total	7 / 20 Passed

Description

78%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.

This is a solid description that clearly communicates both what the skill does and when to use it, with an explicit 'Use when' clause covering multiple trigger scenarios. Its main weakness is that the 'what' portion could be more specific about concrete actions beyond 'design,' and the trigger terms, while good, miss some common user phrasings. Overall it performs well for skill selection purposes.

Suggestions

Add more concrete actions beyond 'design' — e.g., 'implement memory stores, configure retrieval strategies, build knowledge graphs, manage context windows' to improve specificity.

Include additional natural trigger terms and synonyms users might say, such as 'context window,' 'conversation history,' 'stateful,' 'recall,' 'RAG,' or 'knowledge base.'

Dimension	Reasoning	Score
Specificity	Names the domain (memory architectures) and lists three types (short-term, long-term, graph-based), but the actions are more about 'designing' at a high level rather than listing multiple concrete actions like 'create memory stores, query knowledge graphs, manage session state, prune stale entries.'	3 / 5
Completeness	Clearly answers both 'what' (design short-term, long-term, and graph-based memory architectures) and 'when' (building agents that persist across sessions, maintaining entity consistency, implementing reasoning over accumulated knowledge) with explicit 'Use when' clause and concrete trigger scenarios.	5 / 5
Trigger Term Quality	Includes good natural keywords like 'memory architectures,' 'persist across sessions,' 'entity consistency,' 'conversations,' and 'accumulated knowledge.' However, it misses common synonyms and variations users might say such as 'context window,' 'recall,' 'RAG,' 'knowledge base,' 'stateful agents,' or 'conversation history.'	4 / 5
Distinctiveness Conflict Risk	Fairly distinct with its focus on memory architectures for agents, which is a specific niche. However, there could be minor overlap with general agent-building skills or knowledge graph skills. The mention of 'graph-based' and 'entity consistency' helps differentiate but 'reasoning over accumulated knowledge' is somewhat broad.	4 / 5
	Total	16 / 20 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: administrakt0r/AI-Agents-Safe-Coding-Skills
Path: skills/memory-systems/SKILL.md
Commit: 57c135b

Reviewed: 3 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.