memory-systems

tessl i github:muratcankoylan/Agent-Skills-for-Context-Engineering --skill memory-systems

This skill should be used when the user asks to "implement agent memory", "persist state across sessions", "build knowledge graph", "track entities", or mentions memory architecture, temporal knowledge graphs, vector stores, entity memory, or cross-session persistence.

48%

Overall

Validation — 88%

Implementation — 35%

Activation — 37%

SKILL.md

Review

Evals

Validation

88%

Warnings & errors only

Criteria	Description	Result
metadata_version	'metadata' field is not a dictionary	Warning
license_field	'license' field is missing	Warning

	Total	14 / 16 Passed

Implementation

35%

This skill reads more like a textbook chapter than actionable guidance for Claude. It spends significant tokens explaining concepts (vector stores, knowledge graphs, memory layers) that Claude already understands, while providing minimal executable code or concrete implementation steps. The content would benefit from dramatic reduction to essential patterns with links to detailed references.

Suggestions

Reduce the document to ~100 lines focusing on decision criteria and key patterns, moving detailed explanations to reference files

Replace pseudocode examples with complete, executable implementations including imports, error handling, and actual database connections

Add explicit workflow with validation steps for implementing each memory pattern (e.g., 'Step 1: Set up graph DB, Step 2: Define schema, Step 3: Validate with test query')

Remove explanatory content about what vector stores and knowledge graphs are - Claude knows this; focus only on when to choose each and how to implement

Dimension	Reasoning	Score
Conciseness	Extremely verbose with extensive explanations of concepts Claude already knows (what vector stores are, what knowledge graphs are, the context-memory spectrum). The benchmark table and detailed layer explanations add bulk without providing actionable guidance. Much content describes rather than instructs.	1 / 3
Actionability	Provides some code examples for entity tracking and temporal queries, but they are incomplete pseudocode rather than executable implementations. Most content is conceptual explanation rather than concrete, copy-paste-ready guidance. Missing actual implementation details for the memory systems described.	2 / 3
Workflow Clarity	Lists memory layers and patterns but lacks clear step-by-step workflows for implementing any of them. The consolidation process mentions steps but without validation checkpoints. No feedback loops for error recovery when memory operations fail.	2 / 3
Progressive Disclosure	References an implementation reference file and related skills, but the main document is a monolithic wall of text with extensive inline content that should be split into separate files. The detailed topics section alone could be multiple reference documents.	2 / 3
	Total	7 / 12 Passed

Activation

37%

This description is essentially a list of trigger terms masquerading as a skill description. While it excels at providing keywords users might say, it completely fails to explain what the skill actually does - there are no concrete actions, capabilities, or outcomes described. This is an inverted skill description that needs the 'what' component added.

Suggestions

Add concrete actions at the beginning describing what the skill does, e.g., 'Implements persistent memory systems for agents including knowledge graphs, vector stores, and entity tracking across sessions.'

Restructure to lead with capabilities (what) before the trigger clause (when), following the pattern: '[Actions/capabilities]. Use when [triggers].'

Include specific deliverables or outcomes like 'creates memory schemas', 'configures vector databases', 'builds entity relationship models' to clarify the skill's concrete value.

Dimension	Reasoning	Score
Specificity	The description contains no concrete actions - it only lists trigger terms without explaining what the skill actually does. There are no verbs describing capabilities like 'builds', 'creates', 'stores', or 'retrieves'.	1 / 3
Completeness	The description only answers 'when' (trigger conditions) but completely omits 'what' - there is no explanation of what capabilities or actions this skill provides. The 'what' component is entirely missing.	1 / 3
Trigger Term Quality	Excellent coverage of natural trigger terms users would say: 'implement agent memory', 'persist state across sessions', 'build knowledge graph', 'track entities', plus technical terms like 'vector stores', 'entity memory', 'cross-session persistence'.	3 / 3
Distinctiveness Conflict Risk	The trigger terms are fairly specific to memory/persistence domain, but without knowing what the skill actually does, it could overlap with database skills, caching skills, or state management skills. The niche is somewhat clear but not fully distinct.	2 / 3
	Total	7 / 12 Passed

Reviewed

19 days ago

Table of Contents

Validation Implementation Activation

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.