memory-systems
Guides implementation of agent memory systems, compares production frameworks (Mem0, Zep/Graphiti, Letta, LangMem, Cognee), and designs persistence architectures for cross-session knowledge retention. Use when the user asks to "implement agent memory", "persist state across sessions", "build knowledge graph for agents", "track entities over time", "add long-term memory", "choose a memory framework", or mentions temporal knowledge graphs, vector stores, entity memory, adaptive memory, dynamic memory or memory benchmarks (LoCoMo, LongMemEval).
Install with Tessl CLI
npx tessl i github:muratcankoylan/Agent-Skills-for-Context-Engineering --skill memory-systems91
Quality
92%
Does it follow best practices?
Impact
83%
1.33xAverage score across 3 eval scenarios
Optimize this skill with Tessl
npx tessl skill review --optimize ./skills/memory-systems/SKILL.mdDiscovery
100%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 an excellent skill description that hits all the marks. It provides specific capabilities with named frameworks, comprehensive trigger terms covering both natural language and technical terminology, explicit 'Use when...' guidance, and a clearly defined niche that distinguishes it from related skills. The description uses proper third-person voice throughout.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple concrete actions: 'guides implementation', 'compares production frameworks' (with specific names: Mem0, Zep/Graphiti, Letta, LangMem, Cognee), and 'designs persistence architectures'. The framework names add significant specificity. | 3 / 3 |
Completeness | Clearly answers both what (guides implementation, compares frameworks, designs architectures) AND when with an explicit 'Use when...' clause containing multiple specific trigger phrases and scenarios. | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural terms users would say: 'implement agent memory', 'persist state across sessions', 'build knowledge graph', 'add long-term memory', 'choose a memory framework', plus technical terms like 'temporal knowledge graphs', 'vector stores', 'entity memory', and benchmark names. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive niche focused specifically on agent memory systems with named frameworks and specific concepts (temporal knowledge graphs, LoCoMo, LongMemEval benchmarks). Unlikely to conflict with general coding or database skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
85%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a strong skill document that provides comprehensive, actionable guidance for implementing agent memory systems. The framework comparison tables and benchmark data are particularly valuable, and the code examples are executable. Minor verbosity in the opening sections and some redundancy with metadata could be trimmed for better token efficiency.
Suggestions
Remove or condense the opening paragraph and 'When to Activate' section since this information is already in the skill description metadata
Consider moving the detailed benchmark comparison table to the implementation reference file to reduce main document length
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is mostly efficient with good use of tables and structured content, but includes some unnecessary explanatory text (e.g., 'Memory provides the persistence layer...' opening paragraph) and the 'When to Activate' section largely duplicates the skill description metadata. | 2 / 3 |
Actionability | Provides concrete, executable code examples for Mem0, temporal queries, and Cognee integration. The framework comparison tables give specific guidance, and the 'Choosing a Memory Architecture' section provides clear decision criteria with actionable steps. | 3 / 3 |
Workflow Clarity | Clear progression from simple to complex architectures (prototype → scale → complex reasoning → full control). Error recovery section provides explicit fallback strategies, and the anti-patterns section helps avoid common mistakes. Validation is implicit through benchmark testing guidance. | 3 / 3 |
Progressive Disclosure | Well-organized with clear sections, appropriate use of tables for comparison data, and explicit references to external files (implementation.md) and related skills. Content is appropriately split between overview and detailed references. | 3 / 3 |
Total | 11 / 12 Passed |
Validation
100%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
- Reviewed
Table of Contents
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.