agent-memory-systems
Memory is the cornerstone of intelligent agents. Without it, every interaction starts from zero. This skill covers the architecture of agent memory: short-term (context window), long-term (vector stores), and the cognitive architectures that organize them. Key insight: Memory isn't just storage - it's retrieval. A million stored facts mean nothing if you can't find the right one. Chunking, embedding, and retrieval strategies determine whether your agent remembers or forgets. The field is fragm
Install with Tessl CLI
npx tessl i github:duclm1x1/Dive-Ai --skill agent-memory-systems28
Does it follow best practices?
If you maintain this skill, you can automatically optimize it using the tessl CLI to improve its score:
npx tessl skill review --optimize ./path/to/skillValidation for skill structure
Discovery
7%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 description reads like an educational essay or course overview rather than a functional skill description. It provides conceptual background about memory systems but fails to specify what actions Claude can take, when to use this skill, or include natural trigger terms users would say. The description also appears truncated ('The field is fragm').
Suggestions
Replace conceptual exposition with concrete actions (e.g., 'Implements memory systems for agents including vector store setup, embedding strategies, and retrieval optimization').
Add an explicit 'Use when...' clause with natural trigger terms like 'agent memory', 'remember context', 'vector database', 'RAG system', or 'long-term storage'.
Remove philosophical framing ('cornerstone', 'Key insight') and focus on actionable capabilities that distinguish this skill from general AI development skills.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description uses abstract, conceptual language ('cornerstone of intelligent agents', 'cognitive architectures') without listing concrete actions Claude can perform. No specific capabilities like 'create memory stores' or 'retrieve embeddings' are mentioned. | 1 / 3 |
Completeness | The description explains conceptual background about memory but never answers 'what does this skill do' in actionable terms, and completely lacks any 'Use when...' clause or explicit trigger guidance. | 1 / 3 |
Trigger Term Quality | Contains technical jargon ('vector stores', 'chunking', 'embedding') that users wouldn't naturally say. Missing natural trigger terms like 'remember', 'store information', 'recall', or 'agent memory system'. | 1 / 3 |
Distinctiveness Conflict Risk | The focus on 'agent memory' and specific terms like 'vector stores' and 'embeddings' provides some distinctiveness, but the vague framing could overlap with general AI/ML skills or documentation skills. | 2 / 3 |
Total | 5 / 12 Passed |
Implementation
14%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill is essentially a skeleton with headers but no substantive content. The patterns and anti-patterns sections are empty, the Sharp Edges table is malformed with nonsensical entries, and there's no actionable guidance on implementing memory systems. The skill describes what memory systems are conceptually but provides zero executable or practical guidance.
Suggestions
Add concrete code examples for each memory type (e.g., vector store initialization, chunking implementation, retrieval queries)
Fix the Sharp Edges table - currently the 'Issue' column repeats 'Issue' and solutions appear to be random code comments; provide actual issue descriptions and actionable solutions
Fill in the Pattern sections with actual implementation steps, code snippets, and decision criteria (e.g., when to use episodic vs semantic memory)
Add a Quick Start section with a minimal working example of setting up an agent memory system
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content has some unnecessary narrative framing ('You are a cognitive architect...') and the capabilities list is verbose. However, it's not excessively padded with explanations Claude would already know. | 2 / 3 |
Actionability | The skill provides no concrete code, commands, or executable examples. Pattern sections are empty headers with no implementation details. The 'Sharp Edges' table has malformed content with solutions that appear to be random code comments rather than actual guidance. | 1 / 3 |
Workflow Clarity | There are no clear workflows, sequences, or validation steps. The patterns are listed as headers only with no actual process descriptions. No guidance on how to implement any memory system. | 1 / 3 |
Progressive Disclosure | The content is poorly organized with empty sections, a malformed table, and no references to detailed documentation. The structure suggests organization but delivers no actual content in most sections. | 1 / 3 |
Total | 5 / 12 Passed |
Validation
90%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 | |
- 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.