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

Quality

Does it follow best practices?

Impact

Pending

No eval scenarios have been run

Securityby

Passed

No known issues

Optimize this skill with Tessl

npx tessl skill review --optimize ./.agent/skills/agent-memory-systems/SKILL.md

Quality

Discovery

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 about memory concepts rather than a functional skill description. It provides no concrete actions, no trigger guidance, and appears to be truncated mid-sentence. The philosophical framing ('Memory is the cornerstone...') and conceptual explanations fail to communicate what Claude should actually do with this skill.

Suggestions

Replace conceptual explanations with concrete actions (e.g., 'Store conversation context, retrieve relevant past interactions, manage long-term knowledge bases')

Add explicit trigger guidance with a 'Use when...' clause containing natural user terms like 'remember this', 'recall our previous conversation', 'save this for later'

Remove educational content and focus on actionable capabilities - the description should tell Claude what to do, not teach theory about memory systems

Dimension	Reasoning	Score
Specificity	The description uses abstract, conceptual language ('cornerstone of intelligent agents', 'cognitive architectures') without listing concrete actions Claude can perform. It reads like educational content rather than a capability description.	1 / 3
Completeness	The description explains conceptual background about memory systems but never states what this skill actually does or when Claude should use it. No 'Use when...' clause or equivalent trigger guidance exists.	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 'save context'.	1 / 3
Distinctiveness Conflict Risk	The description is so vague about actual capabilities that it's unclear what domain this skill serves. 'Memory' and 'agents' are extremely broad terms that could conflict with many other skills.	1 / 3
	Total	4 / 12 Passed

Implementation

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

This skill content is severely underdeveloped and appears truncated. It consists primarily of persona framing, abstract philosophy about memory, a keyword list labeled 'Capabilities', and links to sub-skills without any actual instructional content. There is no actionable guidance, no code examples, and no concrete implementation details that would help Claude build memory systems.

Suggestions

Add concrete, executable code examples for at least one memory implementation (e.g., vector store setup, chunking implementation, retrieval query)

Replace the persona framing and philosophical content with a concise quick-start section showing how to implement basic agent memory

Provide a brief overview of when to use each memory type before linking to sub-skills, so the main skill has standalone value

Remove the 'Capabilities' keyword list - it provides no actionable information and wastes tokens

Dimension	Reasoning	Score
Conciseness	The content is padded with unnecessary persona framing ('You are a cognitive architect...') and philosophical statements that Claude doesn't need. The 'Capabilities' section is just a list of keywords with no actionable value.	1 / 3
Actionability	No concrete code, commands, or executable guidance provided. The content describes concepts abstractly ('Memory failures look like intelligence failures') without any specific implementation details, examples, or copy-paste ready solutions.	1 / 3
Workflow Clarity	No workflow or process is defined. The skill references sub-skills but provides no sequencing, validation steps, or guidance on how to actually implement memory systems. The content appears truncated mid-sentence.	1 / 3
Progressive Disclosure	The structure attempts progressive disclosure by linking to sub-skills, which is appropriate. However, the main skill provides no useful overview content - just persona description and keyword lists before jumping to references.	2 / 3
	Total	5 / 12 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: Dokhacgiakhoa/antigravity-ide
Commit: 3395991

Reviewed: 24 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.