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 s...

1.10x

Quality

Does it follow best practices?

Impact

76%

1.10x

Average score across 3 eval scenarios

Securityby

Passed

No known issues

Optimize this skill with Tessl

npx tessl skill review --optimize ./skills/antigravity-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 academic introduction rather than a functional skill description. It focuses on conceptual framing ('cornerstone', 'architecture') instead of actionable capabilities, contains no trigger terms users would naturally use, and is truncated mid-word. The description fails to help Claude distinguish when to select this skill over others.

Suggestions

Replace philosophical framing with concrete actions: 'Store and retrieve information across conversations, manage persistent notes, search saved knowledge' instead of 'cornerstone of intelligent agents'

Add explicit trigger guidance: 'Use when the user asks to remember something, save notes, recall previous information, or manage persistent knowledge'

Include natural user keywords: 'remember', 'save', 'notes', 'recall', 'look up', 'stored information', 'knowledge base'

Dimension	Reasoning	Score
Specificity	The description uses abstract, philosophical language ('cornerstone of intelligent agents', 'architecture of agent memory') without listing any concrete actions Claude can perform. No specific capabilities like 'store', 'retrieve', 'search', or 'update' are mentioned.	1 / 3
Completeness	The description only vaguely addresses 'what' (covers architecture of memory) and completely lacks any 'when' guidance. There is no 'Use when...' clause or equivalent trigger guidance.	1 / 3
Trigger Term Quality	Contains technical jargon ('vector s...', 'context window') that users wouldn't naturally say. Missing natural trigger terms like 'remember', 'recall', 'save information', 'notes', or 'knowledge base'.	1 / 3
Distinctiveness Conflict Risk	The description is extremely generic - 'memory' and 'intelligent agents' could apply to virtually any skill involving data persistence, context management, or knowledge retrieval. High conflict risk with many potential skills.	1 / 3
	Total	4 / 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 placeholders, the sharp edges table is malformed with placeholder text, and the overview cuts off mid-sentence. It fails to provide any actionable guidance on implementing memory systems for agents.

Suggestions

Complete the pattern sections with executable code examples showing how to implement each memory type (e.g., vector store setup, chunking implementation)

Fix the Sharp Edges table - replace 'Issue' placeholders with actual problems and provide complete solutions, not just code comments

Add a concrete workflow showing the full memory lifecycle: storage -> indexing -> retrieval -> usage with validation checkpoints

Remove the philosophical framing in the intro and replace with a quick-start example demonstrating basic memory storage and retrieval

Dimension	Reasoning	Score
Conciseness	The content has some unnecessary philosophical framing ('cognitive architect', 'obsess over') but isn't excessively verbose. However, the capabilities list is bloated with 10 items that could be condensed, and the content cuts off mid-sentence suggesting incomplete editing.	2 / 3
Actionability	The skill provides no concrete code, commands, or executable guidance. Pattern sections are empty headers with no implementation details. The 'Sharp Edges' table has broken content with 'Issue' placeholders and solutions that are just comments without context.	1 / 3
Workflow Clarity	There are no clear workflows, sequences, or validation steps. The patterns section lists concepts without explaining how to implement them. No multi-step processes are defined despite memory systems requiring complex retrieval/storage workflows.	1 / 3
Progressive Disclosure	The document is poorly organized with empty pattern sections, a malformed table, and no references to detailed documentation. The structure suggests sections but delivers no actual content within them.	1 / 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: boisenoise/skills-collections
Commit: 5c5ae21

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.