agent-memory-systems

You are a cognitive architect who understands that memory makes agents intelligent. You've built memory systems for agents handling millions of interactions. You know that the hard part isn't storing - it's retrieving the right memory at the right time.

Quality

32%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./plugins/AI-Agents-Safe-Coding-Skills/skills/agent-memory-systems/SKILL.md

The canonical home for this skill is agent-memory-systems in sickn33/agentic-awesome-skills

Quality

Content

36%Weight 40%Scale 1-5

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

The body is structured into reasonable sections but is largely empty and not actionable: patterns and anti-patterns are one-line stubs, and the Sharp Edges table is garbled with markdown headers in the Solution column. It provides no executable guidance or sequenced workflow.

Suggestions

Flesh out each Pattern with concrete guidance or code (e.g., a decision table for vector-store selection, example chunking code with embedding calls).

Fix the Sharp Edges table so the Solution column contains actual solutions instead of stray '## ...' headers, and include severity-appropriate mitigations.

Add a sequenced workflow with validation checkpoints for at least one representative task (e.g., evaluate chunk size against retrieval recall before committing).

Dimension	Reasoning	Score
Conciseness	The body is short and does not pad with concepts Claude already knows, so it is mostly token-efficient; it lands at 3 rather than 4 because the terseness leaves sections nearly empty rather than densely useful.	3 / 5
Actionability	Patterns such as 'Choosing the right memory type for different information' give only high-level hints with no concrete steps, code, or commands, matching 'minimal concrete guidance'; not a 3 because no executable detail or examples are provided.	2 / 5
Workflow Clarity	No sequenced multi-step workflow or validation checkpoints exist, and the Sharp Edges table is malformed (its Solution column holds markdown headers like '## Contextual Chunking'), leaving steps poorly defined; not a 3 because there is no coherent sequence at all.	2 / 5
Progressive Disclosure	Content is a single short file under 50 lines with organized section headers and no (broken) deep references, which the simple-skill exception allows to reach 3; not a 4 because several sections are empty or broken and add little navigational value.	3 / 5
	Total	10 / 20 Passed

Description

28%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description is written as first-person persona prose rather than a concise capability-and-trigger statement, so it lacks concrete actions and any 'Use when...' guidance. It names the memory domain but is vague on both what the skill does and when to invoke it.

Suggestions

Rewrite in third person stating concrete actions (e.g., 'Designs agent memory architectures: selects memory types, chooses vector stores, defines chunking and retrieval strategies').

Add an explicit 'Use when...' clause with natural trigger phrases users would say (e.g., 'Use when building agent memory systems, selecting vector databases, or tuning retrieval/chunking').

Remove persona backstory ('You are a cognitive architect...') which adds no evaluatable capability information.

Dimension	Reasoning	Score
Specificity	The description names the memory-systems domain but provides no concrete capability actions beyond the abstract phrase 'retrieving the right memory at the right time', matching the 'names domain but actions minimal or generic' anchor; not a 3 because no 1-2 concrete actions are listed.	2 / 5
Completeness	The 'what' is vague persona backstory rather than a stated capability, and there is no 'when' trigger clause at all, matching the 'vague what and no when' anchor; not a 3 because the what is not clearly stated as a concrete action.	2 / 5
Trigger Term Quality	Terms like 'memory', 'retrieving', and 'agents' appear but the text is persona prose ('You are a cognitive architect') with no natural user-utterance phrasing, so it has only generic keywords missing the phrases users actually say; not a 3 because common variations/synonyms are absent.	2 / 5
Distinctiveness Conflict Risk	'Memory systems for agents' is somewhat specific but very broad and could overlap with many agent-architecture skills, matching 'somewhat specific but could still overlap'; not a 4 because no distinct concrete triggers reduce overlap risk.	3 / 5
	Total	9 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: administrakt0r/AI-Agents-Safe-Coding-Skills
Path: plugins/AI-Agents-Safe-Coding-Skills/skills/agent-memory-systems/SKILL.md
Commit: 900c504

Reviewed: 14 minutes 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.