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

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-claude/skills/agent-memory-systems/SKILL.md

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

Quality

Content

0%Scale 1-3

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 an empty outline with placeholder content. It provides no actionable guidance, no code examples, no concrete workflows, and no real information about implementing agent memory systems. The sharp edges table contains dummy 'Issue' placeholders and solutions that are just markdown headings, indicating the content was never completed.

Suggestions

Replace the abstract introduction with concrete, executable code examples showing how to implement at least one memory type (e.g., a working vector store setup with embedding and retrieval code).

Fill in the Patterns sections with actual step-by-step workflows including specific tools, libraries, and validation steps (e.g., how to test chunking strategies with retrieval quality metrics).

Replace the placeholder 'Issue' entries in the Sharp Edges table with real issues and concrete solutions with code or commands.

Either add substantive content to each section or remove empty sections and link to separate detailed files for each memory type pattern.

Dimension	Reasoning	Score
Conciseness	The opening paragraphs explain concepts Claude already knows (what memory failures look like, that retrieval is harder than storage). The capabilities list is pure padding with no actionable content. The content is verbose yet paradoxically incomplete—it wastes tokens on fluff while providing no substance.	1 / 3
Actionability	There is zero executable code, no concrete commands, no specific examples, and no actual instructions. Every section is a heading or label with no content beneath it. The patterns are named but never described. The sharp edges table has placeholder 'Issue' text and solutions that are just headings with no explanation.	1 / 3
Workflow Clarity	There are no workflows, no sequenced steps, no validation checkpoints. The patterns section lists names without any process description. There is no guidance on how to actually implement any memory system.	1 / 3
Progressive Disclosure	The content is a skeleton of headings with no substance and no references to external files. There's no navigation structure—just empty sections. The 'Related Skills' section lists names but provides no links or context for how they connect.	1 / 3
	Total	4 / 12 Passed

Description

0%Scale 1-3

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 is a persona statement rather than a skill description. It contains no concrete actions, no trigger terms, and no guidance on when to use the skill. It violates the third-person voice requirement by using second-person framing ('You are') and relies entirely on vague, self-promotional language.

Suggestions

Replace the persona framing with concrete actions the skill performs, e.g., 'Stores, indexes, and retrieves agent memory entries across conversations. Manages semantic search over past interactions.'

Add an explicit 'Use when...' clause with natural trigger terms, e.g., 'Use when the user asks about agent memory, conversation history, context retrieval, or persistent state across sessions.'

Remove first/second person voice ('You are', 'You've built') and rewrite in third person describing what the skill does, not who the user is.

Dimension	Reasoning	Score
Specificity	The description contains no concrete actions whatsoever. It uses abstract, metaphorical language like 'cognitive architect' and 'memory makes agents intelligent' without specifying what the skill actually does (e.g., store, retrieve, index, search).	1 / 3
Completeness	Neither 'what does this do' nor 'when should Claude use it' is answered. There is no 'Use when...' clause or equivalent trigger guidance, and the capabilities are entirely absent—replaced by self-aggrandizing persona framing.	1 / 3
Trigger Term Quality	There are no natural user-facing keywords. Terms like 'cognitive architect' and 'millions of interactions' are not things a user would say when needing a memory system skill. 'Memory' appears but only in vague, philosophical context.	1 / 3
Distinctiveness Conflict Risk	The description is so vague it could apply to any agent-related, data storage, or retrieval skill. There are no distinct triggers or domain-specific terms that would differentiate it from other skills.	1 / 3
	Total	4 / 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: administrakt0r/AI-Agents-Safe-Coding-Skills
Path: plugins/AI-Agents-Safe-Coding-Skills-claude/skills/agent-memory-systems/SKILL.md
Commit: 7520423

Reviewed: ~11 hours 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.