agent-memory-mcp

A hybrid memory system that provides persistent, searchable knowledge management for AI agents (Architecture, Patterns, Decisions).

8.00x

Quality

69%

Does it follow best practices?

Impact

96%

8.00x

Average score across 3 eval scenarios

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

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

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

Quality

Content

75%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 a compact, actionable setup guide with real commands and well-documented tool signatures. Its main weaknesses are the absence of any verification/integration step (registering the MCP server with the agent, confirming it is running) and a filler 'When to Use' section that adds no guidance.

Suggestions

Add the step that registers the running MCP server with the agent's client (e.g., an mcp config snippet) and a verification checkpoint such as calling memory_stats({}) to confirm the connection before use.

Replace the circular 'When to Use' filler sentence with concrete trigger guidance (e.g., when to record a decision vs. search existing patterns) or delete the section.

Move the four MCP tool definitions (args + usage) into a references/ file (e.g., TOOLS.md) and keep a one-line pointer per tool in SKILL.md to reduce context overhead.

Dimension	Reasoning	Score
Conciseness	The body is lean and command-driven with no padding, but the circular 'When to Use' line ('This skill is applicable to execute the workflow or actions described in the overview.') is pure filler that should be trimmed, matching anchor 4 rather than 5.	4 / 5
Actionability	Setup commands (git clone URL, npm install/compile, 'npm run start-server my-project $(pwd)') and per-tool args with usage examples are mostly executable, but the missing step to register the running MCP server with the agent's MCP client leaves a gap between 'mostly executable' and fully copy-paste ready.	4 / 5
Workflow Clarity	The clone → install → compile → start-server sequence is clearly ordered with concrete commands, but there are no verification checkpoints (no server-ready check, no connection test) and no step connecting the MCP server to the agent, which is more than the 'minor validation gaps' of anchor 5 yet better defined than anchor 3's bare step list.	4 / 5
Progressive Disclosure	Sections are well organized (Prerequisites, Setup, Capabilities, Dashboard) with no references to nonexistent files, but at ~79 lines with four documented MCP tools the tool API could be split into a one-level-deep reference file, so it falls short of the clear-overview-with-signaled-references anchor.	4 / 5
	Total	16 / 20 Passed

Description

50%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 gives a clear picture of what the skill is, but says nothing about when to use it and lacks the natural trigger phrases a user would say when needing persistent memory. It reads as a moderate, domain-naming description rather than a strong activation surface.

Suggestions

Append an explicit trigger clause, e.g., 'Use when the user asks to remember, save, or recall project knowledge, decisions, or patterns across sessions.'

State the concrete capabilities as actions: 'search, write, and read long-term agent memories (architecture, patterns, decisions) via MCP tools.'

Include natural synonyms users would say — 'long-term memory', 'knowledge base', 'remember this', 'recall' — to improve trigger term coverage and distinctiveness from generic note-taking skills.

Dimension	Reasoning	Score
Specificity	'A hybrid memory system that provides persistent, searchable knowledge management' names the domain and implies 1-2 actions (persist, search) without stating concrete operations like reading/writing/searching memories via MCP tools, sitting between the minimal-actions anchor 2 and the 1-2-concrete-actions anchor 3.	3 / 5
Completeness	The 'what' is clearly stated (persistent, searchable knowledge management for AI agents), but there is no 'Use when...' clause or equivalent explicit trigger guidance, which per the judging guidelines caps completeness at 3.	3 / 5
Trigger Term Quality	Terms like 'memory system', 'knowledge management', and 'Architecture, Patterns, Decisions' are relevant, but the natural phrases a user would actually say ('remember this', 'recall a decision', 'long-term memory', 'save this pattern') are missing, matching the some-keywords-missing-variations anchor.	3 / 5
Distinctiveness Conflict Risk	The AI-agent memory niche with its three knowledge types is somewhat distinct, but 'memory system' and 'knowledge management' broadly overlap with many note-taking, memory, and documentation skills, so it could still trigger for the wrong skill.	3 / 5
	Total	12 / 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-claude/skills/agent-memory-mcp/SKILL.md
Commit: 64adc55

Reviewed: 17 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.