agent-memory-mcp

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

Quality

—

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Advisory

Suggest reviewing before use

Quality

Content

72%

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

The body is highly actionable with concrete commands and tool examples and is cleanly organized, but it loses points on workflow validation gaps and vague boilerplate filler in the closing sections.

Suggestions

Remove or replace the generic 'When to Use' and 'Limitations' boilerplate with specific guidance tied to this skill's actual scope and failure modes.

Add explicit validation checkpoints to the setup workflow, such as 'Confirm the MCP server is running' after start-server and a fallback if npm run compile fails.

Specify what a successful start-server looks like (e.g., expected console output or a health-check command) so Claude can verify the server launched.

Dimension	Reasoning	Score
Conciseness	The setup and capabilities sections are lean and assume Claude's competence, but the trailing 'When to Use' ('applicable to execute the workflow or actions described in the overview') and boilerplate 'Limitations' sections are vague filler that do not earn their tokens.	2 / 3
Actionability	The body provides concrete, copy-paste-ready commands (git clone, npm install, npm run compile, npm run start-server my-project $(pwd)) and executable MCP tool-call examples with real argument values, matching the fully-executable anchor.	3 / 3
Workflow Clarity	Setup is clearly numbered (clone, install, start server) but there are no validation checkpoints or error-recovery feedback (e.g., confirming the server started or handling a failed compile), so checkpoints are missing rather than explicit.	2 / 3
Progressive Disclosure	It is a well-organized single-file overview with clear section headers and only a one-level external reference (the git clone), with no nested references; per the rubric, skills with no external reference files can score 3 via well-organized sections.	3 / 3
	Total	10 / 12 Passed

Description

50%

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 conveys a clear domain and category structure but relies on abstract language and lacks an explicit 'when to use' trigger, leaving every dimension at the mid-level anchor.

Suggestions

Rewrite the description to lead with concrete actions (e.g., 'Store, search, and retrieve long-term memories and decisions for AI agents').

Add an explicit trigger clause such as 'Use when the user asks to remember, recall, or persist project knowledge, architecture decisions, or patterns across sessions'.

Include natural trigger terms users would actually say (remember, recall, save decisions, long-term memory) instead of technical phrasing like 'hybrid memory system'.

Dimension	Reasoning	Score
Specificity	The description names the domain and categories ('persistent, searchable knowledge management for AI agents (Architecture, Patterns, Decisions)') but uses abstract framing ('provides... knowledge management') rather than listing concrete actions such as read/write/search, so it stops short of multiple specific concrete actions.	2 / 3
Completeness	It clearly states what the skill does but provides no 'Use when...' clause or equivalent trigger guidance, which per the rubric caps completeness at 2.	2 / 3
Trigger Term Quality	It contains some relevant keywords ('memory', 'knowledge', 'Architecture, Patterns, Decisions') but leans on technical phrasing ('hybrid memory system', 'knowledge management') and omits natural user variations like 'remember', 'recall', or 'save decisions'.	2 / 3
Distinctiveness Conflict Risk	The agent-memory niche is somewhat specific, but the abstract framing and lack of an explicit trigger boundary mean it could still overlap with general note-taking or knowledge-base skills.	2 / 3
	Total	8 / 12 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: boisenoise/skills-collections
Commit: f36337d

Reviewed: 2 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.