agent-memory-mcp

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

10.00x

Quality

62%

Does it follow best practices?

Impact

100%

10.00x

Average score across 3 eval scenarios

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./cli-tool/components/skills/ai-research/agent-memory-mcp/SKILL.md

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 concise, actionable, and well-structured with concrete commands and tool examples throughout. The main gap is the absence of a verification step after server start and missing MCP client wiring guidance.

Suggestions

Add a verification checkpoint after starting the server (e.g. 'Confirm the MCP server is reachable / listed by the client') to strengthen the workflow with a feedback loop.

Include the step for registering/connecting the running MCP server to the agent client, since the current actionability stops at launching the server.

Move the per-tool argument tables into a short reference section or a references file once the skill grows, keeping SKILL.md an overview.

Dimension	Reasoning	Score
Conciseness	The body is lean and assumes Claude's competence (no explanation of MCP, Node, or npm), with direct commands and Args/Usage blocks; the two-line intro slightly restates the description, a minor trim, matching anchor 4.	4 / 5
Actionability	Setup gives copy-paste-ready git/npm commands with a concrete example, and each MCP tool shows real call signatures like memory_search({ query, type }); the gap is no guidance for wiring the MCP server into a client, matching anchor 4.	4 / 5
Workflow Clarity	A clear numbered clone -> install -> start-server sequence with concrete commands is present; it lacks an explicit validation/verify checkpoint or error-recovery feedback loop, a minor gap matching anchor 4.	4 / 5
Progressive Disclosure	Sections (Prerequisites, Setup, Capabilities, Dashboard) are well organized and the skill is self-contained with no nested references; at ~80 lines with no bundle files it sits just above the simple-skill threshold, so anchor 4 rather than 5.	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 conveys what the skill is but omits any 'Use when' trigger guidance, capping completeness and trigger quality at the midpoint. It is clear and non-generic but would benefit from explicit activation phrases.

Suggestions

Add an explicit 'Use when...' clause naming concrete triggers, e.g. 'Use when the agent needs to persist, recall, or search project knowledge such as architecture decisions, patterns, or past decisions.'

Surface natural user phrases ('remember this', 'knowledge base', 'agent memory') alongside the technical terms to improve trigger term quality.

Lead with concrete verbs (store, retrieve, search, sync) instead of 'provides ... knowledge management' to lift specificity above anchor 3.

Dimension	Reasoning	Score
Specificity	Names the domain ('hybrid memory system', 'knowledge management') and two functional characteristics ('persistent, searchable'), but lacks explicit concrete verbs like store/retrieve/search; matches anchor 3 (domain + 1-2 actions, not comprehensive).	3 / 5
Completeness	Provides a clear 'what' (hybrid persistent searchable memory for AI agents) but no 'when'/'Use when' clause; per guideline a missing trigger clause caps completeness at 3, matching anchor 3.	3 / 5
Trigger Term Quality	Contains relevant keywords ('memory system', 'knowledge management', 'AI agents') but offers no trigger phrase and misses common user variations like 'remember this' or 'knowledge base'; matches anchor 3 (some relevant keywords, missing variations).	3 / 5
Distinctiveness Conflict Risk	The AI-agent memory niche is somewhat specific and lists content categories (Architecture, Patterns, Decisions), but with no distinct triggers it could still overlap with other memory/knowledge skills; matches anchor 3.	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: davila7/claude-code-templates
Path: cli-tool/components/skills/ai-research/agent-memory-mcp/SKILL.md
Commit: d4f034a

Reviewed: 5 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.