agent-memory-mcp
A hybrid memory system that provides persistent, searchable knowledge management for AI agents (Architecture, Patterns, Decisions).
57
Does it follow best practices?
If you maintain this skill, you can automatically optimize it using the tessl CLI to improve its score:
npx tessl skill review --optimize ./path/to/skillValidation for skill structure
Discovery
17%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 identifies the skill's domain (memory/knowledge management) but fails to provide actionable guidance for skill selection. It lacks concrete actions Claude would perform, natural user-facing trigger terms, and explicit 'Use when...' guidance. The technical framing ('hybrid memory system for AI agents') describes architecture rather than user-facing functionality.
Suggestions
Add a 'Use when...' clause with explicit triggers like 'Use when the user wants to save information for later, recall previous decisions, or search stored knowledge'
Replace technical jargon with natural trigger terms users would say: 'remember this', 'what did we decide about', 'store', 'recall', 'look up previous'
List specific concrete actions: 'Stores architectural decisions, retrieves past patterns, searches saved knowledge, tracks project context across sessions'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain ('hybrid memory system', 'knowledge management') and mentions some capabilities ('persistent, searchable'), but lacks concrete actions. The parenthetical '(Architecture, Patterns, Decisions)' hints at content types but doesn't describe what actions Claude performs. | 2 / 3 |
Completeness | Describes what it is (a memory system) but completely lacks a 'Use when...' clause or any explicit trigger guidance. Users have no indication of when Claude should select this skill. | 1 / 3 |
Trigger Term Quality | Uses technical jargon ('hybrid memory system', 'AI agents') that users wouldn't naturally say. Missing natural trigger terms like 'remember', 'store', 'recall', 'notes', 'save for later', or 'look up'. | 1 / 3 |
Distinctiveness Conflict Risk | 'Knowledge management' and 'memory system' are somewhat specific to this domain, but could overlap with note-taking, documentation, or database skills. The parenthetical categories help narrow scope but aren't definitive. | 2 / 3 |
Total | 6 / 12 Passed |
Implementation
79%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a well-structured, concise skill that provides actionable setup instructions and clear tool documentation. The main weaknesses are the lack of validation steps in the setup workflow (e.g., how to verify the server is running) and the inline documentation that could be split for better progressive disclosure.
Suggestions
Add a validation step after 'Start the MCP Server' to verify successful startup (e.g., expected output, health check command, or how to confirm connection)
Consider moving detailed MCP tool documentation to a separate REFERENCE.md and keeping only quick-reference summaries in the main skill file
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is lean and efficient, providing only necessary setup steps and tool documentation without explaining concepts Claude already knows. No padding or unnecessary context. | 3 / 3 |
Actionability | Provides fully executable bash commands for setup, concrete MCP tool signatures with args, and clear usage examples showing input-to-tool mapping. Copy-paste ready. | 3 / 3 |
Workflow Clarity | Setup steps are clearly sequenced (clone, install, start), but lacks validation checkpoints. No verification that the MCP server started successfully or troubleshooting guidance if it fails. | 2 / 3 |
Progressive Disclosure | Content is well-organized with clear sections, but the capabilities section is fairly detailed inline. Could benefit from linking to a separate REFERENCE.md for full API documentation or advanced usage patterns. | 2 / 3 |
Total | 10 / 12 Passed |
Validation
90%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 | |
- Reviewed
Table of Contents
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.