agent-memory-mcp
A hybrid memory system that provides persistent, searchable knowledge management for AI agents (Architecture, Patterns, Decisions).
41
41%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Advisory
Suggest reviewing before use
Optimize this skill with Tessl
npx tessl skill review --optimize ./skills/antigravity-agent-memory-mcp/SKILL.mdQuality
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 reads more like a product tagline than an actionable skill description. It lacks concrete actions, natural trigger terms, and any 'Use when...' guidance, making it difficult for Claude to know when to select this skill over others. The parenthetical categories hint at scope but don't compensate for the missing specificity and trigger information.
Suggestions
Add an explicit 'Use when...' clause, e.g., 'Use when the user asks to remember a decision, record an architectural pattern, or retrieve previously stored project knowledge.'
Replace abstract language with concrete actions: e.g., 'Stores and retrieves architecture decisions, design patterns, and project context. Searches past entries by keyword or topic.'
Include natural trigger terms users would say, such as 'remember this', 'what did we decide', 'save this pattern', 'project memory', 'look up', 'recall'.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain ('memory system', 'knowledge management') and hints at what it covers ('Architecture, Patterns, Decisions'), but doesn't list concrete actions like 'store decisions', 'search patterns', or 'retrieve architecture notes'. | 2 / 3 |
Completeness | Provides a partial 'what' (knowledge management for AI agents) but completely lacks a 'when' clause or any explicit trigger guidance for when Claude should select this skill. | 1 / 3 |
Trigger Term Quality | Uses technical/abstract terms like 'hybrid memory system', 'persistent, searchable knowledge management', and 'AI agents' which are not natural phrases a user would say. Missing everyday trigger terms like 'remember', 'save note', 'look up decision', 'project context'. | 1 / 3 |
Distinctiveness Conflict Risk | The parenthetical '(Architecture, Patterns, Decisions)' adds some specificity, but 'knowledge management' and 'memory system' are broad enough to overlap with note-taking, documentation, or other context-management skills. | 2 / 3 |
Total | 6 / 12 Passed |
Implementation
64%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
The skill provides solid, actionable setup instructions and clear MCP tool documentation with concrete examples. Its main weaknesses are generic boilerplate sections ('When to Use', 'Limitations') that waste tokens without adding value, and the lack of validation/verification steps in the setup workflow (e.g., confirming the server is running, handling common errors).
Suggestions
Remove or replace the generic 'When to Use' and 'Limitations' sections with project-specific guidance (e.g., when to use memory_write vs memory_search, memory size limits, supported content types).
Add a validation step after 'Start the MCP Server' such as checking server output or running memory_stats to confirm the server is operational.
Add brief error recovery guidance for common setup failures (e.g., port conflicts, missing Node.js version).
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is mostly efficient but includes some unnecessary filler. The 'When to Use' and 'Limitations' sections are generic boilerplate that add no real value. The MCP tool descriptions are reasonably lean but could be tighter. | 2 / 3 |
Actionability | Setup steps include concrete, copy-paste-ready bash commands. MCP tool documentation provides specific argument signatures and usage examples with realistic invocations. The dashboard startup command is also concrete. | 3 / 3 |
Workflow Clarity | The setup workflow is clearly sequenced (clone → install → start), but there are no validation checkpoints—no way to verify the server started correctly, no error recovery guidance, and no verification step after installation. For a server-based tool, missing health checks or confirmation steps is a gap. | 2 / 3 |
Progressive Disclosure | The content is reasonably organized with clear sections, but everything is inline in a single file with no references to external documentation. Given no bundle files are provided, there's no deeper reference structure. The tool reference section could potentially be split out for a cleaner overview, but for this size it's acceptable. | 2 / 3 |
Total | 9 / 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 | |
- Repository
- boisenoise/skills-collections
- Commit
e41e34a
- 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.