Validation
69%| Criteria | Description | Result |
|---|---|---|
skill_md_line_count | SKILL.md line count is 83 (<= 500) | Pass |
frontmatter_valid | YAML frontmatter is valid | Pass |
name_field | 'name' field is valid: 'agent-memory-mcp' | Pass |
description_field | 'description' field is valid (131 chars) | Pass |
description_voice | 'description' uses third person voice | Pass |
description_trigger_hint | Description may be missing an explicit 'when to use' trigger hint (e.g., 'Use when...') | Warning |
compatibility_field | 'compatibility' field not present (optional) | Pass |
allowed_tools_field | 'allowed-tools' field not present (optional) | Pass |
metadata_version | 'metadata' field is not a dictionary | Warning |
metadata_field | 'metadata' field not present (optional) | Pass |
license_field | 'license' field is missing | Warning |
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
body_present | SKILL.md body is present | Pass |
body_examples | Examples detected (code fence or 'Example' wording) | Pass |
body_output_format | No obvious output/return/format terms detected; consider specifying expected outputs | Warning |
body_steps | Step-by-step structure detected (ordered list) | Pass |
Total | 11 / 16 Passed |
Implementation
80%This is a well-structured skill with excellent conciseness and actionability - commands are copy-paste ready and tool usage examples are concrete. The main weaknesses are missing validation steps in the setup workflow (how to verify the server started correctly) and the dashboard section lacks integration guidance with the main workflow.
Suggestions
- Add a validation step after server start, e.g., 'Verify server is running: check for "MCP server listening" message or test with memory_stats({})'
- Add brief troubleshooting guidance for common setup failures (port conflicts, missing dependencies)
- Clarify when to use the dashboard vs MCP tools directly, or move dashboard docs to a separate file
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is lean and efficient, avoiding unnecessary explanations. It assumes Claude knows what MCP servers, Node.js, and git are without explaining these concepts. | 3 / 3 |
Actionability | Provides fully executable commands for setup (git clone, npm install, npm run) and concrete examples for each MCP tool with specific argument structures and usage patterns. | 3 / 3 |
Workflow Clarity | Setup steps are clearly sequenced (1-3), but there's no validation checkpoint after installation or server start. No guidance on verifying the server is running correctly or troubleshooting if it fails. | 2 / 3 |
Progressive Disclosure | Content is reasonably organized with clear sections, but the MCP tools documentation could be split to a separate REFERENCE.md. The dashboard section feels tacked on without context on when/why to use it. | 2 / 3 |
Total | 10 / 12 Passed |
Activation
17%The description uses abstract, technical language that describes a concept rather than concrete capabilities. It lacks natural trigger terms users would say and provides no guidance on when Claude should select this skill. The parenthetical content types hint at structure but don't clarify actionable use cases.
Suggestions
- Add a 'Use when...' clause with natural trigger terms like 'remember this', 'store for later', 'what did we decide about', 'look up previous decisions'
- Replace abstract language with concrete actions: 'Store and retrieve architectural decisions, design patterns, and project knowledge' instead of 'provides persistent, searchable knowledge management'
- Include file types or specific scenarios: 'Use when documenting technical decisions, recording learned patterns, or recalling previous project context'
| 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 can be performed. | 2 / 3 |
Completeness | Partially addresses 'what' (knowledge management) but completely missing 'when' guidance. No 'Use when...' clause or equivalent trigger guidance exists. | 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 information', or 'look up'. | 1 / 3 |
Distinctiveness Conflict Risk | The 'hybrid memory system' and 'AI agents' framing provides some distinctiveness, but 'knowledge management' is generic and could overlap with note-taking, documentation, or other storage-related skills. | 2 / 3 |
Total | 6 / 12 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.