mem-search
Search claude-mem's persistent cross-session memory database. Use when user asks "did we already solve this?", "how did we do X last time?", or needs work from previous sessions.
68
83%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Passed
No known issues
Quality
Discovery
89%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is a solid description with excellent trigger terms and clear completeness. The 'Use when' clause with natural user phrases is particularly strong. The main weakness is that the 'what' portion could be more specific about the concrete actions beyond just 'search' — e.g., retrieving specific entries, listing past solutions, or summarizing previous work.
Suggestions
Expand the specificity of actions beyond just 'search' — e.g., 'Search and retrieve entries from claude-mem's persistent cross-session memory database, including past solutions, decisions, and context.'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (persistent cross-session memory database) and one action (search), but doesn't list multiple concrete actions like retrieving, filtering, or summarizing past session data. | 2 / 3 |
Completeness | Clearly answers both what (search claude-mem's persistent cross-session memory database) and when (explicit 'Use when' clause with specific trigger phrases and the general case of needing work from previous sessions). | 3 / 3 |
Trigger Term Quality | Includes excellent natural trigger phrases users would actually say: 'did we already solve this?', 'how did we do X last time?', 'previous sessions'. These are realistic user utterances that map well to the skill's purpose. | 3 / 3 |
Distinctiveness Conflict Risk | Very distinct niche — searching a specific memory database (claude-mem) for cross-session recall. The trigger phrases about previous sessions and past work are unlikely to conflict with other skills. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
77%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-crafted skill that provides clear, actionable guidance for a 3-step memory search workflow. Its strongest aspects are the concrete MCP tool call examples and the explicit workflow sequencing with token-saving rationale. Minor weaknesses include some redundant explanatory content and the lack of external references for parameter details or advanced usage.
Suggestions
Remove or condense the 'Why This Workflow?' section — the token savings rationale is already stated in the workflow header and Step 3 context.
Consider moving the full parameter lists to a separate REFERENCE.md to keep the main skill leaner and focused on the workflow.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Generally efficient but includes some unnecessary sections like 'Why This Workflow?' which explains token math Claude can infer, and the 'When to Use' examples are somewhat redundant. The parameter lists are useful but could be slightly tighter. | 2 / 3 |
Actionability | Provides fully concrete, copy-paste ready MCP tool calls with specific parameter names, types, and example return formats. Every step has executable examples with realistic data. | 3 / 3 |
Workflow Clarity | The 3-layer workflow (search → filter → fetch) is clearly sequenced with explicit rationale for not skipping steps. The bold 'NEVER fetch full details without filtering first' serves as a validation checkpoint, and the progression from index to timeline to full fetch is unambiguous. | 3 / 3 |
Progressive Disclosure | Content is well-structured with clear headers and logical sections, but everything is in a single file with no bundle files for advanced topics. The Knowledge Agents section at the end hints at deeper functionality but doesn't link to any reference material. For a skill of this length (~100 lines), this is acceptable but the parameter documentation could be split out. | 2 / 3 |
Total | 10 / 12 Passed |
Validation
100%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
- Repository
- thedotmack/claude-mem
- Commit
37d2494
- 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.