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.

Quality

82%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

82%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.

A clear, actionable skill body with executable MCP examples and a well-sequenced filter-first workflow. Minor conciseness redundancy and the absence of any external reference files keep it just short of top marks on progressive disclosure.

Suggestions

Collapse the 'Why This Workflow?' section or merge it into the intro, since its token figures duplicate values already stated inline in Steps 1 and 3.

Consider moving the per-tool parameter tables to a references/ file (e.g. TOOLS.md) and keeping SKILL.md as a concise workflow overview with one-level-deep links.

Add a short explicit verification note in Step 3 (e.g. confirm fetched observations match the targeted IDs before relying on them) to strengthen the workflow checkpoint.

Dimension	Reasoning	Score
Conciseness	Lean and well-structured, assuming Claude's competence (no preamble about what memory is); the 'Why This Workflow?' section partially restates token figures already given inline, so it is efficient with minor trim opportunities rather than maximally lean.	4 / 5
Actionability	Provides fully executable, copy-paste MCP calls (search/timeline/get_observations) with all parameters plus a Examples section covering common cases (bug fixes, last week, batch fetch).	5 / 5
Workflow Clarity	Clear 3-step Search -> Timeline -> Fetch sequence with an explicit filter-first checkpoint ('Review titles... Pick relevant IDs. Discard the rest'); read-only so the destructive/batch validation cap does not force a 3, but it lacks the feedback-loop/checklist elements of the top anchor.	4 / 5
Progressive Disclosure	Single self-contained file with well-organized sections and a clearly signaled one-level pointer (/knowledge-agent); no bundle files exist. It is well structured but bulkier (~130 lines with full parameter tables for three tools inline) than the ideal overview-pointing-to-details model, so it sits just below the top anchor.	4 / 5
	Total	17 / 20 Passed

Description

82%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.

A strong, well-constructed description that clearly states what the skill does and when to use it with natural trigger phrases and a distinct niche. The only gap is limited action breadth (just 'Search'), which keeps specificity at the midpoint.

Dimension	Reasoning	Score
Specificity	Names the domain ('claude-mem's persistent cross-session memory database') and one concrete action ('Search'), matching the anchor for 1-2 concrete actions without comprehensive coverage; not a 4 because only a single action is listed.	3 / 5
Completeness	Explicitly answers both what ('Search claude-mem's persistent cross-session memory database') and when ('Use when user asks...') with concrete trigger phrases, matching the top anchor exactly.	5 / 5
Trigger Term Quality	Includes three natural quoted user phrases ('did we already solve this?', 'how did we do X last time?', 'needs work from previous sessions') that users would actually say, giving good coverage; not a 5 because it lacks the broader synonym/variant density of the top anchor.	4 / 5
Distinctiveness Conflict Risk	Targets a clear niche (claude-mem's cross-session memory) with distinct previous-session triggers, giving minimal overlap risk with other skills.	5 / 5
	Total	17 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: thedotmack/claude-mem
Path: plugin/skills/mem-search/SKILL.md
Commit: fae697a

Reviewed: 3 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.