search

Searches memories and displays compact one-liner results, or looks up a specific memory by ID. Use for quick memory lookups, checking if something was recorded, resolving [mem0:id] citations, or browsing memories without full category detail.

Quality

93%

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

87%Weight 40%Scale 1-3

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A concise, actionable, well-organized single-purpose skill body with a clear three-step workflow and concrete tool invocation. The main weakness is the UUID memory-ID branch, which flags a direct lookup path but does not specify the actual tool call to perform it.

Suggestions

Specify the direct-lookup action for the UUID branch — e.g., note which mem0_memory action/parameters to use when the query is a memory ID, so the alternate path is as executable as the search path.

Add a one-line note on how the short_id in [mem0:<short_id>] is derived from the full memory ID, so the display format is reproducible end-to-end.

Clarify what "compact" truncation applies (the format says 80 chars) — confirm whether content is hard-truncated at 80 chars or summarized, to keep output deterministic.

Dimension	Reasoning	Score
Conciseness	The body is lean (~37 lines) with no exposition of concepts Claude already knows and no padding ("Quick semantic search with compact output. Lighter than /mem0-tour."); every token earns its place, matching the score-3 lean/efficient anchor rather than the score-2 'mostly efficient but could be tightened'.	3 / 3
Actionability	Concrete executable guidance is given: "Use mem0_memory tool with action=\"search\", query=<user's query>" plus an exact output format string and a worked example, which is copy-paste ready like the score-3 anchor; it is not score 2 because it provides real commands rather than pseudocode or abstract description.	3 / 3
Workflow Clarity	The Parse → Search → Display sequence is clearly numbered, but the UUID branch ("If the query matches a UUID pattern... treat it as a direct memory lookup instead of a search") never specifies the lookup tool call or action, leaving that path implicit; this matches the score-2 anchor of steps present but with a gap, not score 3 because the branch is not fully unambiguous.	2 / 3
Progressive Disclosure	Under 50 lines, single-purpose, with well-organized sections (## Execution, ### Step 1–3) and no external references needed; per the simple-skills scoring note this earns a 3 for clear organization rather than the score-2 'some structure' level.	3 / 3
	Total	11 / 12 Passed

Description

100%Weight 40%Scale 1-3

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, third-person description that pairs concrete actions with an explicit 'Use for...' trigger clause covering several natural phrasings. It clearly answers both what the skill does and when to use it with low conflict risk.

Dimension	Reasoning	Score
Specificity	"Searches memories and displays compact one-liner results, or looks up a specific memory by ID" lists multiple concrete actions (search, compact display, ID lookup), matching the score-3 anchor of several specific concrete actions; it is not the score-2 level because it goes beyond naming a domain plus a single action.	3 / 3
Completeness	It states what ("Searches memories and displays compact one-liner results, or looks up a specific memory by ID") and when ("Use for quick memory lookups, checking if something was recorded...") with an explicit trigger clause, matching the score-3 anchor; it is not score 2 because the when is explicit, not merely implied.	3 / 3
Trigger Term Quality	"Use for quick memory lookups, checking if something was recorded, resolving [mem0:id] citations, or browsing memories" gives good coverage of natural phrases a user would say; it is above score 2 because it supplies several common variations rather than a single keyword.	3 / 3
Distinctiveness Conflict Risk	"resolving [mem0:id] citations" and "browsing memories without full category detail" carve a clear niche unlikely to trigger the wrong skill; it is above score 2 because the triggers are distinct rather than a generic "works with memory files" phrasing.	3 / 3
	Total	12 / 12 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: mem0ai/mem0
Path: integrations/pi-agent-plugin/skills/search/SKILL.md
Commit: b357a5a

Reviewed: 6 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.