CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

search

Search memories from earlier Coding Agent sessions in this repository. Use it when earlier work may already explain the code, error, decision, or command you need, so you can avoid repeating file reads, searches, or experiments.

Quality

90%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

The canonical home for this skill is search in mem0ai/mem0

SKILL.md
Quality
Evals
Security

Quality

Content

92%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.

The body is an exemplar of a compact, single-purpose tool skill: exact invocation guidance, complete option semantics, and behavioral rules, with zero filler. Its only gap is the absence of a sample call that would make argument formatting fully copy-paste ready.

DimensionReasoningScore

Conciseness

The body is lean with no padding and no explanations of concepts Claude already knows; every detail is context-specific ("Mem0's configured default", "this repository's shared memory, which everyone who works in it contributes to", "Use a known session ID, never invent one"). Each token earns its place, matching the anchor-5 example's economy.

5 / 5

Actionability

Guidance is concrete and executable for an instruction-only skill: exact tool name (`search_memories`), all four arguments (`top_k`, `category`, `scope`, `run_id`) with values (`dir`, `mine`) and defaults. It stops short of anchor 5 only because there is no worked example invocation and the argument naming shifts between `--top-k` flag form and `top_k` tool-argument form without explicitly reconciling them.

4 / 5

Workflow Clarity

This is a simple single-task skill and the single action is unambiguous: "Call `search_memories` with the user's question", with a defined terminal behavior ("Return the tool's result directly") and explicit default-handling for each argument. The simple-skill exception applies; the operation is read-only, so no validation cap is triggered.

5 / 5

Progressive Disclosure

The body is under 50 lines, needs no external references, and references none (the bundle contains no references/, scripts/, or assets/ files); all content is appropriately inline and organized into tight paragraphs under a single heading. The under-50-line simple-skill guidance allows a 5 with just well-organized content.

5 / 5

Total

19

/

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 description: it states a concrete single capability, includes an explicit and situation-specific "Use it when..." clause, and occupies a distinct niche. The only soft spots are modest keyword synonym coverage and the natural limit of a single-action skill on enumerated actions.

DimensionReasoningScore

Specificity

"Search memories from earlier Coding Agent sessions in this repository" names a concrete action on a well-defined object, matching the "names domain and 1-2 concrete actions" anchor. It is a single-action skill, so it does not list "several specific actions" (anchor 4), but its one action is concrete rather than generic (above anchor 2).

3 / 5

Completeness

It explicitly answers both questions: the what ("Search memories from earlier Coding Agent sessions in this repository") and an explicit "Use it when earlier work may already explain the code, error, decision, or command you need" trigger clause. The when-clause is explicit and specific with concrete trigger situations, matching anchor 5 rather than the less-specific anchor 4.

5 / 5

Trigger Term Quality

The when-clause surfaces natural terms users would say — "earlier work", "code", "error", "decision", "command", "file reads, searches, or experiments" — giving good keyword coverage. It falls short of anchor 5 because common variations like "previous session", "last time", "remember", or "history" are missing, but it is clearly above the sparse keyword coverage of anchor 3.

4 / 5

Distinctiveness Conflict Risk

"Search memories from earlier Coding Agent sessions in this repository" carves out a clear niche with distinct triggers tied to prior work in the repo, so conflict risk with other skills is minimal. Nothing suggests even minor overlap with a closely related skill, keeping it at anchor 5 rather than anchor 4.

5 / 5

Total

17

/

20

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository

mem0ai/mem0

Path

integrations/mem0-agent-plugin/skills/search/SKILL.md

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.