CtrlK
BlogDocsLog inGet started
Tessl Logo

mem0

Mem0 Platform SDK for adding persistent memory to AI applications. TRIGGER when: user mentions "mem0", "MemoryClient", "memory layer", "remember user preferences", "persistent context", "personalization", or needs to add long-term memory to chatbots, agents, or AI apps. Covers Python SDK (mem0ai), TypeScript SDK (mem0ai), and framework integrations (LangChain, CrewAI, OpenAI Agents SDK, Pipecat, LlamaIndex, AutoGen, LangGraph). Also covers the open-source self-hosted Memory class. This is the DEFAULT mem0 skill for ambiguous queries. DO NOT TRIGGER when: user asks about CLI commands, terminal usage, or shell scripts (use mem0-cli), or Vercel AI SDK / @mem0/vercel-ai-provider / createMem0 (use mem0-vercel-ai-sdk).

71

Quality

88%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

High

Do not use without reviewing

SKILL.md
Quality
Evals
Security

Quality

Content

76%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 highly actionable and well-structured with copy-paste code and on-demand reference tables, but workflow clarity is capped by missing validation around destructive delete operations, and three client/ links point to files that do not exist in the bundle.

Suggestions

Add a validation/confirmation checkpoint before batch or destructive calls (e.g., verify the memory UUID and user_id before client.delete_all), so workflow_clarity can exceed 3.

Fix the Client SDK References table: the client/ directory does not exist in the bundle — either create client/python.md, client/node.md, and client/differences.md, or point those rows at real files under references/.

Trim the lightly-padded intro line and the Skill Graph blockquote to push conciseness toward 5.

DimensionReasoningScore

Conciseness

Mostly lean and efficient with copy-paste-ready code and little padding, but a few editorial lines (the managed-memory intro and the Skill Graph blockquote) could be trimmed; not perfectly lean.

4 / 5

Actionability

Fully executable, copy-paste-ready code covering add/search/get_all/update/delete plus a complete retrieve-generate-store integration pattern, with specific filters and commands covering the common cases.

5 / 5

Workflow Clarity

Steps are clearly sequenced (install → init → core ops) with error-recovery guidance in edge cases, but destructive/batch operations (delete, delete_all) lack explicit validation or confirmation checkpoints, which caps this dimension at 3.

3 / 5

Progressive Disclosure

Clear overview with well-signaled one-level-deep reference tables and all referenced references/*.md files present, but the Client SDK References table links to a non-existent client/ directory (python.md, node.md, differences.md), a navigation gap.

4 / 5

Total

16

/

20

Passed

Description

100%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.

The description is exemplary: it states concrete capabilities, provides comprehensive natural trigger terms, explicitly answers both what and when, and clearly disambiguates from sibling skills with DO NOT TRIGGER boundary guidance. No meaningful weaknesses to address.

DimensionReasoningScore

Specificity

Names the domain and lists multiple specific concrete actions and comprehensive coverage (Python/TypeScript SDKs, framework integrations, OSS Memory class), matching the comprehensive-coverage anchor.

5 / 5

Completeness

Explicitly answers both 'what' (Platform SDK for persistent memory) and 'when' via a 'TRIGGER when' clause with concrete phrases, plus a 'DO NOT TRIGGER' exclusion — exactly the score-5 anchor.

5 / 5

Trigger Term Quality

Comprehensive natural terms including the product name, class name 'MemoryClient', and phrases users actually say ('remember user preferences', 'persistent context', 'personalization'), with synonyms well covered.

5 / 5

Distinctiveness Conflict Risk

Clear niche with explicit 'DEFAULT mem0 skill for ambiguous queries' disambiguation and boundary guidance steering CLI/Vercel cases to sibling skills, giving minimal conflict risk.

5 / 5

Total

20

/

20

Passed

Validation

93%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

relative_links

Relative link issues: 3 missing, 4 suspicious

Warning

Total

15

/

16

Passed

Repository
mem0ai/mem0
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.