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).

72

Quality

90%

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

80%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 well-structured, highly actionable SKILL body with lean code-dense content and good reference organization. It loses points on workflow_clarity (no verification step before destructive delete/delete_all) and progressive_disclosure (three referenced client/*.md files are missing from the bundle).

Suggestions

Add a verification/confirmation step before destructive calls — e.g. recommend calling client.get_all() or confirming the memory UUID before client.delete()/client.delete_all() — to lift workflow_clarity above 2.

Fix the dangling Client SDK References links: either add the missing client/python.md, client/node.md, and client/differences.md files to the bundle or remove/replace those table rows with existing references.

DimensionReasoningScore

Conciseness

The body is code-dense and lean — "Every Mem0 integration follows the same pattern: retrieve → generate → store." — with executable snippets and no padding explaining concepts Claude already knows; the edge-case and v2-compatibility sections earn their tokens with non-obvious detail.

3 / 3

Actionability

Provides fully executable, copy-paste-ready guidance throughout — `pip install mem0ai`, `from mem0 import MemoryClient`, `client.add(...)`/`search(...)`/`delete(...)`, a complete chat() integration with OpenAI, and a runnable doc-search script invocation.

3 / 3

Workflow Clarity

Steps are clearly sequenced (Step 1 install → Step 2 init → Step 3 ops) with a retrieve→generate→store pattern, but destructive/batch operations `client.delete("memory-uuid")` and `client.delete_all(user_id=...)` are shown with no verification or confirmation checkpoint, which caps workflow clarity at 2 per the destructive-operations guideline.

2 / 3

Progressive Disclosure

Structure is excellent — labeled reference tables, one-level-deep links, well-signaled navigation — but the three Client SDK References links (client/python.md, client/node.md, client/differences.md) do not exist in the bundle, so referenced paths are partially broken and navigation is not fully reliable.

2 / 3

Total

10

/

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 states concrete capabilities, supplies natural trigger terms, covers both what and when explicitly, and actively disambiguates from sibling mem0 skills. Voice is third person throughout, so no specificity penalty applies.

DimensionReasoningScore

Specificity

Lists multiple concrete capabilities — "adding persistent memory to AI applications", both Python/TypeScript SDKs, named framework integrations (LangChain, CrewAI, OpenAI Agents SDK, etc.), and the OSS Memory class — matching the 'lists multiple specific concrete actions' anchor.

3 / 3

Completeness

Explicitly answers what ("Mem0 Platform SDK for adding persistent memory") and when ("TRIGGER when: user mentions ...", plus a "DO NOT TRIGGER when" anti-trigger clause), satisfying the both-what-and-when-with-explicit-triggers anchor.

3 / 3

Trigger Term Quality

Includes natural phrasing a user would actually say — "mem0", "MemoryClient", "remember user preferences", "persistent context", "personalization", "add long-term memory to chatbots, agents, or AI apps" — giving good coverage of natural trigger terms.

3 / 3

Distinctiveness Conflict Risk

Declares "This is the DEFAULT mem0 skill for ambiguous queries" and routes conflicts away (CLI commands → mem0-cli, Vercel AI SDK → mem0-vercel-ai-sdk), giving a clear niche unlikely to trigger the wrong skill.

3 / 3

Total

12

/

12

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.