CtrlK
BlogDocsLog inGet started
Tessl Logo

mem0-vercel-ai-sdk

Mem0 provider for Vercel AI SDK (@mem0/vercel-ai-provider). TRIGGER when: user mentions "vercel ai sdk", "@mem0/vercel-ai-provider", "createMem0", "retrieveMemories", "addMemories", "getMemories", "searchMemories", "mem0 vercel", "AI SDK provider", "AI SDK memory", or is using generateText/streamText with mem0. Also triggers for Next.js apps needing memory-augmented AI. DO NOT TRIGGER when: user asks about direct Python/TS SDK calls without Vercel (use mem0 skill), or CLI terminal commands (use mem0-cli skill).

74

Quality

92%

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

85%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 highly actionable, well-structured body with executable code, clear setup sequencing, and proper progressive disclosure to verified reference files. The main weakness is conciseness: the wrapped-model flow and the fire-and-forget behavior are each repeated multiple times across sections.

Suggestions

Remove or merge the 'How It Works Internally > Wrapped model flow' diagram, which restates the same four-step sequence already given in Pattern 1's 'What happens under the hood' list — keep one presentation to tighten the body.

State the fire-and-forget behavior of addMemories once (in 'Common Edge Cases and Tips') and reference it from Pattern 1 and the internal-flow section rather than repeating it in three places.

Collapse the 'What happens under the hood' inline list into the pattern's code comment or move it into references/usage-patterns.md so Pattern 1 leads with the executable example and defers the mechanism to the deeper file.

DimensionReasoningScore

Conciseness

Mostly lean and free of basic-concept padding, but the wrapped-model flow is explained twice (Pattern 1's 'What happens under the hood' list and the 'How It Works Internally' diagram) and the fire-and-forget behavior is repeated three times — content that could be tightened.

2 / 3

Actionability

Fully executable, copy-paste-ready TypeScript across three patterns plus install/env commands, a supported-providers table with config values and env vars, and concrete gotchas (gemini alias, v5-only, host override).

3 / 3

Workflow Clarity

Setup is clearly sequenced (Step 1 install, Step 2 env vars, then patterns) and each pattern's internal flow is explicit; no destructive or batch operations require validation feedback loops, so the simple-skill note applies.

3 / 3

Progressive Disclosure

SKILL.md is a concise overview with a well-signaled References table pointing to three one-level-deep local files (verified to exist and not to nest further) plus related-skills navigation — content appropriately split.

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.

An excellent description: it states what the skill does, provides explicit positive and negative triggers using natural terms and API names, and cleanly distinguishes itself from sibling mem0 skills. It is concise, uses third-person voice, and contains no fluff.

DimensionReasoningScore

Specificity

Names the concrete domain ('Mem0 provider for Vercel AI SDK (@mem0/vercel-ai-provider)') and lists multiple specific capabilities via function names (createMem0, retrieveMemories, addMemories, getMemories, searchMemories) and use cases (generateText/streamText with mem0, Next.js memory-augmented AI); uses third-person voice so no penalty applies.

3 / 3

Completeness

Clearly answers both what (Mem0 provider for Vercel AI SDK, memory-augmented AI) and when, with explicit 'TRIGGER when' and 'DO NOT TRIGGER when' clauses that go beyond implied usage.

3 / 3

Trigger Term Quality

Good coverage of natural terms users would say ('vercel ai sdk', 'mem0 vercel', 'AI SDK provider', 'AI SDK memory') alongside specific API names, with both positive and negative triggers.

3 / 3

Distinctiveness Conflict Risk

Clear niche (Vercel AI SDK specifically) with explicit negative triggers routing to sibling mem0 and mem0-cli skills, making it unlikely to trigger for 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: 2 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.