mem0-integrate

Integrate Mem0 into an existing repository using a goal-driven, TDD pipeline. Detects the repo's language automatically and asks the user to pick between Mem0 Platform (managed) and Mem0 Open Source (self-hosted). Writes failing tests before any implementation. Produces a local feature branch plus `.mem0-integration/` artifacts consumed by the paired verification skill. TRIGGER when: user says "integrate mem0", "add mem0 to this repo", "wire mem0 into <repo>", or asks how to add memory to an existing project. DO NOT TRIGGER when: the user wants general SDK usage (use skill:mem0), CLI usage (use skill:mem0-cli), or Vercel AI SDK (use skill:mem0-vercel-ai-sdk). After success, invoke skill:mem0-test-integration to verify in the same workspace (loose coupling).

Quality

92%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

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 thorough, highly actionable integration skill with an explicitly gated multi-step workflow and strong validation feedback loops. Its main weakness is conciseness (restated rationale and inline templates) and the absence of bundle files to offload the long templates, so the body reads as a monolithic wall rather than a navigable overview.

Suggestions

Move the large goal.md/plan.md templates and the verbatim subagent system prompts into files under references/ and link to them, reducing the body and improving progressive_disclosure.

Trim inferable justifications (e.g., 'Protects the user's work — ...', repeated additive/gating rationale) since Claude understands these once stated in 'Integration principles'.

Consolidate the principle restatements across Preconditions, Integration principles, and the step-8/step-10 system prompts to a single canonical list the subagent prompts reference.

Dimension	Reasoning	Score
Conciseness	Mostly efficient and well-organized, but it spends tokens on rationale and justification Claude can infer (e.g., 'Protects the user's work — every edit lands on a feature branch', repeated restatements of the additive/gating principles across Preconditions, Integration principles, and the verbatim subagent constraints) that could be tightened.	2 / 3
Actionability	Provides concrete, executable guidance throughout: a language-detection table, framework defaults, file-by-file templates for goal.md/plan.md, exact exit codes, and verbatim subagent system prompts — copy-paste ready rather than abstract.	3 / 3
Workflow Clarity	The 10-step pipeline is clearly sequenced with hard gates (goal approval, plan approval), explicit validation checkpoints ('They must fail. If they pass before any implementation, the tests are wrong'), exit codes for each failure mode, and a bounded self-healing feedback loop with revert-on-regression.	3 / 3
Progressive Disclosure	Content is well sectioned and the delegate-don't-reimplement rule plus URL list push depth elsewhere, but the body itself is a ~600-line monolith with no SKILL.md-local bundle files (references/scripts/assets absent) and detailed inline templates that could live in separate referenced files, leaving organization short of the clean one-level-deep anchor.	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 actions, explicit positive and negative triggers, and clear routing to sibling skills. It covers what, when, and how it stays distinct without padding.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions: 'Detects the repo's language', 'asks the user to pick between Mem0 Platform and Mem0 Open Source', 'Writes failing tests before any implementation', 'Produces a local feature branch plus .mem0-integration/ artifacts' — matching the 'multiple specific concrete actions' anchor.	3 / 3
Completeness	Answers both 'what' (the TDD integration pipeline and its outputs) and explicit 'when' guidance via the 'TRIGGER when:' / 'DO NOT TRIGGER when:' clauses, satisfying the explicit-triggers anchor.	3 / 3
Trigger Term Quality	Includes natural phrasings users would actually say — 'integrate mem0', 'add mem0 to this repo', 'wire mem0 into <repo>' — plus negative triggers routing to sibling skills, giving strong natural-keyword coverage.	3 / 3
Distinctiveness Conflict Risk	Scoped to a clear niche (Mem0 integration into an existing repo via TDD) with explicit 'DO NOT TRIGGER' routing to sibling skills (mem0, mem0-cli, mem0-vercel-ai-sdk) and handoff to a paired verification skill, making conflicts unlikely.	3 / 3
	Total	12 / 12 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (621 lines); consider splitting into references/ and linking	Warning

	Total	15 / 16 Passed

Repository: mem0ai/mem0
Path: skills/mem0-integrate/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.