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

96%

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

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 a well-structured, lean skill that routes detailed mechanics to two one-level-deep reference files, sequences a 10-step pipeline with explicit gates and exit codes, and builds in validation plus a bounded self-healing loop. Its only soft spot is that the executable call-site code is delegated to published skills rather than shown inline, which is a deliberate design choice.

Suggestions

Inline one minimal Platform write/read code snippet (or a concrete test assertion shape) so the skill is fully copy-paste executable even if the delegated skill URL is unreachable.

Move the four-step commit sequence (dependency, module, wiring, tests) from prose into a short checklist with example commit messages to make step 9 more directly actionable.

Add a one-line 'expected output' per pipeline step in the summary table so a reader can self-verify a step completed without opening pipeline.md.

Dimension	Reasoning	Score
Conciseness	Lean and efficient throughout: it assumes Claude's competence, avoids explaining concepts Claude already knows, and every section (principles, delegation table, pipeline table, artifacts, exit codes) earns its place. The few parenthetical rationales on preconditions are load-bearing rather than padding.	5 / 5
Actionability	Provides concrete executable guidance — exact flags (`--no-heal`, `--heal-max 5`, `--product oss`, `--ci`), exact env vars, the `product.json` schema, branch naming `mem0-integrate/<slug>`, and the four-commit sequence. The actual write/read call-site code lives in delegated published skills (explicitly justified), which is a minor coverage gap rather than pseudocode.	4 / 5
Workflow Clarity	The 10-step pipeline table sequences every step with an explicit per-step gate, marks hard gates, defines exit codes for each failure mode, and includes a self-healing loop with revert-on-regression and a 'never fix a pre-existing test failure' rule — full validation checkpoints and feedback loops for a destructive/batch operation.	5 / 5
Progressive Disclosure	SKILL.md acts as a clear overview/router, with full mechanics in `references/pipeline.md` and verbatim subagent prompts in `references/subagent-prompts.md` — both real files, one level deep, clearly signaled with markdown links and explicit 'read this when executing a step' guidance.	5 / 5
	Total	19 / 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 specific, complete, and distinct: it states concrete actions, gives natural trigger phrases, answers both 'what' and 'when', and disambiguates from related skills. It is concise for its information density and uses third-person voice throughout.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'Detects the repo's language automatically', 'asks the user to pick between Mem0 Platform ... and Mem0 Open Source', 'Writes failing tests before any implementation', and 'Produces a local feature branch plus `.mem0-integration/` artifacts' — giving comprehensive coverage.	5 / 5
Completeness	Explicitly answers both 'what' (the TDD pipeline actions and artifacts) and 'when' ('TRIGGER when: ...') with concrete trigger phrases, matching the anchor for clearly answering both.	5 / 5
Trigger Term Quality	Provides comprehensive natural trigger phrases users would actually say — 'integrate mem0', 'add mem0 to this repo', 'wire mem0 into <repo>', and 'add memory to an existing project' — plus explicit 'DO NOT TRIGGER' routing.	5 / 5
Distinctiveness Conflict Risk	Occupies a clear niche (integrating Mem0 into an existing repo via TDD) and explicitly routes away from sibling skills (mem0, mem0-cli, mem0-vercel-ai-sdk) via the 'DO NOT TRIGGER' clause, minimizing conflict risk.	5 / 5
	Total	20 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: mem0ai/mem0
Path: skills/mem0-integrate/SKILL.md
Commit: 39bc023

Reviewed: 3 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.