onboard

Sets up mem0 for a new project including API key configuration, MCP authentication, project file import, and coding categories. Use on first run in a new project, when API key needs updating, or to re-run initial setup after configuration changes.

Quality

88%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

88%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.

A tightly written, highly actionable onboarding wizard with strong sequencing and explicit validation/feedback loops. Its only real weakness is that all content lives in one inline file with no progressive reference structure, though little of it would clearly benefit from being split out.

Suggestions

Move the long Step 1 API-key setup message template into a short reference file (e.g. references/api-key-setup.md) and link to it, improving both conciseness and progressive_disclosure.

Trim reassurance asides like "This is silent and idempotent — safe to run anytime." to nudge conciseness toward a 5.

Make Step 3's <active_user_id>/<active_project_id> placeholders resolvable by adding a one-line hint on how Claude obtains them, closing the minor actionability gap.

Dimension	Reasoning	Score
Conciseness	The body is largely procedural and assumes Claude's competence (no explaining of what mem0 or an API key is), with executable commands doing most of the talking. Minor reassurance padding ("This is silent and idempotent — safe to run anytime.") and a long inline API-key message keep it just below a 5.	4 / 5
Actionability	Fully executable, copy-paste-ready bash throughout (the SET/NOT_SET check, the project-file detection loop, the venv-gated python invocations, ToolSearch queries) plus concrete user-facing message templates. Specific examples cover the common cases; placeholders like <active_user_id> are appropriate for a wizard.	5 / 5
Workflow Clarity	Steps 0-6 are strictly ordered with explicit validation (SET/NOT_SET verify, MCP tool probe, search_memories connectivity check), feedback loops (repeat if NOT_SET, retry via ensure_deps.sh), and hard "STOP here" checkpoints. Anchor 5 (clear sequence, explicit validation, error-recovery loops) is the best fit; the batch import/category operations include verification so the destructive-batch cap does not apply.	5 / 5
Progressive Disclosure	Well-organized into clearly headed Steps 0-6 with no nested references and easy navigation, and no external doc files are needed so none are missing. Not a 5 because the skill is a ~180-line monolith with everything inline and no reference split, whereas the 5 anchor calls for well-signaled one-level-deep references or a genuinely simple short skill.	4 / 5
	Total	18 / 20 Passed

Description

87%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.

A strong description that explicitly states both the capability set and concrete usage triggers in third-person voice. It is specific, distinct, and free of fluff or over-claims.

Dimension	Reasoning	Score
Specificity	Names the domain (mem0 setup) and lists several concrete actions — "API key configuration, MCP authentication, project file import, and coding categories" — with only minor gaps in granularity. Not a 5 because the actions are named as setup categories rather than fine-grained capabilities; not a 3 because four distinct concrete actions are enumerated.	4 / 5
Completeness	Clearly answers both what ("Sets up mem0 for a new project including...") and when ("Use on first run... when API key needs updating, or to re-run initial setup...") with concrete trigger phrases. Fits the 5 anchor exactly; below-anchor 4 would require an only-weakly-explicit when clause, which is not the case.	5 / 5
Trigger Term Quality	Natural trigger phrases users would say are present — "first run in a new project", "when API key needs updating", "re-run initial setup after configuration changes" — with good coverage. Not a 5 because there are no synonyms or extension-style variants, and a few natural phrasings (e.g. "mem0 setup", "initialize mem0") are missing.	4 / 5
Distinctiveness Conflict Risk	Tied to a specific plugin niche (mem0 onboarding) with distinct, scoped triggers and minimal overlap risk with unrelated skills. Anchor 5 (clear niche, minimal conflict risk) is the best fit; not lowered because nothing in the description is generic enough to invite misfiring.	5 / 5
	Total	18 / 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: integrations/mem0-plugin/skills/onboard/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.