onboarding

Onboard a user to Wren Engine end-to-end. Walks through environment checks, project scaffolding, connection configuration via .env, and first query. Use when: user wants to install Wren Engine, set up a new data source connection, or bootstrap a new project from scratch. Triggers: '/wren-onboarding', 'install wren', 'set up wren engine', 'wren onboarding', 'connect new database to wren'.

Quality

89%

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.

An exemplar procedural skill: concrete executable commands, explicit one-step-per-turn gating, validation checkpoints with error-recovery routing, and disciplined delegation of detail to external docs. Remaining gains are marginal — trim a little explanatory padding and move the inline .env/YAML templates into reference files.

Suggestions

Trim rationale prose (e.g., the Step 3.6 multi-project future-proofing paragraph) to plain statements of what the command writes.

Move the inline .env example, conn.yml template, and error-symptom list into a references/ file to slim SKILL.md further and enable lazy loading.

Consolidate the credential-handling rule into the single Mode-of-operation bullet instead of restating it in Steps 1–3.

Dimension	Reasoning	Score
Conciseness	The body is efficient and assumes competence ("PEP 668 systems will need this", no Python/venv tutorials), but a few spots pad — the multi-project future-proofing rationale in Step 3.6 and credential warnings repeated across the Mode-of-operation rules, Step 2, and Step 3. Not a 5: these could be trimmed; not a 3: no explanation of concepts Claude already knows.	4 / 5
Actionability	Fully executable, copy-paste-ready commands at every step ("wren docs connection-info <ds> --format md", "wren profile add <project> --from-file /tmp/conn.yml", "wren context init --empty") with a complete postgres .env example covering the common case. Placeholders like <ds> are inherent to a template and their resolution is itself commanded via introspection.	5 / 5
Workflow Clarity	A clearly sequenced multi-step process with explicit validation checkpoints and feedback loops: preflight gates, "Only after the user replies 'done'", automatic profile validation with warning→troubleshooting routing, "wren context validate" before "wren context build", and a dedicated On-error recovery section. Matches the 5 anchor.	5 / 5
Progressive Disclosure	Good structure: the body acts as a dispatcher with clearly signaled one-level-deep references ("Procedural details, per-datasource setup notes, and the troubleshooting playbook live in the docs, not here") to installation.md, connect.md, quickstart.md, and sibling skills. Not a 5: no bundle files exist, and roughly 160 lines of inline templates (.env example, conn.yml, error-symptom list) could be split into reference files; not a 3: references are well signaled and nothing is deeply nested.	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: third-person, concrete about what the skill does, with an explicit Use-when clause and product-specific trigger phrases. The only weaknesses are minor — a missing mention of the MDL generation step and a few natural trigger variations.

Suggestions

Mention MDL generation in the capability list (e.g., "...connection configuration via .env, MDL generation, and first query") to fully cover the workflow the body delivers.

Add one or two natural trigger variations such as "getting started with wren" or "add a data source to wren" to broaden keyword coverage.

Dimension	Reasoning	Score
Specificity	"Walks through environment checks, project scaffolding, connection configuration via .env, and first query" names the domain plus four concrete actions. Falls short of the 5 anchor only because a core workflow capability (MDL generation) is unmentioned, a minor coverage gap.	4 / 5
Completeness	Clearly answers both: a third-person "what" ("Onboard a user to Wren Engine end-to-end. Walks through...") and an explicit "when" ("Use when: user wants to install Wren Engine, set up a new data source connection, or bootstrap a new project from scratch") with concrete trigger phrases — a direct match for the 5 anchor.	5 / 5
Trigger Term Quality	Explicit triggers "install wren", "set up wren engine", "wren onboarding", "connect new database to wren", plus "/wren-onboarding", are natural phrases a user would say. A few natural variations (e.g., "getting started with wren", "add a data source") are missing, so it sits between the 4 and 5 anchors, closer to 4.	4 / 5
Distinctiveness Conflict Risk	Every capability and trigger is anchored to the specific product "Wren Engine" ("install Wren Engine", "wren onboarding"), creating a clear niche with minimal overlap risk against generic installation or database skills.	5 / 5
	Total	18 / 20 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
metadata_version	'metadata.version' is missing	Warning

	Total	15 / 16 Passed

Repository: Canner/WrenAI
Path: core/wren/src/wren/skills_content/onboarding/SKILL.md
Commit: 2cc843f

Reviewed: 4 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.