generate-mdl

Generate a Wren MDL project by exploring a database with available tools (SQLAlchemy, database drivers, MCP connectors, or raw SQL). Guides agents through schema discovery, type normalization, and MDL YAML generation using the wren CLI. Use when: user wants to create or set up a new MDL, onboard a new data source, or scaffold a project from an existing database.

Quality

83%

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

85%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 content is highly actionable with executable code and a clearly sequenced, validated workflow including feedback loops. It is well-organized and mostly concise; the main improvement is splitting a few dense reference-style sections into bundle files for cleaner progressive disclosure.

Suggestions

Move the full SQLAlchemy introspection snippet and the type-mapping Python/CLI examples into a bundled reference file (e.g. references/type_mapping.md) and link to it one level deep, keeping only a minimal example inline.

Trim the inline project directory tree and the SQLAlchemy comment annotations to reduce token bulk while preserving the executable essentials.

Add a short bundle file or section for common database-dialect type mappings (postgres, mysql, bigquery, snowflake) so the main body stays an overview.

Dimension	Reasoning	Score
Conciseness	The body is mostly lean and task-oriented with executable snippets and minimal concept padding, but sections like the long SQLAlchemy introspection example and the inline directory tree add some bulk that could be trimmed without losing clarity.	4 / 5
Actionability	It provides fully executable, copy-paste-ready code and CLI commands for each phase (SQLAlchemy introspection, parse_type calls, wren context init/validate/build, wren memory index), with concrete examples covering the common cases and explicit expected outputs.	5 / 5
Workflow Clarity	The seven phases are clearly sequenced with explicit validation checkpoints (Phase 5 validate -> fix -> re-run with a list of common errors), and Phase 7 closes the loop with an edit -> validate -> build -> index feedback cycle, satisfying the destructive/batch feedback-loop requirement.	5 / 5
Progressive Disclosure	The body is well structured into phases with a Quick reference table and clear sections, and it links out one level deep to external docs (Cube guide) and 'wren skills get usage'; however there are no in-bundle reference files, so a few dense sections (e.g. full SQLAlchemy snippet, type-mapping examples) could be split into referenced files for a 5.	4 / 5
	Total	18 / 20 Passed

Description

82%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, action-oriented, and clearly answers both what the skill does and when to use it, with concrete trigger phrases in third person. Trigger-term coverage is strong but could add a few more natural synonyms to fully maximize distinctiveness.

Dimension	Reasoning	Score
Specificity	Names the domain and lists several concrete actions (exploring a database, schema discovery, type normalization, MDL YAML generation) with the specific wren CLI tool, but each action is stated at a high level rather than enumerated comprehensively, leaving minor gaps in coverage.	4 / 5
Completeness	It clearly answers 'what' (explore a database, discover schema, normalize types, generate MDL YAML via wren CLI) and explicitly answers 'when' with concrete 'Use when:' trigger phrases covering create/set up, onboarding, and scaffolding scenarios.	5 / 5
Trigger Term Quality	Includes natural user-facing phrases like 'create or set up a new MDL', 'onboard a new data source', and 'scaffold a project from an existing database', with good keyword coverage, but misses common synonyms and concrete file/tool triggers a user might say (e.g. 'Wren', 'YAML', specific databases).	4 / 5
Distinctiveness Conflict Risk	It occupies a clear niche (Wren MDL project generation from an existing database) with distinct triggers, though 'onboard a new data source' is broad enough to create minor overlap risk with other data-ingestion skills.	4 / 5
	Total	17 / 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/generate-mdl/SKILL.md
Commit: 10a6432

Reviewed: 5 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.