usage

Wren Engine CLI workflow guide for AI agents. Answer data questions end-to-end using the wren CLI: gather schema context, recall past queries, write SQL through the MDL semantic layer, execute, and learn from confirmed results. Use when: user asks a data question, requests a report or analysis, asks about metrics, revenue, customers, orders, trends, or any business data; user says 'how many', 'show me', 'what is the', 'top N', 'compare', 'trend', 'growth', 'breakdown'; user wants to explore, analyze, filter, aggregate, or summarize data from a database; agent needs to query data, connect a data source, handle errors, or manage MDL changes via the wren CLI.

Quality

93%

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 strong operational skill: workflows are sequenced with explicit validation and error-recovery feedback loops, and guidance is almost entirely executable commands. The main improvement areas are trimming the duplicated datasource list and moving the detailed cube-query flag/error material into the reference layer.

Dimension	Reasoning	Score
Conciseness	The body is dense with command tables, decision trees, and error-pattern mappings with essentially no explanation of concepts Claude already knows. It slips slightly below fully lean: the datasource extras list ('postgres...oracle') is repeated verbatim at line 43 and line 203, and the preflight install flow runs long.	4 / 5
Actionability	Nearly every section gives copy-paste-ready commands ('wren memory fetch -q "..." --model <name> --threshold 0', 'wren cube query --cube revenue --measures total,order_count ...') with concrete error-pattern-to-fix tables and a command decision tree. Not a 4 because there are no gaps: common cases (simple vs complex queries, cube vs raw SQL, each error class) all carry executable examples.	5 / 5
Workflow Clarity	The four workflows are explicitly sequenced with validation checkpoints and feedback loops — dry-plan verification before executing complex SQL, 'Fix ONE issue at a time. Re-run dry-plan after each fix', validate → build → index → verify after MDL changes, and layered error recovery (Layer 1 → 2A/2B). This matches the top anchor including explicit validate → fix → retry loops for database operations.	5 / 5
Progressive Disclosure	Good structure with clearly signaled one-level-deep references ('For memory-specific decisions, see the memory reference', 'see the wren-sql reference') that both exist in ./references/. Not a 5 because the signals point to 'wren skills get usage --full' rather than the reference files themselves, and a substantial block of cube-query flag syntax and error tables is inlined in SKILL.md that could live in a reference file.	4 / 5
	Total	18 / 20 Passed

Description

96%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 explicitly answers both what and when with concrete trigger phrases and specific CLI actions in third-person voice. Only weakness is trigger breadth — 'any business data' and generic analysis phrasings create minor conflict risk with non-wren data skills.

Dimension	Reasoning	Score
Specificity	'gather schema context, recall past queries, write SQL through the MDL semantic layer, execute, and learn from confirmed results' plus 'connect a data source, handle errors, or manage MDL changes' names multiple specific concrete actions with comprehensive coverage of the CLI's surface. Not a 4: there are no meaningful gaps in the action list.	5 / 5
Completeness	The first sentence states what ('Answer data questions end-to-end using the wren CLI' with a colon-expanded action list) and 'Use when: user asks a data question, requests a report or analysis...' explicitly states when with concrete trigger phrases. Matches the top anchor exactly.	5 / 5
Trigger Term Quality	'how many', 'show me', 'what is the', 'top N', 'compare', 'trend', 'growth', 'breakdown' plus 'metrics, revenue, customers, orders, trends' covers natural user phrasings and synonyms comprehensively. Not a 4: the common variations users actually say are explicitly enumerated.	5 / 5
Distinctiveness Conflict Risk	'using the wren CLI' and 'MDL semantic layer' give a clear niche with distinct tool-specific triggers. Not a 5: the broad phrases 'any business data', 'requests a report or analysis', and 'explore, analyze, filter, aggregate, or summarize data from a database' could fire for a generic SQL/data-analysis skill that isn't wren.	4 / 5
	Total	19 / 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/usage/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.