Name: lookml
Rating: 55.2 (1 reviews)
Author: membranedev

Blog Docs Log in Get started

lookml

LookML integration. Manage data, records, and automate workflows. Use when the user wants to interact with LookML data.

Quality

62%

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

Fix and improve this skill with Tessl

tessl review fix ./skills/lookml/SKILL.md

Quality

Content

67%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, actionable CLI guide with a clear connection workflow and state-machine checkpoints, weakened mainly by an unnecessary intro definition and minor inconsistencies in step numbering.

Suggestions

Remove or trim the opening 'LookML is a declarative modeling language...' paragraph and the 'focus on integration logic rather than auth plumbing' marketing phrasing, since Claude already knows these concepts.

Fix the step numbering: add a '1a' label and label the referenced 'Step 2' so the connection→search→run sequence is unambiguous.

Consider moving the detailed clientAction object fields and the proxy flags table into a separate reference file to keep SKILL.md a lean overview.

Dimension	Reasoning	Score
Conciseness	The body is mostly command-focused and efficient but includes unnecessary explanation Claude already knows (the opening 'LookML is a declarative modeling language...' definition) and padded marketing lines like 'so you can focus on the integration logic rather than auth plumbing', matching 'Mostly efficient but includes some unnecessary explanation'.	3 / 5
Actionability	It provides many concrete, executable commands (npm install, membrane login, connection ensure, connection get --wait, action list/run, request) with real flags and a proxy options table, matching 'Mostly executable guidance; concrete code or commands with minor gaps'; not a 5 because placeholders and a discovery-only 'Popular actions' section leave LookML-specific examples implicit.	4 / 5
Workflow Clarity	There is a clear install→auth→connect→poll→search→run sequence with an explicit connection state machine and a poll-again feedback loop for CLIENT_ACTION_REQUIRED, matching 'Clear sequence with most checkpoints present'; not a 5 because step numbering is inconsistent (a '#### 1b' with no 1a, and references to 'Step 2' that is never labeled).	4 / 5
Progressive Disclosure	Content is organized into well-labeled sections with no nested/deep references and no bundle files, and a focused single-file CLI guide is an appropriate structure, matching 'Good structure; most content is appropriately placed; minor organization gaps'; not a 5 because it exceeds ~50 lines without splitting the detailed clientAction and proxy reference material into a separate file.	4 / 5
	Total	15 / 20 Passed

Description

57%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 correctly includes a 'Use when' trigger and names the LookML niche, giving it solid completeness and distinctiveness, but the action wording is generic and the trigger terms lack synonyms users actually say.

Suggestions

Replace generic verbs with concrete LookML actions, e.g. 'Create and edit LookML models, views, and explores; run queries; manage dimensions and measures.'

Expand the trigger phrase to cover natural synonyms: 'Use when the user wants to work with LookML or Looker models, views, explores, or .lkml files.'

Tie the 'when' clause to specific user intents (e.g., defining metrics, modeling data relationships) rather than the generic 'interact with LookML data'.

Dimension	Reasoning	Score
Specificity	The phrase 'Manage data, records, and automate workflows' names the LookML domain but the actions are generic abstractions rather than concrete operations, matching 'Names the domain but actions are minimal or generic'; it is not a 3 because no action is as concrete as 'extracts content'.	2 / 5
Completeness	It has both a 'what' ('Manage data, records, and automate workflows') and an explicit 'when' ('Use when the user wants to interact with LookML data'), but the 'when' is generic and could be more specific, matching anchor 4; not capped at 3 because a 'Use when' clause is present.	4 / 5
Trigger Term Quality	'Use when the user wants to interact with LookML data' surfaces the core keyword 'LookML' but misses common variations and synonyms users say (Looker, models, views, explores, .lkml), matching 'Some relevant keywords but missing common variations or synonyms'.	3 / 5
Distinctiveness Conflict Risk	'LookML' is a clear niche with distinct triggers and low conflict risk, but the generic 'Manage data, records, and automate workflows' wording creates minor overlap with general data-management skills, matching 'Mostly distinct; minor overlap risk'.	4 / 5
	Total	13 / 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
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: membranedev/application-skills
Path: skills/lookml/SKILL.md
Commit: f484c82

Reviewed: 6 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.