Name: looker
Rating: 56.8 (1 reviews)
Author: membranedev

Blog Docs Log in Get started

looker

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

Quality

65%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./skills/looker/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, mostly executable guide to the Membrane CLI integration with a clear state-polling connection workflow and feedback loops. It is held back by a padded introductory paragraph, vague overview filler, broken step references, and a "Popular actions" section that does not actually list actions.

Suggestions

Delete the "Looker is a business intelligence and analytics platform..." intro and the vague "Looker Overview" / "When to use which actions" filler; assume Claude knows what Looker is.

Fix the step numbering: label the connect step as "1a" and add an explicit "Step 2: Search for actions" so the "skip to Step 2" reference resolves.

Either name concrete popular Looker actions (e.g. run a Look, query an Explore, fetch dashboard tiles) or remove the empty "Popular actions" section that only re-prints the list command.

Dimension	Reasoning	Score
Conciseness	Most of the body is lean executable commands, but the opening "Looker is a business intelligence and analytics platform..." explains a concept Claude already knows, and the "Looker Overview" / "When to use which actions: Use action names and parameters as needed" lines are vague filler. It is mostly efficient with some unnecessary padding, matching anchor 3 rather than the trimmer anchor 4.	3 / 5
Actionability	Provides copy-paste ready commands throughout (install, login, connection ensure, action run, request) plus a concrete flag table. The "Popular actions" section only repeats the list command rather than naming actual popular actions, a minor gap that keeps it just below the fully-covering anchor 5.	4 / 5
Workflow Clarity	The connect→poll→act sequence has explicit state checkpoints (READY, CLIENT_ACTION_REQUIRED, CONFIGURATION_ERROR) and a retry feedback loop ("poll again... to check if the state moved to READY"). Broken step references ("skip to Step 2" with no Step 2; "1b" with no labeled 1a) are minor gaps that prevent anchor 5.	4 / 5
Progressive Disclosure	No bundle files exist (references/scripts/assets absent) and the SKILL.md is a single well-sectioned document with clear ## and ### headers. At ~140 lines it exceeds the under-50-line simple-skill exception, but the structure is good and content is reasonably placed, matching anchor 4 rather than the monolithic/buried-reference lower anchors.	4 / 5
	Total	15 / 20 Passed

Description

62%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 cleanly answers both what the skill does and when to use it in third-person voice, and the Looker framing keeps it distinct. Its main weakness is generic verbs and thin trigger coverage, which would benefit from concrete Looker-specific actions and trigger phrases (dashboards, explores, LookML).

Suggestions

Replace generic verbs with concrete Looker actions, e.g. "Query Looker explores, run Looks, and manage dashboards" to lift specificity.

Broaden trigger terms to include natural phrases users say, e.g. "Use when the user wants to run Looker dashboards, explores, Looks, or query LookML models."

Keep the explicit "Use when..." clause but add 2-3 concrete trigger phrases so completeness reaches anchor 5.

Dimension	Reasoning	Score
Specificity	Names the Looker domain plus three actions ("Manage data, records, and automate workflows"), but the verbs are generic rather than concrete like "extract text, fill forms, merge documents". It sits above the single-action anchor 2 but lacks the specific actions needed for anchor 4.	3 / 5
Completeness	Explicitly states both what ("Looker integration. Manage data, records, and automate workflows.") and when ("Use when the user wants to interact with Looker data.") in third person. The "when" is a single trigger phrase that could be more specific, so it falls short of the multi-trigger anchor 5 but clears the missing-when anchor 3.	4 / 5
Trigger Term Quality	Includes the natural term "Looker" and the phrase "interact with Looker data", but misses common variations and synonyms a user might say (dashboards, reports, LookML, explores). Coverage is relevant but thin, matching the "some keywords, missing synonyms" anchor rather than the fuller anchor 4.	3 / 5
Distinctiveness Conflict Risk	"Looker" is a named BI platform giving a clear, distinct niche with minimal conflict risk. The generic verbs ("manage data, records") introduce minor overlap risk, keeping it just below the fully-distinct anchor 5.	4 / 5
	Total	14 / 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/looker/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.