Name: metabase
Rating: 59.2 (1 reviews)
Author: membranedev

metabase

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

Quality

68%

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/metabase/SKILL.md

Quality

Content

75%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 a well-structured, mostly executable guide to driving Metabase through the Membrane CLI, with a strong connection-state workflow. Its main weaknesses are a padded intro, a broken empty overview section, dangling step references, and the absence of any Metabase-specific action example or output verification.

Suggestions

Remove or fill the empty 'Metabase Overview' section (the bare Question/Result/Dashboard bullets and 'Use action names and parameters as needed.' add noise) and trim the opening paragraph that explains what Metabase is.

Fix the step numbering: replace the dangling 'skip to Step 2' and lone '1b' with a consistent labeled sequence so the connection flow is unambiguous.

Add one concrete Metabase action example (e.g., listing questions or fetching a dashboard result) with its expected output, plus a verification note after running actions that mutate data.

Dimension	Reasoning	Score
Conciseness	The body is mostly lean executable CLI commands with a flag table, but it pads a few spots Claude likely already knows (the opening 'Metabase is a business intelligence...' paragraph) and includes a broken, near-empty 'Metabase Overview' section, fitting 'efficient; minor instances of over-explanation that could be trimmed' rather than the spotless 5.	4 / 5
Actionability	It provides copy-paste-ready commands for install, login, connection, action search/run, and proxy with a concrete flag table, but the examples are generic Membrane CLI patterns with placeholders (CONNECTION_ID, --input '{"key": "value"}') and no Metabase-specific action example, matching 'mostly executable guidance; minor gaps'.	4 / 5
Workflow Clarity	The connection flow has a clear sequence with explicit state checkpoints and a feedback loop (poll --wait, handle READY/BUILDING/CLIENT_ACTION_REQUIRED, re-poll), but it references a non-existent 'Step 2' and '1b' without a 1a, and running actions lacks any result verification, fitting 'clear sequence with most checkpoints present; minor validation gaps'.	4 / 5
Progressive Disclosure	With no bundle files, the single ~154-line SKILL.md is organized into clear sections (Install, Authentication, Connecting, Searching, Running, Proxy, Best practices) that are easy to navigate, matching 'good structure; most content appropriately placed; minor organization gaps'; the empty Overview section and thin 'Popular actions' pointer are the minor gaps.	4 / 5
	Total	16 / 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 clearly identifies the Metabase domain and includes an explicit 'Use when' trigger, but its action verbs are generic and it omits natural Metabase-specific terms (dashboards, questions, analytics) that users would actually say. It is functional but could be sharpened with concrete capabilities and richer triggers.

Suggestions

Replace generic verbs with concrete Metabase capabilities, e.g. 'Run and explore questions, build and edit dashboards, query and manage records, and automate workflows'.

Expand the trigger clause with natural terms users say: 'Use when the user wants to work with Metabase questions, dashboards, analytics, or BI data'.

Keep the description in third person (it already is) and ensure it stays under one concise line to avoid fluff.

Dimension	Reasoning	Score
Specificity	Names the Metabase domain and a few actions ('Manage data, records, and automate workflows'), but the verbs are generic ('manage', 'automate') rather than concrete like 'extract' or 'fill'; it sits at the '1-2 concrete actions, not comprehensive' anchor and not below because it does list multiple action areas.	3 / 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 Metabase data'), but the trigger clause is generic rather than concrete, fitting the 'both present, when could be more specific' anchor rather than the fully concrete 5.	4 / 5
Trigger Term Quality	The only natural keyword is 'Metabase' / 'Metabase data' in 'Use when the user wants to interact with Metabase data'; common variations users would say (dashboards, questions, analytics, BI, charts) are missing, matching the 'some relevant keywords but missing common variations' anchor.	3 / 5
Distinctiveness Conflict Risk	Naming the specific app Metabase gives a clear niche with minimal conflict risk, but the generic 'interact with Metabase data' trigger leaves minor overlap risk with general data skills, so it sits at 'mostly distinct; minor overlap risk' rather than the clean 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/metabase/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.