Name: metriql-docs
Rating: 59.2 (1 reviews)
Author: membranedev

metriql-docs

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

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/metriql-docs/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 body is highly actionable, with copy-paste ready Membrane CLI commands and a clear connection state-machine workflow including polling feedback loops. Its weaknesses are modest verbosity in a few explanatory sentences and a step-labeling scheme with minor inconsistencies.

Suggestions

Trim padded prose such as the auth-plumbing aside and the agent-types explanation to improve token efficiency.

Fix the step numbering so '1b' has a matching '1a' and label 'Step 2' explicitly where 'skip to Step 2' is referenced.

Consider moving the detailed clientAction state-machine and the proxy flag table into a separate reference file to keep SKILL.md a leaner overview.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient concrete commands, but several padded sentences ("so you can focus on the integration logic rather than auth plumbing", "This is the fastest way to get a connection", and the agent-types blurb) could be trimmed without losing information.	3 / 5
Actionability	Fully executable, copy-paste ready commands with clearly marked placeholders (CONNECTION_ID, <actionId>, QUERY) cover install, auth, connect, search, run, and proxy, plus a flag table for the proxy path.	5 / 5
Workflow Clarity	A clear sequence with a state-machine feedback loop (poll until READY, handle CLIENT_ACTION_REQUIRED then re-poll) is present; minor gaps are inconsistent step labels (a "1b" without a clear "1a", and a "skip to Step 2" that references an unlabeled Step 2).	4 / 5
Progressive Disclosure	Content is well-organized into clear sections with no nested references; at over 50 lines and fully inline with no separate reference files, the detailed clientAction state machine and proxy flag table could arguably live in reference files, which is a minor gap.	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 names the target product and includes an explicit 'Use when' trigger clause, satisfying both what and when. Its main weakness is generic action language (manage/automate) that lacks concrete Metriql-specific operations and overlaps boilerplate used across sibling integration skills.

Suggestions

Replace generic verbs with concrete Metriql-specific actions, e.g. 'Query metrics and dimensions, explore the Metriql model, and run reports.'

Add natural trigger variations users might say, such as 'metrics', 'semantic layer', 'dimensions', or 'measures', beyond just 'Metriql Docs data'.

Tighten the 'what' clause to distinguish it from sibling Membrane integration descriptions that share the 'Manage data, records, and automate workflows' phrasing.

Dimension	Reasoning	Score
Specificity	Names the domain plus several action areas ("Manage data, records, and automate workflows"), but the verbs are generic (manage, automate) rather than concrete Metriql-specific operations, so it sits above the minimal/generic anchor but below comprehensive concrete actions.	3 / 5
Completeness	Both 'what' ("Manage data, records, and automate workflows") and an explicit 'when' trigger ("Use when the user wants to interact with Metriql Docs data") are present; the 'what' is generic, which keeps it below a 5.	4 / 5
Trigger Term Quality	Relevant keywords center on the named product ("Metriql Docs", "Metriql Docs data") plus "data, records, workflows", but there are few natural-phrase variations or synonyms a user would actually say beyond the product name.	3 / 5
Distinctiveness Conflict Risk	Tied to a specific named product with a distinct trigger ("interact with Metriql Docs data"), but the generic action boilerplate ("Manage data, records, and automate workflows") overlaps with sibling Membrane integration skills, creating minor conflict risk.	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/metriql-docs/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.