Name: ometria
Rating: 56.00000000000001 (1 reviews)
Author: membranedev

ometria

Ometria integration. Manage Persons, Organizations, Deals, Pipelines, Activities, Notes and more. Use when the user wants to interact with Ometria data.

Quality

64%

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/ometria/SKILL.md

Quality

Content

57%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 action-dense with executable commands and a strong connection-setup workflow, but it pads token budget with redundant table rows and omits validation for destructive action runs. Progressive disclosure is absent since everything is inlined into one file.

Suggestions

Add a validate/error-check step to 'Running actions' (inspect output for errors before reporting success, confirm destructive operations) to lift workflow_clarity past the destructive/batch cap of 3.

Move the popular-actions table and the clientAction state-machine detail into a references/ file and link from the body, removing the repeated 'No description' noise to tighten conciseness.

Trim non-essential prose such as 'so you can focus on the integration logic rather than auth plumbing' that restates what Claude can infer from the commands.

Dimension	Reasoning	Score
Conciseness	Command examples are tight, but there is padding ('so you can focus on the integration logic rather than auth plumbing') and the popular-actions table repeats 'No description' twenty times, matching anchor 3's 'mostly efficient but some unnecessary explanation'.	3 / 5
Actionability	Concrete, copy-paste bash commands cover the common cases (install, login, connection ensure/get --wait, action list/run, request proxy) with real flags, but placeholder IDs like <actionId> and the 'No description' rows leave minor gaps, matching anchor 4.	4 / 5
Workflow Clarity	The connection flow is well-sequenced with state checkpoints, but 'Running actions' has no validation for destructive/batch operations (delete-custom-field, send-transactional-email, create-gdpr-deletion-request), so the destructive-operation cap holds it at anchor 3.	3 / 5
Progressive Disclosure	The body is a single self-contained file with no bundle references, and bulk content (the 20-row popular-actions table, the clientAction state machine) is inlined rather than split into a reference file, matching anchor 3.	3 / 5
	Total	13 / 20 Passed

Description

71%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 follows the what-plus-when template and names a distinct product, but the trigger phrase is generic and lacks the object-level vocabulary a user would actually say. Specificity is solid though not comprehensive.

Suggestions

Replace generic 'interact with Ometria data' with concrete trigger phrases naming the real Ometria objects (e.g. contacts, orders, campaigns, products, segments) so users' natural wording matches.

Use concrete verbs rather than the bare nouns list (e.g. 'Create and update contacts, manage orders and campaigns') to lift specificity toward comprehensive coverage.

Verify the managed-entity list matches the actual Ometria API surface — the body covers Contacts/Orders/Campaigns/Products, not Persons/Organizations/Deals/Pipelines.

Dimension	Reasoning	Score
Specificity	Lists the domain plus several concrete managed entities ('Persons, Organizations, Deals, Pipelines, Activities, Notes and more'), matching anchor 4 rather than 5 because they are nouns rather than concrete verbs and 'and more' leaves coverage open.	4 / 5
Completeness	Both 'what' ('Manage Persons, Organizations, Deals...') and an explicit 'when' ('Use when the user wants to interact with Ometria data') are present, but the trigger is generic rather than rich with concrete phrases, so it sits at anchor 4 rather than 5.	4 / 5
Trigger Term Quality	The only natural keyword is the product name in 'Use when the user wants to interact with Ometria data'; common object-level variations a user would say (contacts, orders, campaigns, products) are missing, matching anchor 3.	3 / 5
Distinctiveness Conflict Risk	'Ometria' is a specific named product giving a clear niche with distinct triggers and minimal conflict risk, matching anchor 5.	5 / 5
	Total	16 / 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/ometria/SKILL.md
Commit: f484c82

Reviewed: 5 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.