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

veritone

Veritone integration. Manage data, records, and automate workflows. Use when the user wants to interact with Veritone 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/veritone/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 content is a strong, command-driven integration guide with clear sequencing and a real feedback loop for connection state. Its main weaknesses are an unnecessary background intro and a slightly confusing step cross-reference.

Suggestions

Cut the "Veritone is an AI platform... common users" background paragraph; Claude does not need it.

Fix the step numbering so the "1b" section aligns with the "Step 2" it references, or replace both with a single consistent label.

Make the "Popular actions" section list actual popular actions instead of restating the discovery command.

Dimension	Reasoning	Score
Conciseness	The body is mostly concrete commands, but the opening paragraph ("Veritone is an AI platform... Media companies, law enforcement, and government agencies are common users.") explains background Claude does not need.	3 / 5
Actionability	It provides copy-paste-ready commands for install, login, connection, action search/run, and proxy requests with flag tables, with only minor gaps (the "Popular actions" section restates discovery instead of listing actions).	4 / 5
Workflow Clarity	There is a clear install→auth→connect→search→run sequence with an explicit connection-state machine and a poll-after-action feedback loop, but the "Step 2" cross-reference (under a section labeled "1b") is confusing.	4 / 5
Progressive Disclosure	The single file is well-organized into labeled sections with no external bundle files; the inline proxy-flag table and clientAction state machine could be split out, but placement is reasonable.	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 is well-formed with an explicit Use-when trigger and a distinctive brand name, but its capability verbs are generic. It clears the minimum trigger-guidance bar while leaving the specifics underdeveloped.

Suggestions

Replace generic verbs with concrete Veritone capabilities, e.g. "Run transcription and object-detection engines, manage jobs, and browse files/folders."

Add natural trigger terms users actually say, such as "transcribe audio", "Veritone engines/jobs", or "aiware".

Dimension	Reasoning	Score
Specificity	"Manage data, records, and automate workflows" names the domain and a couple of actions, but the verbs ("manage", "automate") are generic rather than concrete capabilities like transcribing audio or running engines.	2 / 5
Completeness	It states both the what ("Veritone integration. Manage data, records, and automate workflows.") and an explicit when ("Use when the user wants to interact with Veritone data"), though the what is generic.	4 / 5
Trigger Term Quality	"Use when the user wants to interact with Veritone data" surfaces the brand keyword "Veritone", but offers no synonyms or related natural terms (transcription, engines, jobs, aiware).	3 / 5
Distinctiveness Conflict Risk	The named platform "Veritone" gives it a clear niche with minimal conflict risk, though the surrounding "manage data" phrasing is generic and could overlap with other data skills.	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/veritone/SKILL.md
Commit: f484c82

Reviewed: 3 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.