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

Blog Docs Log in Get started

rokt

Rokt integration. Manage data, records, and automate workflows. Use when the user wants to interact with Rokt 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/rokt/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 a strong, actionable CLI guide with a well-sequenced connection workflow and explicit state/error handling. Its main weaknesses are a broken "Step 2" cross-reference and a duplicated action-discovery section, both minor.

Suggestions

Fix the dangling cross-reference: either add an actual "Step 2" heading after connection setup or replace "skip to Step 2" with a concrete anchor like "skip to Searching for actions".

Merge the redundant "Popular actions" section into "Searching for actions" so the `membrane action list` command appears once.

Add one complete end-to-end example (real intent -> action list -> action run with a sample input -> reading the `output` field) to close the actionability gap.

Dimension	Reasoning	Score
Conciseness	The body is largely efficient with concrete commands and a justified one-line platform intro, but the `membrane action list --intent=...` command is restated across "Searching for actions" and "Popular actions", a minor redundancy that fits 'efficient; minor instances that could be trimmed' below the lean 5.	4 / 5
Actionability	Provides copy-paste-ready commands (install, login, connection ensure, action list/run, request) and a thorough proxy-options table, but it relies on placeholders (CONNECTION_ID, QUERY) with no complete end-to-end input-to-output example and references a non-existent "Step 2", matching 'mostly executable guidance with minor gaps'.	4 / 5
Workflow Clarity	The install -> auth -> connect -> poll-until-ready -> search -> run sequence includes real validation checkpoints (state polling, CLIENT_ACTION_REQUIRED handling, CONFIGURATION_ERROR feedback), but the repeated "skip to Step 2" references a section that does not exist, a clarity gap that keeps it below the 5 anchor.	4 / 5
Progressive Disclosure	Content is well-organized into clearly headed sections with no nesting and no external bundle files needed, matching 'good structure; most content appropriately placed; minor organization gaps'; the duplicated action-discovery section is the main 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 answers both what and when and is anchored to a distinctive brand, but its action language is generic and the trigger coverage is narrow. Tightening the verbs and broadening the trigger phrases would lift it from good to strong.

Suggestions

Replace generic verbs with concrete Rokt-specific actions, e.g. "Manage Rokt campaigns, creatives, and conversion events; pull reports and attribution data".

Broaden the trigger phrase to cover natural variations: "Use when the user wants to manage Rokt campaigns, creatives, or accounts, run Rokt reports, or interact with Rokt data."

Drop the redundant "Manage data, records" pair (data and records overlap) to reduce fluff and improve specificity.

Dimension	Reasoning	Score
Specificity	Phrases like "Manage data, records, and automate workflows" name the Rokt domain and a few actions, but the verbs (manage, automate) and nouns (data, records) are generic rather than concrete, matching the 'names domain and 1-2 concrete actions but not comprehensive' anchor.	3 / 5
Completeness	Both a clear 'what' ("Rokt integration. Manage data, records, and automate workflows") and an explicit 'when' ("Use when the user wants to interact with Rokt data") are present, but the 'when' is a single narrow phrase and could be more specific, matching the 'has both what and when; when could be more explicit' anchor rather than the fully concrete 5.	4 / 5
Trigger Term Quality	The only real trigger phrase is "Use when the user wants to interact with Rokt data" plus the brand "Rokt"; relevant but missing common variations like 'Rokt campaigns', 'Rokt offers', or 'connect to Rokt', fitting the 'some relevant keywords but missing variations' anchor.	3 / 5
Distinctiveness Conflict Risk	"Rokt" is a specific brand giving it a clear niche and low conflict risk, but the generic "Manage data, records, and automate workflows" phrasing creates minor overlap with other data-management skills, matching 'mostly distinct; minor overlap 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/rokt/SKILL.md
Commit: f484c82

Reviewed: 4 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.