Name: onetrust
Rating: 51.2 (1 reviews)
Author: membranedev

onetrust

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

Quality

56%

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/onetrust/SKILL.md

Quality

Content

50%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-rich with concrete CLI commands and a solid connection-state workflow, but it is padded by a large feature-name bullet dump, lacks validation guidance for destructive action runs, and inlines reference material that belongs in separate files.

Suggestions

Move the ~80-item OneTrust feature enumeration into a separate reference file (e.g. references/entities.md) and keep SKILL.md as an overview that points to it.

Add a validation/verification checkpoint before running actions that mutate OneTrust data (e.g. confirm the action's inputSchema and output, dry-run where possible, verify the response state).

Trim filler such as 'so you can focus on the integration logic rather than auth plumbing' and condense overlapping 'Searching for actions' and 'Popular actions' sections.

Dimension	Reasoning	Score
Conciseness	An ~80-item bullet dump of OneTrust feature names plus mild filler ('so you can focus on the integration logic rather than auth plumbing') are padded token cost Claude does not need, matching the noticeably-verbose anchor with several unnecessary sections.	2 / 5
Actionability	Provides concrete, executable commands throughout (install, login, connection ensure, action list/run, request) with a flag table for proxying, leaving only minor gaps around parameter construction and output handling.	4 / 5
Workflow Clarity	The connection flow is well-sequenced with state polling and a feedback loop (CLIENT_ACTION_REQUIRED -> poll again), but running actions on OneTrust data is a potentially destructive/batch operation with no validation or verification checkpoint, capping clarity at 3.	3 / 5
Progressive Disclosure	Has section structure and headings, but the large inlined feature enumeration and inline action-discovery reference material clearly belong in separate files, and no bundle/reference files exist to absorb it.	3 / 5
	Total	12 / 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 is third-person, concise, and answers both what and when, anchored by a distinctive product name. Its main weakness is generic action verbs and a single trigger phrase rather than concrete OneTrust-specific capabilities and synonyms.

Suggestions

Replace generic verbs ('Manage data, records, and automate workflows') with concrete OneTrust operations such as 'handle data subject requests, run privacy assessments, and manage vendor records'.

Expand the 'Use when' clause with concrete trigger phrases users would say, e.g. 'Use when the user wants to file a data subject request, run a DPIA, or manage consent and vendor records in OneTrust'.

Add natural synonyms and entity names (DSR, assessments, vendors, consent receipts) to improve trigger term coverage.

Dimension	Reasoning	Score
Specificity	Names the domain (OneTrust) and a few actions ('Manage data, records, and automate workflows'), but the verbs are generic rather than concrete OneTrust-specific operations, matching the anchor for 1-2 concrete actions without comprehensive coverage.	3 / 5
Completeness	Explicitly answers both what ('Manage data, records, and automate workflows') and when ('Use when the user wants to interact with OneTrust data'), though the 'when' clause covers a single trigger rather than concrete variations, matching the 4-anchor.	4 / 5
Trigger Term Quality	Includes the natural product trigger 'Use when the user wants to interact with OneTrust data' and the keyword 'OneTrust', but lacks synonyms, variations, or concrete entity terms (e.g. data subject requests, assessments, vendors) users would name.	3 / 5
Distinctiveness Conflict Risk	Naming the specific product 'OneTrust' gives it a clear niche with minimal conflict risk, though the surrounding verbs (data, records, workflows) are broad enough to allow minor overlap with adjacent integration skills.	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/onetrust/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.