Name: zendesk-guide
Rating: 52 (1 reviews)
Author: membranedev

zendesk-guide

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

Quality

57%

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/zendesk-guide/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 actionable with concrete CLI commands and a well-handled connection state machine, but it is padded with product explanation, lacks validation checkpoints before destructive proxy operations, and keeps all detail inline with no reference files. Tightening the intro and adding pre-flight validation would raise the score.

Suggestions

Cut the opening paragraph explaining what Zendesk Guide is and the editorializing about auth plumbing; Claude already knows the product.

Add an explicit validation/check step before destructive proxy requests (e.g. verify the method and target with the user before running DELETE/PUT/PATCH via `membrane request`).

Fix the dangling "skip to Step 2" reference by either numbering the subsequent steps or rewriting it as "skip to Searching for actions".

Move the detailed connection state machine and proxy flag reference into separate reference files and link to them from SKILL.md to improve progressive disclosure.

Dimension	Reasoning	Score
Conciseness	The body opens by explaining what Zendesk Guide is ("knowledge base and self-service platform that helps businesses create, manage, and share support content") and includes editorializing ("so you can focus on the integration logic rather than auth plumbing"), matching the score-3 anchor of mostly efficient with some unnecessary explanation.	3 / 5
Actionability	Provides copy-paste-ready commands (npm install, membrane login, connection ensure, action run, request) plus a complete proxy flag table, but relies on placeholders like CONNECTION_ID and the "Popular actions" section only repeats the discovery command without listing actual actions, matching score-4.	4 / 5
Workflow Clarity	Connection setup has genuine feedback loops (poll with --wait, READY/BUILDING/CLIENT_ACTION_REQUIRED state handling), but proxy requests permit destructive methods (DELETE) with no validation checkpoint, which caps workflow clarity at 3 per the rubric; a broken "skip to Step 2" reference with no Step 2 heading also adds a gap.	3 / 5
Progressive Disclosure	No bundle files exist and all ~140 lines are inlined under section headers; content that could be split out (the connection state machine, the proxy flag reference table) is inlined rather than referenced, matching the score-3 anchor rather than 4.	3 / 5
	Total	13 / 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 correctly identifies the Zendesk Guide niche and includes an explicit "Use when" trigger, but its action language is generic and lacks concrete capabilities or synonym keywords. It is distinct but could be sharper and more specific.

Suggestions

Replace generic verbs ("Manage data, records, and automate workflows") with concrete actions, e.g. "Create, update, and search help center articles, sections, and categories".

Add natural synonym trigger terms such as "help center", "knowledge base", and "support articles" alongside "Zendesk Guide".

Tighten the "Use when" clause with specific triggers like "Use when the user wants to create or search help center articles or manage Zendesk Guide sections and categories".

Dimension	Reasoning	Score
Specificity	Names the Zendesk Guide domain but the actions ("Manage data, records, and automate workflows") are generic verbs rather than concrete operations, matching the score-2 anchor; it is not a 3 because no specific actions like create/fill/merge are listed.	2 / 5
Completeness	Both a "what" (integration, manage data/records, automate workflows) and an explicit "when" ("Use when the user wants to interact with Zendesk Guide data") are present but generic, matching the score-4 anchor; not 5 because neither side uses concrete trigger phrases.	4 / 5
Trigger Term Quality	"Zendesk Guide" is a natural keyword users would say, but no synonyms or variations (help center, knowledge base, articles) are included, matching the score-3 anchor rather than 4 which expects fuller keyword coverage.	3 / 5
Distinctiveness Conflict Risk	The named product "Zendesk Guide" gives a clear niche with distinct triggers, but the generic action verbs create minor overlap risk with sibling Membrane integration skills, placing it at 4 rather than 5.	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/zendesk-guide/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.