Name: help-scout
Rating: 52.8 (1 reviews)
Author: membranedev

help-scout

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

Quality

59%

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/help-scout/SKILL.md

Quality

Content

61%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 solid, command-driven integration guide with executable Membrane CLI examples and a well-structured connection workflow including polling feedback loops. Its main weaknesses are some redundant/padded prose and an absence of validation checkpoints for destructive or batch Help Scout operations.

Suggestions

Add an explicit validation/verification step before running destructive or bulk actions (e.g. dry-run, confirm count, check output before committing).

De-duplicate the action-discovery command that appears in both 'Searching for actions' and 'Popular actions', and trim the auth-plumbing aside.

Fix the 'skip to Step 2' reference — no Step 1/Step 2 labels exist — by either numbering the steps or relinking to the correct section.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient with concrete commands, but includes some unnecessary explanation (e.g. 'so you can focus on the integration logic rather than auth plumbing') and repeats the action-list command across 'Searching for actions' and 'Popular actions', fitting the score-3 anchor of mostly efficient with some tightening needed.	3 / 5
Actionability	It provides concrete, copy-paste-ready commands (install, login, connection ensure, action run, request) plus a flags table, with only minor gaps such as the vague 'Search using a natural language description', matching the score-4 anchor of mostly executable guidance.	4 / 5
Workflow Clarity	The connection setup is well sequenced with state-based checkpoints and a poll-until-ready feedback loop, but the core action-running workflow (including the named 'Bulk Operation' entity) lacks validation/verification steps for destructive or batch operations, which per the rubric cap caps this at 3.	3 / 5
Progressive Disclosure	The single SKILL.md is well organized with clear section headers (Overview, Working with Help Scout, Popular actions, Best practices) and no nested references, though the inline connection-state handling and flags table could arguably live in separate files, fitting the score-4 anchor of good structure with minor organization gaps.	4 / 5
	Total	14 / 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 uses third person and includes an explicit 'Use when' clause, but its capability list is generic ('manage data, records, automate workflows') rather than naming concrete Help Scout actions. Distinctiveness is strong due to the named platform, while trigger-term coverage is adequate but lacks natural synonyms.

Suggestions

Replace generic verbs with concrete Help Scout capabilities, e.g. 'Respond to conversations, manage customers and users, search articles, and run bulk operations'.

Expand trigger terms to include natural user phrasing like 'customer support, tickets, conversations, shared inbox, knowledge base, or live chat'.

Make the 'when' clause more specific than 'interact with Help Scout data' by referencing the actual objects users work with.

Dimension	Reasoning	Score
Specificity	It names the Help Scout domain but the actions 'Manage data, records, and automate workflows' are minimal and generic rather than concrete Help Scout capabilities like responding to conversations or managing tickets, matching the score-2 anchor ('Processes PDF files').	2 / 5
Completeness	It answers both 'what' (Help Scout integration; manage data, records, automate workflows) and 'when' ('Use when the user wants to interact with Help Scout data'), but the 'when' clause is somewhat generic and could be more specific, matching the score-4 anchor.	4 / 5
Trigger Term Quality	It surfaces 'Help Scout' and 'Help Scout data' as relevant keywords but misses common natural variations a user would actually say (tickets, conversations, shared inbox, knowledge base, live chat), fitting the score-3 anchor of partial keyword coverage.	3 / 5
Distinctiveness Conflict Risk	Tying the trigger to the named platform 'Help Scout' carves a clear niche with minimal conflict risk, though the generic action verbs leave minor overlap risk with adjacent CRM/support skills, fitting the score-4 anchor.	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/help-scout/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.