Name: front
Rating: 62.4 (1 reviews)
Author: membranedev

front

Front integration. Manage Conversations, Contacts, Tags, Channels, Teams, Users. Use when the user wants to interact with Front data.

Quality

73%

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/front/SKILL.md

Quality

Content

65%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 excels at actionability with comprehensive executable Membrane CLI commands and a thorough actions table, but loses points on conciseness (front-loaded product explanation and filler) and workflow clarity (destructive operations lack validation checkpoints). Progressive disclosure is middling because the bulk API listing is inlined rather than split into a reference file.

Suggestions

Add an explicit verification/confirmation checkpoint for destructive actions (e.g., re-fetch a contact after delete-contact, or confirm before running delete/update) so workflow clarity can exceed the destructive-operation cap of 3.

Move the 20-row 'Popular actions' table into a separate reference file (e.g. references/actions.md) and link to it from the body, raising progressive disclosure.

Trim the opening 'Front is a customer communication hub...' paragraph and the 'Use action names and parameters as needed' filler, and fix the dangling 'skip to Step 2' reference by labeling the workflow steps.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient with concrete CLI commands, but it opens with a marketing-style explanation of what Front is ('Front is a customer communication hub that combines email, messaging, and apps...') and includes filler like the sparse 'Front Overview' tree and 'Use action names and parameters as needed', which is unnecessary explanation beyond minor trimming.	3 / 5
Actionability	It provides fully executable, copy-paste-ready commands for every common case (install, login, connection ensure, poll/wait, action list, action run with JSON input, request proxy) plus a 20-row popular-actions table with concrete keys, matching the score-5 anchor for copy-paste-ready coverage.	5 / 5
Workflow Clarity	The connection flow is well-sequenced with a feedback loop (re-poll after CLIENT_ACTION_REQUIRED) and error handling, but destructive and batch operations (e.g. delete-contact, list-all) appear in the actions table with no validation/verification checkpoint, so workflow clarity is capped at 3 per the destructive-operation rule; a dangling 'skip to Step 2' reference also has no labeled Step 2.	3 / 5
Progressive Disclosure	The file is organized into clear sections with no nested references, but at ~175 lines it inlines a large popular-actions API table that belongs in a separate reference file and provides no one-level-deep reference links, matching the score-3 anchor of content that should be separate being inline.	3 / 5
	Total	14 / 20 Passed

Description

82%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 strong on completeness and distinctiveness, explicitly pairing a clear 'what' with a concrete 'Use when...' trigger tied to the named Front platform. It is slightly weaker on specificity, since a single generic verb ('Manage') is applied across entities rather than enumerating distinct operations.

Suggestions

Replace the single generic verb 'Manage' with distinct concrete actions (e.g., 'List, search, create, update, and delete Conversations, Contacts, Tags...') to lift specificity toward score 4-5.

Add common user-facing synonyms to the trigger clause such as 'inboxes, messages, or tickets' alongside the entity keywords.

Dimension	Reasoning	Score
Specificity	The description names the domain (Front) and six concrete entities (Conversations, Contacts, Tags, Channels, Teams, Users), but applies only one generic verb ('Manage') rather than enumerating distinct concrete actions, so it matches 'names domain and 1-2 concrete actions, not comprehensive' better than the multi-verb pattern of score 4.	3 / 5
Completeness	It clearly answers what ('Front integration. Manage Conversations, Contacts, Tags, Channels, Teams, Users.') and explicitly answers when with a concrete trigger phrase ('Use when the user wants to interact with Front data.'), matching the score-5 anchor for both what and when.	5 / 5
Trigger Term Quality	It surfaces six natural entity-level keywords (Conversations, Contacts, Tags, Channels, Teams, Users) plus the explicit 'Use when... interact with Front data' trigger, but omits common synonyms users say (inbox, messages, tickets, email).	4 / 5
Distinctiveness Conflict Risk	The skill is tied to a specific named platform ('Front integration') with a distinct trigger ('interact with Front data'), giving it a clear niche with minimal conflict risk against other skills.	5 / 5
	Total	17 / 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/front/SKILL.md
Commit: f484c82

Reviewed: ~17 hours 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.