Name: magicbell
Rating: 60 (1 reviews)
Author: membranedev

magicbell

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

Quality

70%

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/magicbell/SKILL.md

Quality

Content

82%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 highly actionable with concrete, executable Membrane CLI commands and a clear connection workflow that includes state validation and a retry feedback loop. It is well-organized and mostly lean; the only gaps are a slightly loose step numbering scheme and a monolithic single-file structure.

Dimension	Reasoning	Score
Conciseness	The body is dominated by tight, executable commands with purposeful explanatory prose around the connection state machine, so it is efficient with only minor trimmable fluff such as "so you can focus on the integration logic rather than auth plumbing". It matches the 4 anchor ("efficient; minor instances of over-explanation") and is below 5 because a few sentences could still be cut.	4 / 5
Actionability	It provides copy-paste-ready commands for the common cases — install, login, connection ensure, connection get --wait, action list, action run with --input JSON, and request with a full flag table — each concrete and executable. This matches the 5 anchor ("fully executable; copy-paste ready; specific examples cover the common cases").	5 / 5
Workflow Clarity	The install → authenticate → connect → poll-until-ready → search → run sequence is clear with explicit validation (state checks, --wait polling, CLIENT_ACTION_REQUIRED feedback loop, error-field inspection). It is 4 rather than 5 because step numbering is loose — "skip to Step 2" and "1b" reference a Step 2 that is not labeled as a header.	4 / 5
Progressive Disclosure	With no bundle files present, scoring falls to organization: the body is well-structured with clear section headers and content appropriately placed inline (the proxy flag table and connection state detail are reasonable to keep inline). It matches the 4 anchor ("good structure; most content appropriately placed; minor organization gaps") and is below 5 because everything lives in one ~140-line file with no split reference material.	4 / 5
	Total	17 / 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 pairs a "what" with an explicit "Use when" clause and is anchored to a distinct named product, but its actions are generic and it omits the natural notification-related trigger terms. Completeness and distinctiveness are solid; specificity and trigger coverage are the weak spots.

Suggestions

Replace the generic verbs ("Manage data, records, and automate workflows") with concrete MagicBell actions such as "send and fetch notifications, manage notification preferences, and list users and organizations".

Add natural trigger terms users would actually say — "notifications", "notification inbox", "MagicBell notifications" — instead of only "MagicBell data".

Tighten the "Use when" clause to name the triggering situations, e.g. "Use when the user wants to send, fetch, or manage MagicBell notifications."

Dimension	Reasoning	Score
Specificity	The description names the MagicBell domain but the actions — "Manage data, records, and automate workflows" — are minimal and generic rather than concrete capabilities like sending or fetching notifications. It sits below the 3 anchor ("names domain and 1-2 concrete actions") because no genuinely concrete action is named.	2 / 5
Completeness	It answers both what ("MagicBell integration. Manage data, records, and automate workflows.") and when ("Use when the user wants to interact with MagicBell data."), with an explicit "Use when" clause so it is not capped at 3. It is 4 rather than 5 because the "when" trigger ("interact with MagicBell data") is generic and could be more concrete.	4 / 5
Trigger Term Quality	It includes the natural product keyword "MagicBell" and "MagicBell data", but misses common variations a user would actually say such as "notifications", "notification inbox", or "notification preferences". This matches the 3 anchor ("some relevant keywords but missing common variations or synonyms") and is below 4 because several natural terms are absent.	3 / 5
Distinctiveness Conflict Risk	The named product "MagicBell" gives it a clear niche with low conflict risk against unrelated skills, though the generic "manage data, automate workflows" phrasing could overlap with broad data/workflow skills. This fits the 4 anchor ("mostly distinct; minor overlap risk") and is below 5 only because the action verbs are not MagicBell-specific.	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/magicbell/SKILL.md
Commit: f484c82

Reviewed: 6 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.