Name: mandrill
Rating: 55.2 (1 reviews)
Author: membranedev

mandrill

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

Quality

62%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/mandrill/SKILL.md

Quality

Content

67%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, actionable Membrane-based integration guide with clear sequencing and validation checkpoints for the connection lifecycle, weakened mainly by a few padded/low-information sections (the concept intro and the bare Overview bullets) that add tokens without value.

Suggestions

Remove or compress the introductory paragraph and the empty 'Mandrill Overview' bullet list, or replace them with the actual Messages/Templates actions.

Delete the filler line 'When to use which actions: Use action names and parameters as needed.' since it carries no guidance.

Convert the proxy-flags table to a short example or move the full flag reference behind a one-line pointer so the main flow stays lean.

Dimension	Reasoning	Score
Conciseness	Most of the body is efficient executable CLI guidance, but it includes unnecessary padding — the introductory 'Mandrill is a transactional email API service...' paragraph, the content-free 'Mandrill Overview' bullet list, and the filler line 'When to use which actions: Use action names and parameters as needed.' — matching 'mostly efficient but includes some unnecessary explanation.'	3 / 5
Actionability	It provides concrete, copy-pasteable `membrane` CLI commands with real flags and `--json` outputs throughout (login, connection ensure, action list/run, request proxy), with only minor gaps such as placeholder values, fitting 'mostly executable guidance; concrete commands with minor gaps.'	4 / 5
Workflow Clarity	The install → auth → connect → wait-for-ready → search → run sequence is clearly ordered with explicit state-based validation checkpoints (READY / CLIENT_ACTION_REQUIRED / CONFIGURATION_ERROR) and a polling feedback loop, meeting 'clear sequence with most checkpoints present' though a couple of recovery branches are left implicit.	4 / 5
Progressive Disclosure	The body is organized into well-labeled sections (Auth, Connecting, Searching, Popular actions, Proxy requests, Best practices) and stays a single manageable file with no bundle references, but the inline proxy-flags table and the thin Overview section leave minor organization gaps versus the well-split ideal.	4 / 5
	Total	15 / 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 includes a 'Use when...' trigger and names the Mandrill niche, but its capability phrasing ("manage data, records, automate workflows") is generic and omits the concrete email actions that distinguish Mandrill, leaving trigger-term and specificity coverage mediocre.

Suggestions

Replace generic verbs with concrete Mandrill actions, e.g. 'Send transactional email, manage templates and messages, and automate email workflows.'

Add natural trigger terms users say: 'transactional email', 'send email', 'password resets', 'order confirmations', 'email templates'.

Sharpen the when-clause to mention email-sending intent, e.g. 'Use when the user wants to send or manage transactional email via Mandrill.'

Dimension	Reasoning	Score
Specificity	Names the Mandrill domain, but the stated actions — "Manage data, records, and automate workflows" — are generic and never mention the concrete Mandrill capabilities (send transactional email, templates, messages), fitting the 'actions minimal or generic' anchor rather than the concrete-actions anchors at 3+.	2 / 5
Completeness	It states both a what ("Mandrill integration. Manage data, records, and automate workflows.") and an explicit when ("Use when the user wants to interact with Mandrill data."), but the when trigger is somewhat generic and could be more specific, matching the 'both what and when; when could be more explicit' anchor.	4 / 5
Trigger Term Quality	"Mandrill" and "interact with Mandrill data" are relevant keywords, but the description omits the natural terms users would actually say (transactional email, send email, password resets, email templates), so it matches 'some relevant keywords but missing common variations or synonyms.'	3 / 5
Distinctiveness Conflict Risk	Naming the specific Mandrill product gives it a clear niche with minimal conflict risk, though the generic "data, records, and workflows" phrasing introduces minor overlap with broad integration skills, matching 'mostly distinct; minor overlap risk.'	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/mandrill/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.