Name: mail-blaze
Rating: 55.2 (1 reviews)
Author: membranedev

mail-blaze

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

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./skills/mail-blaze/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 is a strong, mostly executable guide with concrete CLI commands and a clear connection-polling branch, held back by a broken step numbering scheme (orphaned '1b', undefined 'Step 2') and the absence of any validation/confirmation step around destructive proxy operations. Fixing the workflow sequence and adding a safety checkpoint would move the strongest dimensions up.

Suggestions

Fix the broken workflow numbering: either add the missing 'Step 1' / '1a' section or renumber linearly, and define 'Step 2' explicitly instead of forward-referencing an undefined step.

Add a validation/confirmation checkpoint before destructive or batch proxy calls (e.g. 'Confirm the method and path before `-X DELETE` or `PUT`; verify the returned status before proceeding'), which would also lift the workflow_clarity cap.

De-duplicate the 'Searching for actions' and 'Popular actions' sections, and consider a minimal end-to-end worked example binding a real CONNECTION_ID so the commands are fully copy-paste ready.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient: concrete commands with brief, targeted explanations and no padding about what an email platform or CLI is. A few lines over-explain (e.g. restating that Membrane handles auth in multiple sections), but it leans well above the midpoint rather than just barely efficient. Not 5 due to the repeated auth/credential guidance and the long flag table that restates obvious CLI options.	4 / 5
Actionability	Almost every section ships a concrete, runnable command (install, login, connection ensure/get, action list/run, request with flags) covering the common cases. It falls just short of fully copy-paste-ready 5 because placeholders like CONNECTION_ID are unbound and the proxy section lists flags without a full example for non-GET methods.	4 / 5
Workflow Clarity	There is a recognizable connection-state polling sequence with explicit READY/CLIENT_ACTION_REQUIRED/CONFIGURATION_ERROR branches, but the overall flow is broken: '#### 1b' appears with no 1a or 'Step 1', 'Step 2' is referenced but never defined, and destructive proxy operations (e.g. `-X DELETE`) get no validation/confirm step. Per the rubric, batch/destructive operations without validation cap workflow_clarity at 3, so it cannot exceed 3 despite the clear polling branch.	3 / 5
Progressive Disclosure	Content is well organized into overview, install, auth, connection, actions, proxy, and best-practices sections with no nested file references (none exist in the bundle). It is not 5 because the Popular actions section partly duplicates 'Searching for actions' and the inlined proxy flag table is content that, in a richer skill, would warrant a separate reference; still mostly well placed.	4 / 5
	Total	15 / 20 Passed

Description

60%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 successfully pairs a clear 'what' with an explicit 'Use when...' trigger and is anchored to the distinct Mail Blaze product, but the capability verbs stay generic and trigger-keyword coverage is thin. Tightening with concrete operations and richer natural-language triggers would push it into the top band.

Suggestions

Replace generic verbs ('Manage data, records, automate workflows') with concrete operations, e.g. 'create and send email campaigns, manage subscribers and lists, build automation sequences, and track campaign performance.'

Add natural trigger phrases and synonyms users would actually say, e.g. 'Use when the user asks about Mail Blaze email campaigns, subscriber lists, automations, or campaign analytics.'

Keep the explicit 'Use when...' clause (it correctly satisfies the trigger-guidance requirement) and third-person voice.

Dimension	Reasoning	Score
Specificity	Names the domain ('Mail Blaze data') and two concrete action families ('Manage data, records' and 'automate workflows'), but the actions stay generic and don't enumerate specific records or workflow operations. It sits at the 'names domain and 1-2 concrete actions, not comprehensive' anchor rather than 4 because no operations are itemized.	3 / 5
Completeness	It has a clear 'what' ('Manage data, records, and automate workflows') and an explicit 'when' ('Use when the user wants to interact with Mail Blaze data'), matching the 'both present, when could be more explicit' anchor. Not 5 because the trigger is generic and lacks concrete trigger phrases.	4 / 5
Trigger Term Quality	'interact with Mail Blaze data' is the one natural user phrase, but common variations (email campaigns, lists, subscribers, automations) and the product's actual name variations are missing. Not 2 because 'interact with Mail Blaze data' is a plausible user utterance, but not 4 given the thin keyword coverage.	3 / 5
Distinctiveness Conflict Risk	The 'Mail Blaze' name plus 'interact with Mail Blaze data' gives a fairly distinct niche with only minor overlap risk against other marketing/CRM skills. Not 5 because 'manage data, records' alone would be generic without the product name anchoring it.	4 / 5
	Total	14 / 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/mail-blaze/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.