Name: sendblue
Rating: 64 (1 reviews)
Author: membranedev

sendblue

Sendblue integration. Manage Persons, Organizations, Leads, Pipelines, Deals, Users and more. Use when the user wants to interact with Sendblue data.

Quality

76%

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/sendblue/SKILL.md

Quality

Content

81%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 strongly actionable, well-sequenced integration guide with copy-paste CLI commands and a clear state-polling workflow. Its main gap is conciseness — an explainer intro and a few motivational lines could be trimmed — and a lack of any progressive-disclosure split despite some content that could live in reference files.

Suggestions

Trim the introductory 'Sendblue is an SMS marketing platform...' paragraph and motivational phrases like 'so you can focus on the integration logic rather than auth plumbing', since Claude does not need Sendblue/SMS marketing explained.

Consider moving the proxy flags table and the detailed connection state-machine into a separate reference file (e.g. references/connections.md) and linking to it from the body, to improve progressive disclosure.

Add a short explicit verification checkpoint after running actions (e.g. confirm the `output` field shape or check for an `error` field) so the run-action workflow has a feedback loop.

Dimension	Reasoning	Score
Conciseness	The body is mostly code and command-driven, but the intro paragraph ('Sendblue is an SMS marketing platform...') and motivational lines ('so you can focus on the integration logic rather than auth plumbing', 'This is the fastest way to get a connection') are trimmable padding Claude does not need.	3 / 5
Actionability	Provides fully executable, copy-paste-ready CLI commands throughout (install, login, connection ensure/get with --wait, action list/run with JSON input, request proxy) plus a concrete flags table, covering the common cases.	5 / 5
Workflow Clarity	The connection setup is a clearly sequenced multi-step flow with explicit polling, a state-to-action decision table (READY / CLIENT_ACTION_REQUIRED / CONFIGURATION_ERROR), and a feedback loop ('poll again after the user completes the action') for error recovery.	5 / 5
Progressive Disclosure	No bundle files exist, so all content lives in one well-organized SKILL.md with clean section headers and no nested references; it is easy to navigate but monolithic, with no one-level-deep references to split out the proxy/state-machine detail.	4 / 5
	Total	17 / 20 Passed

Description

71%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 cleanly states what the skill manages and when to use it, anchored to a distinctive brand name. Its main weakness is sparse trigger-term coverage — it leans on the brand name alone without the natural synonyms (SMS, contacts, campaigns) a user might actually say.

Suggestions

Add natural trigger terms and synonyms to the 'when' clause, e.g. 'Use when the user wants to send SMS, manage contacts or campaigns, or otherwise interact with Sendblue data.'

Replace the vague 'and more' padding with a couple more concrete entities or drop it, to push specificity toward comprehensive coverage.

Specify what 'Manage' means for the listed entities (e.g. 'create, update, and list') so the capabilities read as concrete actions.

Dimension	Reasoning	Score
Specificity	Names the domain and several concrete entity types ('Manage Persons, Organizations, Leads, Pipelines, Deals, Users'), but 'and more' is vague padding and the 'Manage' verb is generic, so it is not comprehensive enough for a 5.	4 / 5
Completeness	Explicitly answers both 'what' (manage the listed Sendblue entities) and 'when' ('Use when the user wants to interact with Sendblue data'), though the 'when' is generic rather than tied to concrete trigger phrases.	4 / 5
Trigger Term Quality	The trigger clause 'Use when the user wants to interact with Sendblue data' is present, but natural keywords are thin — only the brand name 'Sendblue' recurs with no synonyms or common variations like 'SMS', 'contacts', 'campaigns', or 'messages'.	3 / 5
Distinctiveness Conflict Risk	Tied to a distinctive branded app with named CRM-style entities, so it occupies a clear niche with minimal risk of triggering for the wrong skill.	5 / 5
	Total	16 / 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/sendblue/SKILL.md
Commit: f484c82

Reviewed: ~22 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.