Name: sendgrid
Rating: 59.2 (1 reviews)
Author: membranedev

Blog Docs Log in Get started

sendgrid

SendGrid integration. Manage Campaigns. Use when the user wants to interact with SendGrid data.

Quality

68%

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/sendgrid/SKILL.md

Quality

Content

75%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 content is well-structured and actionable with a strong connection-setup workflow and validation feedback loops. Main gaps are a missing worked action example, an unlabelled 'Step 2' reference, and no verification step for destructive action execution.

Suggestions

Add one fully worked example (e.g. send-email with a concrete --input payload) so the running-actions guidance is copy-paste complete.

Label or fix the 'Step 2' cross-reference so the connection workflow's numbering is internally consistent.

Add a brief verify step after running destructive/batch actions (e.g. re-list or check the output status) to close the feedback loop.

Dimension	Reasoning	Score
Conciseness	The body is mostly tight commands, tables, and flag references; only the opening SendGrid definition paragraph and the vague 'Use action names and parameters as needed.' line are trimmable over-explanation.	4 / 5
Actionability	Provides concrete, copy-paste-ready CLI commands (login, connection ensure, action list/run, request) plus a popular-actions table, but lacks a fully worked end-to-end example with real parameter values for a representative action like send-email.	4 / 5
Workflow Clarity	The connection setup flow is clearly sequenced with explicit state checks and a poll-after-user-action feedback loop, though the referenced 'Step 2' is never labelled and action execution has no result-verification step.	4 / 5
Progressive Disclosure	Single-file skill with no bundle files, organized under clear section headers; the large popular-actions and proxy-flag tables could be split into reference files, which keeps it just short of a 5.	4 / 5
	Total	16 / 20 Passed

Description

62%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 concise and answers both what and when with an explicit 'Use when' clause, but it under-specifies the skill's full capability set and natural trigger terms. Expanding the trigger phrases would lift completeness and trigger-term quality.

Suggestions

List more concrete capabilities (e.g. send email, manage contacts and lists, manage templates, handle suppression/bounces) to raise specificity.

Add natural trigger synonyms such as 'email', 'contacts', 'templates', 'bounces', or 'suppression list' so users' phrasings match the skill.

Make the 'Use when' clause more concrete, e.g. 'Use when the user wants to send emails, manage SendGrid campaigns, contacts, templates, or suppression lists.'

Dimension	Reasoning	Score
Specificity	Names the SendGrid domain and one concrete action ('Manage Campaigns'), but stops short of listing the broader set of capabilities (contacts, templates, suppression, email send) covered by the skill.	3 / 5
Completeness	Both a 'what' ('Manage Campaigns') and an explicit 'when' ('Use when the user wants to interact with SendGrid data') are present, though the 'when' trigger is generic rather than listing concrete use cases.	4 / 5
Trigger Term Quality	Includes the natural keyword 'SendGrid' and 'Campaigns', but omits common variations and synonyms a user would say (emails, bounces, contacts, templates, suppression list).	3 / 5
Distinctiveness Conflict Risk	SendGrid is a specific named platform giving the skill a clear niche with minimal conflict risk, but the generic 'interact with SendGrid data' phrasing keeps it from a fully distinct trigger set.	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/sendgrid/SKILL.md
Commit: f484c82

Reviewed: 4 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.