sendgrid-automation

Automate SendGrid email operations including sending emails, managing contacts/lists, sender identities, templates, and analytics via Rube MCP (Composio). Always search tools first for current schemas.

1.86x

Quality

58%

Does it follow best practices?

Impact

97%

1.86x

Average score across 3 eval scenarios

Securityby

Advisory

Suggest reviewing before use

Optimize this skill with Tessl

npx tessl skill review --optimize ./plugins/all-skills/skills/sendgrid-automation/SKILL.md

Quality

Discovery

67%

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 does a good job listing specific SendGrid capabilities and is highly distinctive due to the SendGrid branding. However, it lacks an explicit 'Use when...' clause which caps completeness, and the trigger terms could be broader to capture more natural user language patterns around email operations.

Suggestions

Add an explicit 'Use when...' clause, e.g., 'Use when the user asks about SendGrid, sending transactional or marketing emails, managing email contacts or mailing lists, or checking email delivery analytics.'

Include more natural user-facing trigger terms like 'send an email', 'email campaign', 'mailing list', 'email delivery', 'transactional email' to improve keyword coverage.

Dimension	Reasoning	Score
Specificity	Lists multiple specific concrete actions: sending emails, managing contacts/lists, sender identities, templates, and analytics. Also specifies the tooling mechanism (Rube MCP/Composio) and includes a procedural note about searching tools first.	3 / 3
Completeness	Clearly answers 'what does this do' with specific SendGrid operations, but lacks an explicit 'Use when...' clause or equivalent trigger guidance. The 'when' is only implied by the domain (SendGrid email operations).	2 / 3
Trigger Term Quality	Includes good keywords like 'SendGrid', 'email', 'contacts', 'lists', 'templates', 'analytics', but misses common user variations like 'send an email', 'email campaign', 'mailing list', 'transactional email', or 'email API'. The term 'Rube MCP (Composio)' is technical jargon unlikely to be used by most users.	2 / 3
Distinctiveness Conflict Risk	The explicit mention of 'SendGrid' creates a very clear niche that is unlikely to conflict with other email or communication skills. The combination of SendGrid-specific operations and the Composio tooling makes this highly distinctive.	3 / 3
	Total	10 / 12 Passed

Implementation

50%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

This is a thorough SendGrid automation skill with strong domain-specific knowledge, particularly around pitfalls (send_at scheduling behavior, legacy vs marketing API distinctions, async operations). Its main weaknesses are significant content repetition between sections, lack of concrete executable examples showing actual tool call payloads, and missing explicit validation checkpoints in multi-step workflows. The document would benefit from deduplication, at least one end-to-end example with actual parameters, and splitting into multiple files.

Suggestions

Add at least one concrete, end-to-end example showing actual MCP tool call parameters (e.g., a complete SENDGRID_CREATE_SINGLE_SEND invocation with realistic values) to improve actionability.

Deduplicate pitfalls — consolidate all pitfall information into the 'Known Pitfalls' section and reference it from individual workflows instead of repeating the same warnings (async operations, UUID formats, send_at behavior, legacy API) in multiple places.

Add explicit validation/verification steps within workflow sequences, e.g., after step 5 in the campaign workflow: 'Verify: Retrieve the created Single Send to confirm it was created correctly before scheduling.'

Split the quick reference table and detailed per-workflow sections into separate bundle files (e.g., REFERENCE.md, WORKFLOWS.md) to keep SKILL.md as a concise overview with navigation links.

Dimension	Reasoning	Score
Conciseness	The skill is comprehensive but verbose — there's significant repetition between the per-workflow 'Pitfalls' sections and the consolidated 'Known Pitfalls' section (e.g., async contact operations, UUID formats, send_at behavior, legacy API warnings are all stated multiple times). The quick reference table also partially duplicates the workflow tool sequences. However, the content is domain-specific knowledge Claude wouldn't inherently know, so the verbosity is in structure rather than explaining obvious concepts.	2 / 3
Actionability	The skill provides specific tool names, parameter names with double-underscore notation, and clear tool sequences, which is highly actionable for MCP tool invocation. However, there are no executable code examples or concrete tool call examples showing actual JSON payloads or MCP invocations — everything remains at the level of parameter listings and descriptions rather than copy-paste-ready examples. A concrete example of a full SENDGRID_CREATE_SINGLE_SEND call with actual parameters would significantly improve actionability.	2 / 3
Workflow Clarity	Workflows are well-sequenced with clear step ordering and labeled as [Required], [Optional], [Prerequisite]. However, validation checkpoints are largely missing — for example, after creating a Single Send there's no explicit verification step, and the async contact operations mention waiting 10-30 seconds but don't include an explicit 'verify before proceeding' checkpoint in the numbered workflow steps. The destructive operation (REMOVE_LIST_AND_OPTIONAL_CONTACTS) mentions requiring confirmation but lacks a formal validation loop.	2 / 3
Progressive Disclosure	The content is well-organized with clear section headers and a logical progression from setup to workflows to common patterns to pitfalls. However, at ~250+ lines this is a monolithic document that would benefit from splitting detailed workflow sections or the quick reference table into separate files. There's one external link (Composio toolkit docs) but no bundle files to offload the extensive per-workflow details.	2 / 3
	Total	8 / 12 Passed

Validation

90%

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 — 10 / 11 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	10 / 11 Passed

Repository: davepoon/buildwithclaude
Commit: c911a92

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.