convertkit-automation

Automate ConvertKit (Kit) tasks via Rube MCP (Composio): manage subscribers, tags, broadcasts, and broadcast stats. Always search tools first for current schemas.

1.16x

Quality

—

Does it follow best practices?

Impact

83%

1.16x

Average score across 3 eval scenarios

Securityby

Advisory

Suggest reviewing before use

Quality

Content

65%

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

A concrete, well-structured MCP automation skill that adds genuinely Kit-specific knowledge Claude lacks. Its main weaknesses are duplicated pitfall content, a missing verification checkpoint before the permanent unsubscribe operation, and an absence of progressive disclosure to external files.

Suggestions

De-duplicate the pitfalls: keep concrete gotchas either inline per workflow or in the consolidated 'Known Pitfalls' section, not both, to tighten conciseness.

Add an explicit verification checkpoint to the unsubscribe workflow (e.g. confirm the email/ID matches the intended subscriber, or confirm with the user) before the irreversible KIT_DELETE_SUBSCRIBER call.

Move the detailed per-tool parameter reference and consolidated pitfalls into a separate reference file (e.g. REFERENCE.md) linked from the overview to improve progressive disclosure.

Dimension	Reasoning	Score
Conciseness	Mostly efficient and entirely Kit-specific (cursor pagination, string-vs-boolean quirks, idempotency), but pitfalls are duplicated between the inline per-workflow sections and the consolidated 'Known Pitfalls' block (e.g. "include_total_count is a string 'true'", cursor handling, ID formats), which could be tightened.	2 / 3
Actionability	Names exact tool slugs (KIT_LIST_SUBSCRIBERS, KIT_DELETE_SUBSCRIBER, etc.) with complete parameter lists, types, formats, and constrained values ('active'/'inactive', YYYY-MM-DD, per_page max 500), giving copy-paste-ready tool-call guidance for an instruction-only MCP skill.	3 / 3
Workflow Clarity	Sequences are explicit with [Prerequisite]/[Required]/[Optional] tags and the Setup section has validation checkpoints (confirm RUBE_SEARCH_TOOLS responds, confirm ACTIVE), but the destructive, irreversible unsubscribe workflow lacks an explicit pre-destruction verification step, capping it at 2 per the destructive-operations guideline.	2 / 3
Progressive Disclosure	The file is well-organized with clear sections and a Quick Reference table, but it is a single ~200-line monolith with no external references; detailed per-tool parameter docs and the consolidated Known Pitfalls could be split into separate reference files.	2 / 3
	Total	9 / 12 Passed

Description

82%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A specific, distinctive, third-person description that names concrete capabilities and natural trigger terms. Its only gap is the missing explicit 'when to use' trigger clause, which leaves completeness at 2.

Suggestions

Append an explicit trigger clause such as 'Use when the user asks to manage ConvertKit/Kit subscribers, tags, or broadcasts' to raise completeness from 2 to 3.

Dimension	Reasoning	Score
Specificity	It lists multiple concrete actions — "manage subscribers, tags, broadcasts, and broadcast stats" — matching the score-3 anchor that enumerates specific capabilities rather than vague language.	3 / 3
Completeness	It clearly answers WHAT the skill does, but there is no "Use when..." clause or equivalent explicit trigger guidance for WHEN Claude should invoke it, which caps completeness at 2 per the rubric guideline.	2 / 3
Trigger Term Quality	It includes natural, platform-specific terms a user would say — "ConvertKit", "Kit", "subscribers", "tags", "broadcasts" — giving good coverage of the vocabulary users actually use.	3 / 3
Distinctiveness Conflict Risk	The niche is tightly scoped to "ConvertKit (Kit)" via "Rube MCP (Composio)", making it clearly distinguishable and unlikely to trigger for the wrong skill.	3 / 3
	Total	11 / 12 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: davepoon/buildwithclaude
Commit: 366e45b

Reviewed: 1 day 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.