CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

convertkit-automation

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

Quality

71%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./skills/convertkit-automation/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

61%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 well-structured and highly actionable, with exact tool slugs, typed parameters, pitfalls, and a quick-reference table, but it is held back by duplicated pitfall content, a vacuous closing section, and missing validation checkpoints on destructive operations (permanent unsubscribe, broadcast deletion). Consolidating the repeated pitfalls and adding explicit verify-before-delete steps would lift both conciseness and workflow clarity.

Suggestions

Add an explicit verification/confirmation checkpoint before destructive operations (e.g., re-fetch the subscriber via KIT_LIST_SUBSCRIBERS and confirm with the user before KIT_DELETE_SUBSCRIBER, and handle 404 with a re-lookup), including error-recovery feedback loops.

Deduplicate the pitfalls repeated between the workflow sections and the 'Known Pitfalls' section (include_total_count string, cursor pagination, cancelled_at/status coupling), stating each fact once.

Remove or rewrite the vacuous 'When to Use' closing section, replacing it with genuine trigger guidance or deleting it in favor of the per-workflow 'When to use' lines.

DimensionReasoningScore

Conciseness

The body is dense and free of concept explanations Claude already knows, but it is noticeably redundant: pitfalls like 'include_total_count is a string true', cursor pagination, and the cancelled_at/status coupling are stated both in workflow sections and again in 'Known Pitfalls', and the closing 'When to Use' section ('This skill is applicable to execute the workflow or actions described in the overview') is vacuous padding. It fits 'mostly efficient but could be tightened' better than the minor-trimming level 4.

3 / 5

Actionability

Concrete, executable guidance throughout: exact tool slugs (KIT_LIST_SUBSCRIBERS, KIT_TAG_SUBSCRIBER, KIT_DELETE_BROADCAST), parameter names with types and formats ('include_total_count is a string true', 'YYYY-MM-DD'), and a Quick Reference table mapping tasks to tools. Not 5 because the Common Patterns blocks are step descriptions rather than copy-paste-ready example calls with actual argument values.

4 / 5

Workflow Clarity

Each workflow has a clear 'When to use', sequenced tool calls with [Required]/[Optional]/[Prerequisite] markers, and setup includes a validation checkpoint ('Confirm connection status shows ACTIVE'). However, the skill includes destructive operations — permanent unsubscribe (KIT_DELETE_SUBSCRIBER) and permanent broadcast deletion — and the unsubscribe workflow has no explicit verify-before-delete checkpoint or error-recovery loop, so per the destructive-operation cap workflow clarity cannot exceed 3.

3 / 5

Progressive Disclosure

A single self-contained SKILL.md (~190 lines) with well-organized sections (Prerequisites, Setup, five numbered workflows, Common Patterns, Known Pitfalls, Quick Reference) and no nested references. Structure and navigation are good with only minor gaps — the per-tool parameter detail and duplicated pitfall lists could be split into a reference file to keep the overview leaner, which keeps it below 5.

4 / 5

Total

14

/

20

Passed

Description

70%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 clearly states what the skill does within a distinctive niche, but it entirely lacks a 'when to use' trigger clause, and its action verbs ('manage') are generic despite enumerating the right capability areas. Adding an explicit 'Use when...' sentence with natural trigger phrases (email marketing, newsletters, unsubscribe) would raise both completeness and trigger quality.

Suggestions

Add an explicit trigger clause, e.g. 'Use when the user mentions ConvertKit, Kit, email subscribers, tags, broadcasts, or email marketing automation.'

Replace the generic verb 'manage' with the concrete operations the skill supports (list/search subscribers, tag subscribers, unsubscribe, list/view/delete broadcasts, get broadcast stats).

Include common user synonyms such as 'newsletter', 'email list', and 'unsubscribe' as trigger terms.

DimensionReasoningScore

Specificity

The description enumerates several concrete capability areas — 'manage subscribers, tags, broadcasts, and broadcast stats' — within a named domain (ConvertKit/Kit via Rube MCP). It falls short of 5 because the verb 'manage' is generic and finer actions (tag/unsubscribe/delete, connection setup) are not named, and above 3 because it covers more than 1-2 specific action areas.

4 / 5

Completeness

The 'what' is clear ('Automate ConvertKit (Kit) tasks via Rube MCP (Composio): manage subscribers, tags, broadcasts, and broadcast stats'), but there is no 'Use when...' clause or equivalent explicit trigger guidance, capping completeness at 3 per the judging guidelines.

3 / 5

Trigger Term Quality

Includes natural user terms 'ConvertKit (Kit)', 'subscribers', 'tags', 'broadcasts', and 'broadcast stats', with the product's current and former names covered. Not 5 because common user phrasings like 'email marketing', 'newsletter', 'email list', and 'unsubscribe' are absent.

4 / 5

Distinctiveness Conflict Risk

'ConvertKit (Kit)' plus 'Rube MCP (Composio)' names a specific niche SaaS integration; a user mentioning these terms unambiguously means this skill, so conflict risk with other skills is minimal.

5 / 5

Total

16

/

20

Passed

Validation

93%

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

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository

administrakt0r/AI-Agents-Safe-Coding-Skills

Path

skills/convertkit-automation/SKILL.md

Reviewed

Table of Contents

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.