convertkit-automation

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

Install with Tessl CLI

npx tessl i github:Lingjie-chen/MT5 --skill convertkit-automation

What are skills?

1.16x

Quality

65%

Does it follow best practices?

Impact

83%

1.16x

Average score across 3 eval scenarios

Optimize this skill with Tessl

npx tessl skill review --optimize ./.trae/skills/convertkit-automation/SKILL.md

SKILL.md

Review

Evals

Evaluation results

85%

23%

Full Subscriber Export for Campaign Analysis

Subscriber pagination and connection setup

Criteria

Without context

With context

RUBE_SEARCH_TOOLS first

RUBE_MANAGE_CONNECTIONS call

100%

Active status check before proceeding

70%

Status filter value

100%

include_total_count as string

100%

Cursor-based pagination loop

100%

Cursor used as-is

100%

Defensive response parsing

50%

100%

Uses KIT_LIST_SUBSCRIBERS tool

100%

Output file written

100%

Without context: $1.0462 · 3m 22s · 33 turns · 89 in / 10,541 out tokens

With context: $0.4180 · 1m 50s · 18 turns · 21 in / 6,295 out tokens

78%

11%

Webinar Attendee Follow-Up Tagging

Email-based subscriber tagging workflow

Criteria

Without context

With context

RUBE_SEARCH_TOOLS first

RUBE_MANAGE_CONNECTIONS setup

Lookup before tag: tool sequence

66%

100%

Exact email lookup parameter

100%

Subscriber ID extracted from response

100%

Numeric IDs for tagging

66%

83%

No tag creation via API

100%

Handles subscriber not found

100%

Uses KIT_TAG_SUBSCRIBER tool

42%

100%

Results output file

100%

Without context: $0.2189 · 1m 13s · 13 turns · 66 in / 4,325 out tokens

With context: $0.3867 · 1m 29s · 18 turns · 429 in / 5,206 out tokens

86%

Broadcast Performance Audit and Draft Cleanup

Broadcast analytics and rate limit handling

Criteria

Without context

With context

RUBE_SEARCH_TOOLS first

RUBE_MANAGE_CONNECTIONS setup

25%

per_page set to 500

100%

Stats only for sent broadcasts

100%

Draft detection logic

100%

Broadcast ID confirmed before delete

100%

Rate-limit backoff on 429

100%

Defensive response parsing

100%

Broadcast pagination

100%

Output files produced

100%

Without context: $1.6262 · 6m 54s · 68 turns · 251 in / 23,068 out tokens

With context: $0.5780 · 2m 34s · 20 turns · 25 in / 9,824 out tokens

Evaluated: 3 days ago
Agent: Claude Code
Model: Claude Sonnet 4.6

Table of Contents

Full Subscriber Export for Campaign Analysis Webinar Attendee Follow-Up Tagging Broadcast Performance Audit and Draft Cleanup

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.