convertkit-automation
Automate ConvertKit (Kit) tasks via Rube MCP (Composio): manage subscribers, tags, broadcasts, and broadcast stats. Always search tools first for current schemas.
What this skill does
# ConvertKit (Kit) Automation via Rube MCP
Automate ConvertKit (now known as Kit) email marketing operations through Composio's Kit toolkit via Rube MCP.
## Prerequisites
- Rube MCP must be connected (RUBE_SEARCH_TOOLS available)
- Active Kit connection via `RUBE_MANAGE_CONNECTIONS` with toolkit `kit`
- Always call `RUBE_SEARCH_TOOLS` first to get current tool schemas
## Setup
**Get Rube MCP**: Add `https://rube.app/mcp` as an MCP server in your client configuration. No API keys needed — just add the endpoint and it works.
1. Verify Rube MCP is available by confirming `RUBE_SEARCH_TOOLS` responds
2. Call `RUBE_MANAGE_CONNECTIONS` with toolkit `kit`
3. If connection is not ACTIVE, follow the returned auth link to complete Kit authentication
4. Confirm connection status shows ACTIVE before running any workflows
## Core Workflows
### 1. List and Search Subscribers
**When to use**: User wants to browse, search, or filter email subscribers
**Tool sequence**:
1. `KIT_LIST_SUBSCRIBERS` - List subscribers with filters and pagination [Required]
**Key parameters**:
- `status`: Filter by status ('active' or 'inactive')
- `email_address`: Exact email to search for
- `created_after`/`created_before`: Date range filter (YYYY-MM-DD)
- `updated_after`/`updated_before`: Date range filter (YYYY-MM-DD)
- `sort_field`: Sort by 'id', 'cancelled_at', or 'updated_at'
- `sort_order`: 'asc' or 'desc'
- `per_page`: Results per page (min 1)
- `after`/`before`: Cursor strings for pagination
- `include_total_count`: Set to 'true' to get total subscriber count
**Pitfalls**:
- If `sort_field` is 'cancelled_at', the `status` must be set to 'cancelled'
- Date filters use YYYY-MM-DD format (no time component)
- `email_address` is an exact match; partial email search is not supported
- Pagination uses cursor-based approach with `after`/`before` cursor strings
- `include_total_count` is a string 'true', not a boolean
### 2. Manage Subscriber Tags
**When to use**: User wants to tag subscribers for segmentation
**Tool sequence**:
1. `KIT_LIST_SUBSCRIBERS` - Find subscriber ID by email [Prerequisite]
2. `KIT_TAG_SUBSCRIBER` - Associate a subscriber with a tag [Required]
3. `KIT_LIST_TAG_SUBSCRIBERS` - List subscribers for a specific tag [Optional]
**Key parameters for tagging**:
- `tag_id`: Numeric tag ID (required)
- `subscriber_id`: Numeric subscriber ID (required)
**Pitfalls**:
- Both `tag_id` and `subscriber_id` must be positive integers
- Tag IDs must reference existing tags; tags are created via the Kit web UI
- Tagging an already-tagged subscriber is idempotent (no error)
- Subscriber IDs are returned from LIST_SUBSCRIBERS; use `email_address` filter to find specific subscribers
### 3. Unsubscribe a Subscriber
**When to use**: User wants to unsubscribe a subscriber from all communications
**Tool sequence**:
1. `KIT_LIST_SUBSCRIBERS` - Find subscriber ID [Prerequisite]
2. `KIT_DELETE_SUBSCRIBER` - Unsubscribe the subscriber [Required]
**Key parameters**:
- `id`: Subscriber ID (required, positive integer)
**Pitfalls**:
- This permanently unsubscribes the subscriber from ALL email communications
- The subscriber's historical data is retained but they will no longer receive emails
- Operation is idempotent; unsubscribing an already-unsubscribed subscriber succeeds without error
- Returns empty response (HTTP 204 No Content) on success
- Subscriber ID must exist; non-existent IDs return 404
### 4. List and View Broadcasts
**When to use**: User wants to browse email broadcasts or get details of a specific one
**Tool sequence**:
1. `KIT_LIST_BROADCASTS` - List all broadcasts with pagination [Required]
2. `KIT_GET_BROADCAST` - Get detailed information for a specific broadcast [Optional]
3. `KIT_GET_BROADCAST_STATS` - Get performance statistics for a broadcast [Optional]
**Key parameters for listing**:
- `per_page`: Results per page (1-500)
- `after`/`before`: Cursor strings for pagination
- `include_total_count`: Set to 'true' for total count
**Key parameters for details**:
- `id`: Broadcast ID (required, positive integer)
**Pitfalls**:
- `per_page` max is 500 for broadcasts
- Broadcast stats are only available for sent broadcasts
- Draft broadcasts will not have stats
- Broadcast IDs are numeric integers
### 5. Delete a Broadcast
**When to use**: User wants to permanently remove a broadcast
**Tool sequence**:
1. `KIT_LIST_BROADCASTS` - Find the broadcast to delete [Prerequisite]
2. `KIT_GET_BROADCAST` - Verify it is the correct broadcast [Optional]
3. `KIT_DELETE_BROADCAST` - Permanently delete the broadcast [Required]
**Key parameters**:
- `id`: Broadcast ID (required)
**Pitfalls**:
- Deletion is permanent and cannot be undone
- Deleting a sent broadcast removes it but does not unsend the emails
- Confirm the broadcast ID before deleting
## Common Patterns
### Subscriber Lookup by Email
```
1. Call KIT_LIST_SUBSCRIBERS with email_address='[email protected]'
2. Extract subscriber ID from the response
3. Use ID for tagging, unsubscribing, or other operations
```
### Pagination
Kit uses cursor-based pagination:
- Check response for `after` cursor value
- Pass cursor as `after` parameter in next request
- Continue until no more cursor is returned
- Use `include_total_count: 'true'` to track progress
### Tag-Based Segmentation
```
1. Create tags in Kit web UI
2. Use KIT_TAG_SUBSCRIBER to assign tags to subscribers
3. Use KIT_LIST_TAG_SUBSCRIBERS to view subscribers per tag
```
## Known Pitfalls
**ID Formats**:
- Subscriber IDs: positive integers (e.g., 3887204736)
- Tag IDs: positive integers
- Broadcast IDs: positive integers
- All IDs are numeric, not strings
**Status Values**:
- Subscriber statuses: 'active', 'inactive', 'cancelled'
- Some operations are restricted by status (e.g., sorting by cancelled_at requires status='cancelled')
**String vs Boolean Parameters**:
- `include_total_count` is a string 'true', not a boolean true
- `sort_order` is a string enum: 'asc' or 'desc'
**Rate Limits**:
- Kit API has per-account rate limits
- Implement backoff on 429 responses
- Bulk operations should be paced appropriately
**Response Parsing**:
- Response data may be nested under `data` or `data.data`
- Parse defensively with fallback patterns
- Cursor values are opaque strings; use exactly as returned
## Quick Reference
| Task | Tool Slug | Key Params |
|------|-----------|------------|
| List subscribers | KIT_LIST_SUBSCRIBERS | status, email_address, per_page |
| Tag subscriber | KIT_TAG_SUBSCRIBER | tag_id, subscriber_id |
| List tag subscribers | KIT_LIST_TAG_SUBSCRIBERS | tag_id |
| Unsubscribe | KIT_DELETE_SUBSCRIBER | id |
| List broadcasts | KIT_LIST_BROADCASTS | per_page, after |
| Get broadcast | KIT_GET_BROADCAST | id |
| Get broadcast stats | KIT_GET_BROADCAST_STATS | id |
| Delete broadcast | KIT_DELETE_BROADCAST | id |
## When to Use
This skill is applicable to execute the workflow or actions described in the overview.
## Limitations
- Use this skill only when the task clearly matches the scope described above.
- Do not treat the output as a substitute for environment-specific validation, testing, or expert review.
- Stop and ask for clarification if required inputs, permissions, safety boundaries, or success criteria are missing.
Related in AI Agents
skill-development
IncludedComprehensive meta-skill for creating, managing, validating, auditing, and distributing Claude Code skills and slash commands (unified in v2.1.3+). Provides skill templates, creation workflows, validation patterns, audit checklists, naming conventions, YAML frontmatter guidance, progressive disclosure examples, and best practices lookup. Use when creating new skills, validating existing skills, auditing skill quality, understanding skill architecture, needing skill templates, learning about YAML frontmatter requirements, progressive disclosure patterns, tool restrictions (allowed-tools), skill composition, skill naming conventions, troubleshooting skill activation issues, creating custom slash commands, configuring command frontmatter, using command arguments ($ARGUMENTS, $1, $2), bash execution in commands, file references in commands, command namespacing, plugin commands, MCP slash commands, Skill tool configuration, or deciding between skills vs slash commands. Delegates to docs-management skill for official documentation.
reprompter
IncludedTransform messy prompts into well-structured, effective prompts — single or multi-agent. Use when: "reprompt", "reprompt this", "clean up this prompt", "structure my prompt", rough text needing XML tags and best practices, "reprompter teams", "repromptception", "run with quality", "smart run", "smart agents", multi-agent tasks, audits, parallel work, anything going to agent teams. Don't use when: simple Q&A, pure chat, immediate execution-only tasks. See "Don't Use When" section for details. Outputs: Structured XML/Markdown prompt, quality score (before/after), optional team brief + per-agent sub-prompts, agent team output files. Success criteria: Single mode quality score ≥ 7/10; Repromptception per-agent prompt quality score 8+/10; all required sections present, actionable and specific.
adaptive-compaction
IncludedAdaptive add-on policy and recovery layer that decides WHEN to compact, prune, snapshot, or fork -- replacing fixed-percent auto-compaction across Claude Code, Codex, and MCP-capable hosts. Trigger on auto-compact timing or damage: "when should I compact", "is it safe to compact now or start a fresh session", "auto-compact fires too early/mid-task", "switching to an unrelated task but the window still has space", "context rot", "answers get worse the longer the session runs", "the agent forgot the plan or my decisions after it summarized", "add a layer on top that manages context without changing the agent", raising autoCompactWindow to give the policy room, or installing/tuning a cross-tool compaction policy or PreCompact hook -- even when "compaction" is never said but the problem is context-window pressure or post-summarization memory loss. Do NOT use to summarize a conversation, build RAG, write a summarization prompt (decides WHEN not HOW), or answer max-context-length trivia.
agent-skill-creator
IncludedCreate cross-platform agent skills from workflow descriptions. Activates when users ask to create an agent, automate a repetitive workflow, create a custom skill, or need advanced agent creation. Triggers on phrases like create agent for, automate workflow, create skill for, every day I have to, daily I need to, turn process into agent, need to automate, create a cross-platform skill, validate this skill, export this skill, migrate this skill. Supports single skills, multi-agent suites, transcript processing, template-based creation, interactive configuration, cross-platform export, and spec validation.
llm-wiki
IncludedUse when building or maintaining a persistent personal knowledge base (second brain) in Obsidian where an LLM incrementally ingests sources, updates entity/concept pages, maintains cross-references, and keeps a synthesis current. Triggers include "second brain", "Obsidian wiki", "personal knowledge management", "ingest this paper/article/book", "build a research wiki", "compound knowledge", "Memex", or whenever the user wants knowledge to accumulate across sessions instead of being re-derived by RAG on every query.
skill-master
IncludedAgent Skills authoring, evaluation, and optimization. Create, edit, validate, benchmark, and improve skills following the agentskills.io specification. Use when designing SKILL.md files, structuring skill folders (references, scripts, assets), ingesting external documentation into skills, running trigger evals, benchmarking skill quality, optimizing descriptions, or performing blind A/B comparisons. Keywords: agentskills.io, SKILL.md, skill authoring, eval, benchmark, trigger optimization.