webflow-automation
Automate Webflow CMS collections, site publishing, page management, asset uploads, and ecommerce orders via Rube MCP (Composio). Always search tools first for current schemas.
What this skill does
# Webflow Automation via Rube MCP
Automate Webflow operations including CMS collection management, site publishing, page inspection, asset uploads, and ecommerce order retrieval through Composio's Webflow toolkit.
## Prerequisites
- Rube MCP must be connected (RUBE_SEARCH_TOOLS available)
- Active Webflow connection via `RUBE_MANAGE_CONNECTIONS` with toolkit `webflow`
- 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 `webflow`
3. If connection is not ACTIVE, follow the returned auth link to complete Webflow OAuth
4. Confirm connection status shows ACTIVE before running any workflows
## Core Workflows
### 1. Manage CMS Collection Items
**When to use**: User wants to create, update, list, or delete items in Webflow CMS collections (blog posts, products, team members, etc.)
**Tool sequence**:
1. `WEBFLOW_LIST_WEBFLOW_SITES` - List sites to find the target site_id [Prerequisite]
2. `WEBFLOW_LIST_COLLECTIONS` - List all collections for the site [Prerequisite]
3. `WEBFLOW_GET_COLLECTION` - Get collection schema to find valid field slugs [Prerequisite for create/update]
4. `WEBFLOW_LIST_COLLECTION_ITEMS` - List existing items with filtering and pagination [Optional]
5. `WEBFLOW_GET_COLLECTION_ITEM` - Get a specific item's full details [Optional]
6. `WEBFLOW_CREATE_COLLECTION_ITEM` - Create a new item with field data [Required for creation]
7. `WEBFLOW_UPDATE_COLLECTION_ITEM` - Update an existing item's fields [Required for updates]
8. `WEBFLOW_DELETE_COLLECTION_ITEM` - Permanently remove an item [Optional]
9. `WEBFLOW_PUBLISH_SITE` - Publish changes to make them live [Optional]
**Key parameters for CREATE_COLLECTION_ITEM**:
- `collection_id`: 24-character hex string from LIST_COLLECTIONS
- `field_data`: Object with field slug keys (NOT display names); must include `name` and `slug`
- `field_data.name`: Display name for the item
- `field_data.slug`: URL-friendly identifier (lowercase, hyphens, no spaces)
- `is_draft`: Boolean to create as draft (default false)
**Key parameters for UPDATE_COLLECTION_ITEM**:
- `collection_id`: Collection identifier
- `item_id`: 24-character hex MongoDB ObjectId of the existing item
- `fields`: Object with field slug keys and new values
- `live`: Boolean to publish changes immediately (default false)
**Field value types**:
- Text/Email/Link/Date: string
- Number: integer or float
- Boolean: true/false
- Image: `{"url": "...", "alt": "...", "fileId": "..."}`
- Multi-reference: array of reference ID strings
- Multi-image: array of image objects
- Option: option ID string
**Pitfalls**:
- Field keys must use the exact field `slug` from the collection schema, NOT display names
- Always call `GET_COLLECTION` first to retrieve the schema and identify correct field slugs
- `CREATE_COLLECTION_ITEM` requires `name` and `slug` in `field_data`
- `UPDATE_COLLECTION_ITEM` cannot create new items; it requires a valid existing `item_id`
- `item_id` must be a 24-character hexadecimal MongoDB ObjectId
- Slug must be lowercase alphanumeric with hyphens: `^[a-z0-9]+(?:-[a-z0-9]+)*$`
- CMS items are staged; use `PUBLISH_SITE` or set `live: true` to push to production
### 2. Manage Sites and Publishing
**When to use**: User wants to list sites, inspect site configuration, or publish staged changes
**Tool sequence**:
1. `WEBFLOW_LIST_WEBFLOW_SITES` - List all accessible sites [Required]
2. `WEBFLOW_GET_SITE_INFO` - Get detailed site metadata including domains and settings [Optional]
3. `WEBFLOW_PUBLISH_SITE` - Deploy all staged changes to live site [Required for publishing]
**Key parameters for PUBLISH_SITE**:
- `site_id`: Site identifier from LIST_WEBFLOW_SITES
- `custom_domains`: Array of custom domain ID strings (from GET_SITE_INFO)
- `publish_to_webflow_subdomain`: Boolean to publish to `{shortName}.webflow.io`
- At least one of `custom_domains` or `publish_to_webflow_subdomain` must be specified
**Pitfalls**:
- `PUBLISH_SITE` republishes ALL staged changes for selected domains -- verify no unintended drafts are pending
- Rate limit: 1 successful publish per minute
- For sites without custom domains, must set `publish_to_webflow_subdomain: true`
- `custom_domains` expects domain IDs (hex strings), not domain names
- Publishing is a production action -- always confirm with the user first
### 3. Manage Pages
**When to use**: User wants to list pages, inspect page metadata, or examine page DOM structure
**Tool sequence**:
1. `WEBFLOW_LIST_WEBFLOW_SITES` - Find the target site_id [Prerequisite]
2. `WEBFLOW_LIST_PAGES` - List all pages for a site with pagination [Required]
3. `WEBFLOW_GET_PAGE` - Get detailed metadata for a specific page [Optional]
4. `WEBFLOW_GET_PAGE_DOM` - Get the DOM/content node structure of a static page [Optional]
**Key parameters**:
- `site_id`: Site identifier (required for list pages)
- `page_id`: 24-character hex page identifier
- `locale_id`: Optional locale filter for multi-language sites
- `limit`: Max results per page (max 100)
- `offset`: Pagination offset
**Pitfalls**:
- `LIST_PAGES` paginates via offset/limit; iterate when sites have many pages
- Page IDs are 24-character hex strings matching pattern `^[0-9a-fA-F]{24}$`
- `GET_PAGE_DOM` returns the node structure, not rendered HTML
- Pages include both static and CMS-driven pages
### 4. Upload Assets
**When to use**: User wants to upload images, files, or other assets to a Webflow site
**Tool sequence**:
1. `WEBFLOW_LIST_WEBFLOW_SITES` - Find the target site_id [Prerequisite]
2. `WEBFLOW_UPLOAD_ASSET` - Upload a file with base64-encoded content [Required]
**Key parameters**:
- `site_id`: Site identifier
- `file_name`: Name of the file (e.g., `"logo.png"`)
- `file_content`: Base64-encoded binary content of the file (NOT a placeholder or URL)
- `content_type`: MIME type (e.g., `"image/png"`, `"image/jpeg"`, `"application/pdf"`)
- `md5`: MD5 hash of the raw file bytes (32-character hex string)
- `asset_folder_id`: Optional folder placement
**Pitfalls**:
- `file_content` must be actual base64-encoded data, NOT a variable reference or placeholder
- `md5` must be computed from the raw bytes, not from the base64 string
- This is a two-step process internally: generates an S3 pre-signed URL, then uploads
- Large files may encounter timeouts; keep uploads reasonable in size
### 5. Manage Ecommerce Orders
**When to use**: User wants to view ecommerce orders from a Webflow site
**Tool sequence**:
1. `WEBFLOW_LIST_WEBFLOW_SITES` - Find the site with ecommerce enabled [Prerequisite]
2. `WEBFLOW_LIST_ORDERS` - List all orders with optional status filtering [Required]
3. `WEBFLOW_GET_ORDER` - Get detailed information for a specific order [Optional]
**Key parameters**:
- `site_id`: Site identifier (must have ecommerce enabled)
- `order_id`: Specific order identifier for detailed retrieval
- `status`: Filter orders by status
**Pitfalls**:
- Ecommerce must be enabled on the Webflow site for order endpoints to work
- Order endpoints are read-only; no create/update/delete for orders through these tools
## Common Patterns
### ID Resolution
Webflow uses 24-character hexadecimal IDs throughout:
- **Site ID**: `WEBFLOW_LIST_WEBFLOW_SITES` -- find by name, capture `id`
- **Collection ID**: `WEBFLOW_LIST_COLLECTIONS` with `site_id`
- **Item ID**: `WEBFLOW_LIST_COLLECTION_ITEMS` with `collection_id`
- **Page ID**: `WEBFLOW_LIST_PAGES` with `site_id`
- **Domain IDs**: `WEBFLOW_GET_SITE_INFO` -- found in `customDomains` array
- **Field slugs**: `WEBFLOW_GET_COLLECTION` -- found in collection `fields` array
### Pagination
Webflow uses offset-based pagination:
- `offset`: Starting index (0-based)
- `limit`: Items per page (max 100)
- Increment offset by limit until 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.