contentful-graphql-automation
by ComposioHQcontentful-graphql-automation helps agents run Contentful GraphQL workflows through Rube MCP. Learn setup requirements, connection checks, schema-first tool discovery, and practical usage patterns for safer automation.
This skill scores 67/100, which means it is acceptable for directory listing but should be presented as a lightweight Rube MCP workflow guide rather than a deeply self-contained automation package. Directory users get enough information to know when to install it and how an agent should begin, but the lack of supporting examples or assets limits confidence for complex Contentful GraphQL use cases.
- Valid skill frontmatter declares the required MCP dependency (`rube`) and gives a clear trigger: automating Contentful GraphQL tasks through Composio/Rube.
- Prerequisites and setup are explicit, including connecting `https://rube.app/mcp`, using `RUBE_MANAGE_CONNECTIONS`, and confirming an ACTIVE `contentful_graphql` connection.
- The skill repeatedly instructs agents to call `RUBE_SEARCH_TOOLS` first, which helps handle current schemas and reduces stale-tool assumptions.
- No support files, scripts, reference examples, or README are present beyond SKILL.md, so adoption depends on the agent using Rube’s live tool discovery correctly.
- Workflow guidance appears mostly pattern-based rather than providing many concrete Contentful GraphQL task examples, which may leave room for guesswork on specific operations.
Overview of contentful-graphql-automation skill
What contentful-graphql-automation does
contentful-graphql-automation is a Claude skill for running Contentful GraphQL operations through Composio’s Rube MCP toolkit. Its main value is not “writing GraphQL” in isolation; it guides the agent to discover the current contentful_graphql tool schema first, verify the Contentful connection, and then execute operations using the live MCP tools instead of guessing parameters.
Best-fit users and workflows
This skill is a good fit for teams using Contentful as a CMS and an AI client that supports MCP. Typical users want to automate content queries, inspect available GraphQL capabilities, build repeatable CMS workflows, or connect Contentful content operations to broader agentic workflows. It is especially relevant if you already use Rube MCP or Composio and want contentful-graphql-automation for Workflow Automation rather than a static prompt that only drafts query text.
Key differentiator: schema-first execution
The important behavior in the upstream skill is the “search tools first” rule. Before the agent calls any Contentful GraphQL action, it should use RUBE_SEARCH_TOOLS to retrieve current tool slugs, input schemas, execution plans, and pitfalls. This matters because MCP tool definitions can change, and Contentful spaces/environments often differ. The skill is most useful when accuracy depends on live tool discovery, not memorized API assumptions.
Adoption requirements to check first
You need Rube MCP available in your AI client and an active Contentful GraphQL connection through RUBE_MANAGE_CONNECTIONS with toolkit contentful_graphql. The repository path is composio-skills/contentful-graphql-automation, and the skill currently consists mainly of SKILL.md; there are no bundled scripts, rule folders, or reference examples to lean on. That makes the skill lightweight, but it also means your prompt must provide enough Contentful context.
How to Use contentful-graphql-automation skill
contentful-graphql-automation install and setup path
Install the skill from the Composio skills repository, for example:
npx skills add ComposioHQ/awesome-claude-skills --skill contentful-graphql-automation
Then configure Rube MCP in your client by adding:
https://rube.app/mcp
Before asking for any real Contentful operation, confirm that RUBE_SEARCH_TOOLS is available. Next, use RUBE_MANAGE_CONNECTIONS with toolkit contentful_graphql; if the connection is not ACTIVE, complete the returned authorization flow. Do not treat installation as complete until the MCP server responds and the Contentful GraphQL connection is active.
Inputs the skill needs for reliable usage
A weak request is: “Query Contentful for posts.” A stronger request gives the agent execution context:
- Contentful space or project context, if known
- environment, locale, content type, or collection name
- fields you need returned
- filters, limits, ordering, preview/published expectations
- whether the task is read-only or may modify configuration
- desired output format, such as JSON, Markdown table, CSV-like rows, or a saved workflow plan
Example prompt:
“Use contentful-graphql-automation to discover the current Contentful GraphQL tools with RUBE_SEARCH_TOOLS, verify the contentful_graphql connection, then query published English blog posts from the production environment. Return title, slug, publish date, author name, and SEO description for the 20 most recent entries. Show the tool schema you selected before execution and summarize any missing fields.”
Practical workflow for first run
Start by reading SKILL.md; it is the key source file and contains the operational sequence. In use, follow this pattern:
- Ask the agent to call
RUBE_SEARCH_TOOLSfor your specific Contentful GraphQL use case. - Review the returned tool slugs and schemas before execution.
- Confirm the Contentful connection through
RUBE_MANAGE_CONNECTIONS. - Run the selected tool with schema-valid inputs.
- Ask the agent to report the exact assumptions, filters, and returned fields.
This reduces the most common failure: the agent inventing GraphQL parameters or using an outdated schema.
Prompt pattern for Workflow Automation
For workflow automation, describe the end-to-end job, not just the query. For example:
“Use contentful-graphql-automation for a weekly content audit. Discover current tools first. Query all landing pages updated in the last 7 days, return URL slug, title, internal owner, updated date, and missing SEO fields. Group results by owner and produce a follow-up checklist. Do not make changes; read-only audit.”
This framing helps the skill choose tools, preserve safety boundaries, and return an output that can be used directly in an editorial or operations workflow.
contentful-graphql-automation skill FAQ
Is contentful-graphql-automation only for developers?
No, but it assumes someone can provide Contentful concepts such as content type, environment, locale, fields, or editorial goal. Non-developers can use it effectively for audits and content reporting if they describe the business outcome clearly. Developers will get more from it when they provide exact GraphQL expectations and validate schemas.
How is this better than a normal Contentful prompt?
A normal prompt may draft a plausible GraphQL query, but it cannot safely know the current Rube MCP tool schema or your active Contentful connection state. The contentful-graphql-automation skill adds an execution discipline: discover tools, check connection, then run schema-valid operations. That is the meaningful difference for automation.
When should I not use this skill?
Do not use it if your AI client cannot use MCP tools, if you do not have a Contentful GraphQL connection through Rube/Composio, or if you only need generic GraphQL learning material. It is also not a replacement for a full Contentful migration plan, access-control review, or custom application integration.
What files should I inspect before installing?
Inspect SKILL.md in the GitHub repository first. The current package is compact and does not include helper scripts, examples, or reference folders, so your install decision should be based on whether its MCP-first workflow matches your environment. If you need extensive bundled examples, expect to create your own prompt templates.
How to Improve contentful-graphql-automation skill
Improve contentful-graphql-automation results with better context
The skill performs best when you provide the same details a human Contentful operator would ask for: space/environment, content model names, field IDs, locale rules, preview versus published content, date ranges, and output format. If you do not know field IDs, say so and ask the agent to discover available fields before constructing the operation.
Common failure modes to prevent
The biggest risk is skipping RUBE_SEARCH_TOOLS and relying on assumed tool names or stale schemas. Another common issue is asking for “all content” without limits, filters, or pagination expectations. Avoid vague modification requests such as “clean up entries” unless you define read/write permissions, confirmation steps, and rollback expectations.
Iterate after the first output
After the first run, ask for a short execution review: which tool was selected, which schema fields were required, what assumptions were made, and what data was omitted. Then refine the next request with more precise filters or fields. This turns the skill from a one-off query helper into a repeatable Contentful operations workflow.
Useful enhancements for teams
Teams can improve adoption by creating internal prompt templates for common tasks: content audits, missing SEO metadata checks, localization coverage, recent-entry reports, and release-readiness reviews. Store the preferred content type names, field IDs, environments, and output formats in those templates so each contentful-graphql-automation usage starts with reliable context instead of rediscovery.