bunnycdn-automation
by ComposioHQbunnycdn-automation is a Claude skill for Bunnycdn workflow automation through Composio Rube MCP. It guides agents to install/setup Rube MCP, verify the Bunnycdn connection, search current tool schemas first, and run CDN tasks safely.
This skill scores 68/100, which means it is acceptable to list but should be presented as a lightweight Rube MCP integration guide rather than a full Bunnycdn operations playbook. Directory users get enough trigger and setup clarity to decide whether they use Rube/Composio for Bunnycdn automation, but should expect limited built-in workflow depth and reliance on live tool discovery.
- Valid frontmatter clearly declares the skill name, Bunnycdn automation purpose, and required Rube MCP dependency.
- Prerequisites and setup steps explain that Rube MCP must be connected, the Bunnycdn toolkit connection must be ACTIVE, and RUBE_SEARCH_TOOLS should be called first for current schemas.
- The skill gives an operational pattern for tool discovery and connection checking, which should help an agent avoid guessing tool names or stale schemas.
- No support files, scripts, references, or README are present beyond a single SKILL.md, so adoption depends entirely on the embedded instructions and external Rube/Composio tooling.
- The workflow guidance appears mostly generic around RUBE_SEARCH_TOOLS and RUBE_MANAGE_CONNECTIONS rather than providing many concrete Bunnycdn-specific task examples or edge-case procedures.
Overview of bunnycdn-automation skill
What bunnycdn-automation does
bunnycdn-automation is a Claude skill for operating Bunnycdn through Composio’s Rube MCP toolkit. It helps an agent discover current Bunnycdn tool schemas, verify the account connection, and run CDN-related actions with less guesswork than a generic “use the API” prompt.
The most important behavior is not a fixed command list: the skill instructs the agent to call RUBE_SEARCH_TOOLS first, because Composio tool names and schemas can change. That makes the bunnycdn-automation skill useful when you want live tool discovery before executing workflow automation.
Best fit for Workflow Automation users
This skill is a good fit if you already use MCP-enabled agents and want Bunnycdn operations handled inside a broader workflow, such as CDN setup, content delivery checks, pull zone management, cache-related actions, or account-level operational tasks supported by the current Composio Bunnycdn toolkit.
It is especially relevant for users who prefer natural-language operations but still need the agent to respect connection state, tool schemas, and execution order.
Key adoption requirements
Before installing, confirm that your client can use MCP tools and that Rube MCP is available. The skill requires:
RUBE_SEARCH_TOOLSfor tool discoveryRUBE_MANAGE_CONNECTIONSfor Bunnycdn authentication status- An active Bunnycdn connection through the
bunnycdntoolkit - Willingness to review tool schemas before execution, not assume parameters
This is not a standalone Bunnycdn SDK, CLI wrapper, or static API reference. Its value comes from coordinating Rube MCP calls correctly.
How to Use bunnycdn-automation skill
bunnycdn-automation install and setup path
Install the skill from the Composio skills repository:
npx skills add ComposioHQ/awesome-claude-skills --skill bunnycdn-automation
Then add Rube MCP to your MCP-capable client using:
https://rube.app/mcp
After installation, verify that RUBE_SEARCH_TOOLS is visible in your tool list. Next, use RUBE_MANAGE_CONNECTIONS with toolkit bunnycdn. If the connection is not ACTIVE, follow the returned authorization link and confirm the status before asking the agent to perform Bunnycdn work.
Inputs the skill needs from you
For reliable bunnycdn-automation usage, give the agent the business goal, target Bunnycdn resource, desired safety level, and any known identifiers. A weak prompt is:
Purge my Bunnycdn cache.
A stronger prompt is:
Use bunnycdn-automation to discover current Bunnycdn tools first. Check my Bunnycdn connection status. If active, find the available cache purge or zone-related tools and propose the exact action before executing. Target pull zone
example-site-production. Do not modify unrelated zones.
This improves output because the agent can search schemas, avoid stale assumptions, and scope execution to the right Bunnycdn object.
Recommended workflow for real tasks
A practical bunnycdn-automation guide should follow this sequence:
- Ask the agent to call
RUBE_SEARCH_TOOLSfor the specific Bunnycdn use case. - Ask it to summarize matching tool slugs, required inputs, and risks.
- Confirm the Bunnycdn connection with
RUBE_MANAGE_CONNECTIONS. - Provide or confirm resource identifiers such as zone names, IDs, hostnames, or paths.
- Request a dry-run style plan before any mutating operation.
- Approve execution only after the agent maps your goal to the discovered schema.
For repository review, read composio-skills/bunnycdn-automation/SKILL.md first. There are no extra scripts, references, or metadata files in this skill directory, so SKILL.md is the authoritative source.
bunnycdn-automation skill FAQ
Is bunnycdn-automation better than an ordinary prompt?
Yes, when the task depends on live MCP tools. A normal prompt may hallucinate Bunnycdn API fields or use outdated assumptions. The bunnycdn-automation skill explicitly tells the agent to discover tools first, inspect current schemas, and manage the Bunnycdn connection through Rube MCP before execution.
Do I need Bunnycdn API keys?
The skill’s documented setup uses Rube MCP and Composio connection management rather than asking you to paste API keys into the prompt. You still need an authorized Bunnycdn connection. If RUBE_MANAGE_CONNECTIONS reports that the bunnycdn toolkit is inactive, authentication must be completed before workflows can run.
When should I not use this skill?
Do not use bunnycdn-automation if you need offline documentation, direct SDK development, Terraform-style infrastructure as code, or a guaranteed fixed list of Bunnycdn operations. It is also a poor fit if your agent environment cannot call MCP tools. The skill depends on live Rube MCP availability and current Composio toolkit schemas.
How to Improve bunnycdn-automation skill
Improve bunnycdn-automation prompts with scoped context
The fastest way to improve results is to replace broad requests with scoped operating context. Include:
- Environment: production, staging, or test
- Target: pull zone, storage zone, hostname, path, or account area
- Intent: inspect, create, update, purge, verify, or troubleshoot
- Safety rule: ask before mutating, avoid unrelated zones, summarize schema first
- Success criteria: what output proves the task is complete
Example:
Use bunnycdn-automation for Workflow Automation. Discover current Bunnycdn tools for pull zone inspection, verify my connection, then list the available read-only actions for zone
docs-cdn. Do not make changes.
Avoid common failure modes
The main failure mode is skipping tool discovery. If the agent jumps directly to a Bunnycdn action, redirect it: “Call RUBE_SEARCH_TOOLS first and show the schema you plan to use.” Another issue is vague resource naming. Bunnycdn accounts can contain multiple zones or hostnames, so provide IDs or ask the agent to list candidates before choosing.
For destructive or broad operations, require a confirmation step. Cache purges, zone updates, and security-related changes should be treated as mutating actions even when they sound routine.
Iterate after the first output
After the first plan, improve the result by asking the agent to compare available tools, identify required versus optional fields, and explain what it cannot verify. If execution fails, paste the tool error back into the conversation and ask the agent to re-run discovery for the same use case. This keeps bunnycdn-automation aligned with current Rube MCP schemas instead of relying on stale assumptions.