slackbot-automation
by ComposioHQslackbot-automation is a Claude skill for Slackbot workflows through Composio Rube MCP. It guides agents to search current tools, verify the Slackbot connection, and execute with live schemas.
This skill scores 68/100, which means it is acceptable for directory listing but should be presented as a lightweight Rube MCP workflow guide rather than a full Slackbot automation package. Directory users get enough clarity to know it is for Composio/Rube Slackbot operations and how an agent should begin, but adoption still depends on external MCP setup and runtime tool discovery.
- Valid skill frontmatter declares the required `rube` MCP and a clear Slackbot automation purpose.
- Prerequisites and setup steps specify checking `RUBE_SEARCH_TOOLS`, using `RUBE_MANAGE_CONNECTIONS`, and confirming an ACTIVE Slackbot connection before workflows.
- The skill repeatedly instructs agents to search tools first for current schemas, which improves triggerability and reduces stale tool-call assumptions.
- No support files, scripts, README, or install command are present; setup depends on users already knowing how to add and use the Rube MCP endpoint.
- Slackbot actions are handled through dynamic tool discovery rather than documented concrete end-to-end Slackbot examples, so agents may still need schema interpretation at runtime.
Overview of slackbot-automation skill
What slackbot-automation does
slackbot-automation is a Claude skill for running Slackbot workflows through Composio’s Rube MCP server. Instead of guessing Slackbot API shapes, the skill instructs the agent to discover the current available tools with RUBE_SEARCH_TOOLS, confirm the Slackbot connection with RUBE_MANAGE_CONNECTIONS, and then execute the selected workflow using the returned schema.
This makes the slackbot-automation skill most useful when your task depends on live Slackbot tool definitions, authentication state, or changing Composio toolkit schemas.
Best-fit users and workflows
Use slackbot-automation for Workflow Automation when you want an agent to operate inside a connected Slackbot environment rather than only draft instructions. Good fits include:
- Sending or managing Slackbot messages through approved tools
- Building repeatable Slackbot operations from a natural-language request
- Checking available Slackbot capabilities before committing to an automation path
- Running Slack-related workflows where schema freshness matters
It is best for users who already work with MCP-enabled AI clients and can connect Rube MCP. It is less useful if you only need general Slack copywriting, a Slack app architecture plan, or raw Slack API code.
Key differentiator: search tools before action
The main value of slackbot-automation is its “discover first, execute second” pattern. The skill explicitly requires the agent to call RUBE_SEARCH_TOOLS before attempting a task. That matters because Rube returns current tool slugs, input fields, execution plans, and pitfalls. For install decisions, this is the important signal: the skill is not a static prompt template; it is a lightweight operating procedure for safer live tool use.
How to Use slackbot-automation skill
slackbot-automation install context
Install the skill from the ComposioHQ skill collection:
npx skills add ComposioHQ/awesome-claude-skills --skill slackbot-automation
The upstream skill itself does not include extra scripts, resources, or a README; the main file to inspect is composio-skills/slackbot-automation/SKILL.md. Before expecting useful output, configure Rube MCP in your AI client by adding https://rube.app/mcp as an MCP server. The skill assumes these tools are available:
RUBE_SEARCH_TOOLSRUBE_MANAGE_CONNECTIONS- Rube execution tools returned by discovery
Then use RUBE_MANAGE_CONNECTIONS with toolkit slackbot and complete the returned auth flow if the connection is not ACTIVE.
Inputs the skill needs from you
For reliable slackbot-automation usage, provide the agent with the operational goal, target Slack context, constraints, and success criteria. Weak prompt: “Automate a Slackbot message.” Strong prompt:
“Use slackbot-automation to send a Slackbot update to the engineering channel after checking the active Slackbot connection. First discover current Rube Slackbot tools. The message should summarize deployment status, avoid tagging everyone, and ask the on-call engineer to confirm if errors appear. Show me the planned tool call before execution.”
This improves output because it tells the agent what to discover, what connection to verify, what safety constraints matter, and when to pause.
Recommended workflow
A practical slackbot-automation guide looks like this:
- Ask the agent to invoke the skill for a specific Slackbot task.
- Require
RUBE_SEARCH_TOOLSfirst, using your real use case as the query. - Confirm Slackbot connection status through
RUBE_MANAGE_CONNECTIONS. - Review the discovered tool slug and required input schema.
- Ask for a planned execution step if the action is sensitive.
- Execute only after required channel, message, user, or workflow fields are clear.
- Verify the result and capture the working pattern for reuse.
Do not ask the agent to invent parameters from memory. The whole point of the slackbot-automation install is to route the agent through live Rube discovery.
Files to read before first run
Read SKILL.md first because it contains the actual operating contract: prerequisites, setup, tool discovery, and core workflow pattern. There are no supporting scripts/, references/, resources/, rules/, README.md, or metadata.json files in the skill folder, so adoption depends on understanding that single file and the external Composio Slackbot toolkit documentation at composio.dev/toolkits/slackbot.
slackbot-automation skill FAQ
Is slackbot-automation enough without Rube MCP?
No. The skill requires Rube MCP. If RUBE_SEARCH_TOOLS is unavailable, the agent cannot follow the intended workflow. Treat Rube MCP connectivity and an active Slackbot connection as prerequisites, not optional enhancements.
How is this better than an ordinary Slack prompt?
An ordinary prompt can draft a message or describe Slack automation, but it cannot reliably inspect current Composio tool schemas. The slackbot-automation skill gives the agent a repeatable sequence: discover tools, validate connection, use the returned schema, then execute. That reduces guesswork when tool definitions or required fields change.
Is this beginner-friendly?
It is beginner-friendly for users already comfortable with MCP-enabled clients, but not for someone who has never configured an MCP server. The skill’s content is concise and procedural, yet it assumes you can add an MCP endpoint, authenticate a toolkit connection, and understand the difference between planning and executing a tool call.
When should I not use it?
Do not use slackbot-automation for generic Slack strategy, bot design documents, or code-only Slack app development. Also avoid it when the Slackbot connection cannot be authorized, when your organization prohibits AI-triggered Slack actions, or when the task requires manual human approval before any message or workflow execution.
How to Improve slackbot-automation skill
Improve slackbot-automation prompts with execution detail
Better results come from giving the agent enough context to choose and fill the right Rube tool. Include:
- Target channel, user, or Slackbot destination
- Desired action and exact message content where relevant
- Timing or trigger conditions
- Approval requirements before execution
- Formatting constraints such as no mass mentions
- What verification should look like after completion
A strong request is specific but still lets the skill discover the latest schema instead of hardcoding old assumptions.
Common failure modes to prevent
The most common failure is skipping tool discovery and trying to call a guessed Slackbot tool. Prevent this by explicitly saying: “Use RUBE_SEARCH_TOOLS first and base all fields on the returned schema.” Another failure is attempting execution before the Slackbot connection is ACTIVE; ask the agent to check RUBE_MANAGE_CONNECTIONS and stop if auth is incomplete. A third failure is ambiguous Slack context, such as “send it to the team,” which can lead to the wrong destination.
Iterate after the first output
After the first run, ask the agent to summarize which tool slug was used, which fields were required, and which inputs were missing or inferred. Save that as a reusable internal prompt pattern for future slackbot-automation usage. For recurring workflows, refine the prompt into a checklist: discovery query, connection check, required Slack fields, review step, execution step, and verification step.
Repository-level improvement ideas
The skill would be stronger with a short README.md, example prompts for common Slackbot tasks, and a small troubleshooting section for inactive connections or missing MCP tools. If you maintain a fork, consider adding safe-use guidance for approval-sensitive actions, sample discovery queries, and examples showing how to transform vague Slack requests into schema-ready tool calls.