happy-scribe-automation
by ComposioHQhappy-scribe-automation helps Claude run Happy Scribe workflows through Composio Rube MCP. Learn setup needs, connection checks, tool discovery, and safe usage patterns for transcription, subtitles, exports, and project automation.
This skill scores 64/100, which means it is acceptable for directory listing but should be presented as a lightweight connector-oriented skill rather than a complete Happy Scribe automation playbook. Directory users get enough information to trigger it and set up the required Rube/Happy Scribe connection, but should expect to discover exact tools and schemas at runtime.
- Valid skill metadata with a clear trigger: automate Happy Scribe tasks through Rube MCP/Composio.
- Prerequisites and setup steps identify required Rube MCP access, Happy Scribe connection management, and ACTIVE connection verification.
- Strong operational guardrail to call RUBE_SEARCH_TOOLS first for current tool schemas, reducing risk from stale API assumptions.
- No support files, scripts, examples, or reference material are included beyond SKILL.md, so users must rely on Rube tool discovery at runtime.
- The documented workflow is mostly a generic Composio/Rube pattern rather than concrete Happy Scribe task recipes, which limits install-decision specificity.
Overview of happy-scribe-automation skill
What happy-scribe-automation does
happy-scribe-automation is a Claude skill for running Happy Scribe workflows through Composio’s Rube MCP server. It helps an agent discover the current Happy Scribe tool schemas, verify the user’s connection, and then execute transcription, subtitle, export, or project-management actions with less guesswork than a generic prompt.
The key behavior is not “assume the API shape.” The skill explicitly instructs the agent to call RUBE_SEARCH_TOOLS first, because Rube MCP tool names, fields, and execution plans can change.
Best fit for Workflow Automation users
This skill is a good fit if you already use Claude with MCP and want Happy Scribe tasks embedded in a broader workflow: processing uploaded media, checking transcript status, exporting subtitles, or handing results to another tool. It is especially useful for teams that run repeatable content operations and want the agent to verify tool availability before taking action.
It is less useful if you only need a one-off transcript and prefer working directly in the Happy Scribe web interface.
What makes the skill different
The most important differentiator is the discovery-first pattern. Instead of hardcoding Happy Scribe operations, the happy-scribe-automation skill relies on Rube MCP to return the current Happy Scribe toolkit schema, required fields, and pitfalls. That makes it more resilient for automation than prompts that guess endpoint names or request formats.
Adoption requirements to check first
Before installing, confirm that your AI client supports MCP servers and that you can add https://rube.app/mcp. You also need an active Happy Scribe connection through RUBE_MANAGE_CONNECTIONS using the happy_scribe toolkit. If the connection is not active, the agent must pause and send you through the returned authorization flow before running workflows.
How to Use happy-scribe-automation skill
happy-scribe-automation install context
Install the skill from the Composio skill collection:
npx skills add ComposioHQ/awesome-claude-skills --skill happy-scribe-automation
Then configure Rube MCP in your client by adding this MCP server endpoint:
https://rube.app/mcp
The upstream skill contains only SKILL.md, so read that file first. There are no companion scripts, references, or rule folders to inspect. The practical setup path is: confirm RUBE_SEARCH_TOOLS is available, run RUBE_MANAGE_CONNECTIONS for toolkit happy_scribe, complete auth if needed, and only then ask the agent to perform Happy Scribe work.
Inputs the skill needs from you
For reliable happy-scribe-automation usage, provide the job goal, media source, target language, output format, and any deadline or naming convention. If you want exports, specify whether you need transcript text, subtitles, captions, or another format returned by the discovered tools.
Weak prompt:
Transcribe this video with Happy Scribe.
Stronger prompt:
Use happy-scribe-automation for Workflow Automation. Discover the current Happy Scribe tools first, confirm my
happy_scribeconnection is ACTIVE, then create a transcription job for the uploaded Spanish interview. When complete, export an English transcript and SRT subtitles. Use the project namecustomer-story-q3and tell me any fields you need before execution.
This works better because it gives the agent a goal, connection requirement, language/output expectations, and a permission boundary.
Recommended workflow pattern
A good happy-scribe-automation guide follows four steps:
- Search tools with
RUBE_SEARCH_TOOLSfor the exact Happy Scribe task. - Check the
happy_scribeconnection withRUBE_MANAGE_CONNECTIONS. - Execute the tool using only the schema returned by discovery.
- Report job IDs, status, next actions, and any export links or missing fields.
Ask the agent to keep the same Rube session when possible so tool discovery and execution context stay aligned.
Practical prompt tips for better results
Mention whether the task is create, monitor, update, list, export, or delete. Happy Scribe workflows often depend on IDs, file locations, language codes, and export formats, so provide them upfront when known. If the media is not yet available to the agent, ask it to discover the required upload or source-field options before attempting execution.
happy-scribe-automation skill FAQ
Is happy-scribe-automation enough without Rube MCP?
No. The skill requires Rube MCP and depends on RUBE_SEARCH_TOOLS and RUBE_MANAGE_CONNECTIONS. Without Rube MCP connected, the agent can explain the workflow but cannot reliably execute Happy Scribe automation.
Why not just ask Claude to use Happy Scribe?
A normal prompt may invent fields, skip authentication checks, or assume old API behavior. happy-scribe-automation is useful because it tells the agent to discover current tool schemas before acting. That is the main reason to install it instead of saving a generic Happy Scribe prompt.
Is this skill beginner-friendly?
It is beginner-friendly if your MCP client is already working. The difficult part is not the skill itself; it is the connection setup. New users should first verify that RUBE_SEARCH_TOOLS responds, then connect the happy_scribe toolkit through RUBE_MANAGE_CONNECTIONS, and only then run task prompts.
When should I avoid this skill?
Avoid it for manual editorial review, transcript polishing, or translation quality control unless those steps are part of a larger automation prompt. The skill is designed to operate Happy Scribe through tools, not to replace human review of transcript accuracy, speaker labels, or subtitle timing.
How to Improve happy-scribe-automation skill
Improve happy-scribe-automation prompts with constraints
The fastest way to improve happy-scribe-automation results is to state constraints before execution: source media, language, expected outputs, project naming, whether to wait for completion, and what the agent should do if the connection is inactive. This reduces tool retries and prevents the agent from choosing the wrong Happy Scribe operation.
Example:
If transcription creation requires a file URL and I have not provided one, stop and ask me for it. Do not create placeholder jobs. Use discovered schemas only.
Common failure modes to prevent
The main failure modes are skipping tool discovery, using stale field names, running before the Happy Scribe connection is active, and treating status polling as if it were instant completion. Require the agent to show the discovered tool name and required inputs before executing high-impact actions such as job creation or deletion.
Iterate after the first output
After the first run, ask for a concise execution summary: tool used, input fields, job ID, status, export format, and unresolved issues. Use that summary to make the next prompt more specific, such as requesting another export format, monitoring an existing job ID, or applying a consistent naming convention across multiple media files.
Extend the workflow carefully
For broader automation, chain this skill with file storage, publishing, or notification tools only after the Happy Scribe step is stable. A safe pattern is: transcribe or subtitle in Happy Scribe, verify output availability, export, then pass the result to the next tool. Keep each handoff explicit so the agent does not confuse transcript creation, status checking, and downstream delivery.