Skip to main content
Skill Studio is the power-user editor for skills. The creation wizard and flow builder generate skills for you; Studio is where you open the hood. It is a three-panel workspace with a file tree, a code editor, and live validation plus a test runner. Open it from a skill card’s Edit action, or via the Open in Studio link after the wizard finishes.

The Layout

  • Left: the skill’s files. SKILL.md holds the skill’s definition and instructions; procedural skills also have main.py (or a Node.js entry point), requirements.txt, and any supporting files.
  • Center: the editor, with syntax highlighting for Python, Markdown, JSON, and YAML.
  • Right: tabbed panels for Validation, Test Runner, Credentials, Metadata, and Versions.

Validation

The Validation panel checks the skill continuously as you edit. Checks include a valid frontmatter schema, a present entry point, declared dependencies, safe operations only, and that the skill’s declared inputs and outputs match what the code actually reads and writes. A failing check blocks Publish until fixed, so you cannot ship a broken skill by accident.

Test Runner

The Test Runner executes the skill in a sandbox without publishing:
  1. Provide sample input as JSON, or leave it empty for a connectivity check
  2. Click Run
  3. Output streams in real time, with a status badge (Running, Success, Failed) and elapsed time
Test as often as you like; test runs do not affect the published version.

Refine with AI

The Refine input at the bottom of the editor asks AI to edit the active file for you: “Add a totals row to the report table” or “Handle the case where the API returns no results”. The AI edits in place; you review the change in the editor.

Credentials and Metadata

  • Credentials tab: attach a stored credential to the skill and test it.
  • Metadata tab: edit the skill’s name, description, icon, category, scope, run budgets, and any tunables the skill exposes.

Platform tools and connected services

The Runtime panel lists the platform tools the skill declares. A skill gets extra abilities through the platform_tools list in its frontmatter:
  • Built-in tools such as memory_search (search your organization’s Files), web_search, and create_file.
  • Capabilities such as gmail.read or calendar.read.
  • Tools from Connected Services. Any tool from a connected MCP service works here too. Add its name (for example mcp_rankpilot_search) to platform_tools and the skill can call that service during its run. The exact names are listed on the Connected Services screen when you expand a service’s row. Connector calls from a skill run with the same organization isolation and audit trail as calls from chat.

Versions

Every publish creates a new version. The Versions tab lists the history with changelogs, and any version has a Revert to this version button. Reverting is non-destructive: it creates a new version with the old content, so the full history is always preserved.

Publishing

When validation passes, click Publish. The new version becomes the one that runs in chat, in schedules, and for anyone the skill is shared with. Use Save Draft to keep work in progress without affecting the live version.
You rarely need Studio to make a change. For “make the summary shorter” style adjustments, Evolve handles the edit, the diff, and the version bump for you.