Workflow Schema Tuning

by breaking-brake

Workflow Schema Tuning is an AI Engineering skill for Claude Code, published by breaking-brake in cc-wf-studio.

5.4K stars571 forkson breaking-brake/cc-wf-studioAdded 2026/08/16Repository updated 2026/08/09

View source on GitHub Download repo ZIP

agent-skillsclaude-codemcp-toolsslash-commandssub-agentsvscode-extensionworkflow-automation

Install in seconds

Install Workflow Schema Tuning

Copy Workflow Schema Tuning into your Claude Code skills folder. Run the command in your terminal, or review the source on GitHub before installing.

terminal

npx degit https://github.com/breaking-brake/cc-wf-studio/tree/main/.claude/skills/workflow-schema-tuning ~/.claude/skills/workflow-schema-tuning

Requires Node.js. Downloads this skill only — not the rest of the repository — into your Claude Code skills folder.

Without Node.js

git clone https://github.com/breaking-brake/cc-wf-studio.git

Clones the whole repository, then copy the skill’s own directory into your skills folder yourself.

In this catalog

Source file: .claude/skills/workflow-schema-tuning/SKILL.md in breaking-brake/cc-wf-studio
Installs to: ~/.claude/skills/workflow-schema-tuning
Collection: One of 11 skills cataloged from this repository
Category: AI Engineering — 2451 skills

What Workflow Schema Tuning does

Workflow Schema Tuning guides edits to resources/workflow-schema.json in cc-wf-studio to influence how AI agents generate workflows, by removing biases and keeping schema descriptions minimal and agent-agnostic. Use when the AI editor consistently picks the wrong node types or cites false constraints.

Workflow Schema Tuning is cataloged under AI Engineering on DirSkills. Workflow Schema Tuning comes from a repository tagged agent-skills, claude-code, mcp-tools, slash-commands and sub-agents.

Documentation

README

Excerpt

Workflow Schema Tuning

The schema (resources/workflow-schema.json) is the primary spec delivered to the AI editor at runtime via the get_workflow_schema MCP tool. It is not a runtime validator — the runtime barely validates anything. Whatever the schema says, the AI believes. Treat schema edits as prompt engineering, not type definitions.

Core principle: align direction, do not prescribe rules

AI agents already know how to choose between node types intuitively (e.g., when to delegate to a sub-agent vs. handle in-context). The fix for bad output is almost never "add more rules" — it is "remove what is biasing the AI in the wrong direction."

This is the opening of the README. Read the full README on GitHub.

Frequently asked about Workflow Schema Tuning

What else does breaking-brake publish alongside Workflow Schema Tuning?
Workflow Schema Tuning is one of 11 skills that DirSkills catalogs from breaking-brake/cc-wf-studio, the repository it ships in. Its siblings there include CC Workflow AI Editor, CCWF CLI and Jira Driven Planning. Each one is a separate skill with its own page in this directory, installs the same way Workflow Schema Tuning does, and is maintained by breaking-brake in that same repository. The rest of the collection is listed on the breaking-brake/cc-wf-studio page.
How does Workflow Schema Tuning compare to other AI Engineering skills?
Workflow Schema Tuning ranks #484 by stars among the 2451 AI Engineering skills in this catalog. The most-starred ones next to it are Architecture Decision Records, AI-First Engineering and Agentic OS. DirSkills ranks by the star count of the repository each skill ships in, so that order reflects how popular those repositories are rather than any review of Workflow Schema Tuning against them. Open each page to compare what they document and how they install.