Agent skill

Workflow Schema Tuning

by breaking-brake in breaking-brake/cc-wf-studio

Guides edits to cc-wf-studio's workflow schema so AI agents generate better workflows, treating schema text as prompt engineering rather than validation.

Custom licenceAuto-check passedAgent Workflows

Install Workflow Schema Tuning

skills CLI
$ npx skills add breaking-brake/cc-wf-studio --skill workflow-schema-tuning -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install breaking-brake/cc-wf-studio workflow-schema-tuning --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/breaking-brake/cc-wf-studio.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/workflow-schema-tuning .claude/skills/workflow-schema-tuning && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
workflow-schema-tuning
GitHub stars
5.4k
Token cost
~1.3k tokens
SKILL.md length
645 words
Files
1
Skills in repo
11
Repo updated
First seen
Licence
Custom licence

At a glance

Guides edits to cc-wf-studio's workflow schema so AI agents generate better workflows, treating schema text as prompt engineering rather than validation.

  • Works in 5 steps: ai-editing-skill-template.md step 4 —… → nodeTypes..description — the AI's first… → nodeTypes..aiGenerationGuidance — when… → …
  • Changing why the AI picks one node type over another when generating workflows
  • SKILL.md covers Core principle: align…, Schema architecture, Where biases hide (audit… and Workflow for making changes, plus 2 more sections
  • Calls npm

What it does

The schema in `resources/workflow-schema.json` is delivered to the AI editor at runtime through the `get_workflow_schema` MCP tool and is not a runtime validator, so whatever it says, the AI believes. The skill therefore treats schema edits as prompt engineering. Its principle is to align direction instead of prescribing rules: keep descriptions minimal and focused on each node's positional role, avoid long when-to-use lists, and test a minimal change before adding guidance.

The `.toon` file that the AI consumes is generated from the JSON with `npm run generate:toon`, and a full `npm run build` does that as its first step. An audit checklist lists where bias hides, in priority order, starting with step four of `ai-editing-skill-template.md`, where a line such as preferring built-in sub-agents overrides other signals, and then the node type descriptions. Some of the skill's trigger phrases are written in Japanese, such as the AI not choosing a certain node type.

When your agent uses it

  • Changing why the AI picks one node type over another when generating workflows
  • Editing a node description in the workflow schema
  • Auditing the schema for misleading constraints

Example prompts

  • “The AI never chooses the sub-agent node. Find what is biasing it in the schema.”
  • “Add a new node type to workflow-schema.json and regenerate the TOON file.”
  • “Audit the schema descriptions for rules that are not actually enforced at runtime.”

Requirements

  • The cc-wf-studio repository with npm available

Workflow steps

5 steps, taken from the first numbered list in SKILL.md.

  1. ai-editing-skill-template.md step 4 — strongest pull. A line like "use built-in sub-agents by default" overrides every other signal in the…
  2. nodeTypes..description — the AI's first impression of what each node means. Keep terse, contrastive, role-focused.
  3. nodeTypes..aiGenerationGuidance — when present, this is read closely. Audit for stale "default" framings or anti-patterns that no longer…
  4. examples[] — the AI learns strongly from examples. If every example uses one node type, expect that node to dominate output.
  5. Top-level constraints (connections.overview.forbidden, exportValidationRules, postGenerationChecklist) — these can encode false…

What it can do on your machine

Read from SKILL.md and the folder at commit a7bf24a. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • npm

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md. Its commands use npm, which can reach the network depending on how they are called.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Workflow Schema Tuning loads about 1.3k tokens when it runs. Until then it costs about 136 tokens; SKILL.md has 645 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~136
When it runs · the whole SKILL.md, loaded when a task matches
~1.3k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

Its licence (Custom licence) doesn't allow us to republish the file, so here is its outline and opening line. It has 645 words (~1,348 tokens).

“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…”

— opening of SKILL.md by breaking-brake, Custom licence
name
workflow-schema-tuning

Read the full SKILL.md on GitHub

Files

Just SKILL.md in .claude/skills/workflow-schema-tuning of breaking-brake/cc-wf-studio.

Open the folder on GitHubat commit a7bf24a

Compare with similar skills

Workflow Schema Tuning next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Workflow Schema Tuning compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Workflow Schema Tuning this skillbreaking-brake/cc-wf-studio5.4k—~1.3kAutomated safety check: PassCustom licence
Add Promptcyanheads/pubmed-mcp-server155—~1.6kAutomated safety check: PassApache-2.0
Spring AI MCP Server Patternsgiuseppe-trisciuoglio/developer-kit3551 repos~2.7kAutomated safety check: NotesMIT
Cco Overheadegorfedorov/claude-context-optimizer114—~606Automated safety check: PassMIT
MCP Developmentrohitg00/awesome-claude-code-toolkit2.7k—~1.2kAutomated safety check: PassApache-2.0
MCP Server BuildershareAI-lab/learn-claude-code78k5 repos~1.2kAutomated safety check: PassMIT

Similar skills

  • Add Prompt

    cyanheads/pubmed-mcp-server

    Scaffold a new MCP prompt template. An agent skill from cyanheads/pubmed-mcp-server.

    155 GitHub stars~1.6k tokensUpdated 4 days ago
    Agent WorkflowsAuto-check passed
  • Spring AI MCP Server Patterns

    giuseppe-trisciuoglio/developer-kit

    Provides Spring Boot MCP server patterns that create Model Context Protocol servers with Spring AI by defining tool handlers, exposing resources, configuring prompt templates, and setting up…

    355 GitHub starsUsed in 1 repo~2.7k tokens
    Agent WorkflowsAuto-check: notes
  • Cco Overhead

    egorfedorov/claude-context-optimizer

    Audit the fixed context overhead every session starts with — system prompt, MCP tools, agents, CLAUDE.md, memory — measured from real transcript usage

    114 GitHub stars~606 tokensUpdated 8 days ago
    Agent WorkflowsAuto-check passed
  • MCP Development

    rohitg00/awesome-claude-code-toolkit

    MCP server development including tool design, resource endpoints, prompt templates, and transport configuration

    2.7k GitHub stars~1.2k tokensUpdated 4 mo ago
    Agent WorkflowsAuto-check passed
  • MCP Server Builder

    shareAI-lab/learn-claude-code

    Walks through building MCP servers in Python or TypeScript that expose tools, resources and prompts to Claude, with templates, registration and testing.

    78k GitHub starsUsed in 5 repos~1.2k tokens
    Agent WorkflowsAuto-check passed
  • Skill Seekers Builder

    yusufkaraaslan/Skill_Seekers

    Detects the type of a knowledge source and uses the Skill Seekers MCP tools to turn docs, repos, PDFs or videos into packaged AI skills.

    15k GitHub stars~760 tokensUpdated 8 days ago
    Agent WorkflowsAuto-check passed

More from breaking-brake/cc-wf-studio

All 11 skills in this repo
  • PR Review Analysis

    breaking-brake/cc-wf-studio

    Fetches review comments from a GitHub pull request, checks each one against the real code, rates it valid, invalid or partial, and can reply on GitHub.

    5.4k GitHub starsUsed in 1 repo~626 tokens
    Auto-check passed
  • CC Workflow Studio AI Editor

    breaking-brake/cc-wf-studio

    Creates and edits visual agent workflows in CC Workflow Studio through conversation, with the agent reading and writing the canvas over MCP.

    5.4k GitHub stars~561 tokensUpdated 2 days ago
    Auto-check passed
  • Changesets Pull Request to Main

    breaking-brake/cc-wf-studio

    Opens a pull request to main in a pnpm and Changesets monorepo, after working out which packages changed and making sure a changeset file exists.

    5.4k GitHub stars~1.4k tokensUpdated 2 days ago
    Auto-check passed
  • ccwf Workflow CLI

    breaking-brake/cc-wf-studio

    Teaches the agent to use the ccwf command line tool to validate, preview, render, export and run cc-wf-studio workflow JSON files without opening VS Code.

    5.4k GitHub starsUsed in 1 repo~3.3k tokens
    Auto-check passed
  • PR Merge Branch Cleanup

    breaking-brake/cc-wf-studio

    Clean up merged feature branches after PR to main is merged. Use when the user says "ブランチ削除", "cleanup", "マージ後の片付け", or wants to delete a merged branch.

    5.4k GitHub stars~232 tokensUpdated 2 days ago
    Auto-check passed
  • Next Idea Ideation Loop

    breaking-brake/cc-wf-studio

    Runs one unattended ideation round for cc-wf-studio: orient on plans and issues, invent user-visible improvements, judge them against a value bar and file the winners as locked idea issues.

    5.4k GitHub stars~1k tokensUpdated 2 days ago
    Auto-check passed

Questions about Workflow Schema Tuning

What does Workflow Schema Tuning do?

Guides edits to cc-wf-studio's workflow schema so AI agents generate better workflows, treating schema text as prompt engineering rather than validation. json` is delivered to the AI editor at runtime through the `get_workflow_schema` MCP tool and is not a runtime validator, so whatever it says, the AI believes. The skill therefore treats schema edits as prompt engineering.

When should I use Workflow Schema Tuning?

Workflow Schema Tuning fits situations like: changing why the AI picks one node type over another when generating workflows; editing a node description in the workflow schema; auditing the schema for misleading constraints.

How do I install Workflow Schema Tuning in Claude Code?

Run `npx skills add breaking-brake/cc-wf-studio --skill workflow-schema-tuning -a claude-code`. Or copy the skill folder (.claude/skills/workflow-schema-tuning in breaking-brake/cc-wf-studio) into .claude/skills/workflow-schema-tuning in your project. Claude Code loads it when a task matches its description.

How do I install Workflow Schema Tuning in Codex?

Run `npx skills add breaking-brake/cc-wf-studio --skill workflow-schema-tuning -a codex`. Or copy the skill folder (.claude/skills/workflow-schema-tuning in breaking-brake/cc-wf-studio) into .agents/skills/workflow-schema-tuning in your project. Codex loads it when a task matches its description.

Can I use Workflow Schema Tuning in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add breaking-brake/cc-wf-studio --skill workflow-schema-tuning -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/workflow-schema-tuning, .gemini/skills/workflow-schema-tuning, .github/skills/workflow-schema-tuning and .opencode/skills/workflow-schema-tuning in your project.

What does Workflow Schema Tuning need to run?

Going by SKILL.md and its folder, Workflow Schema Tuning needs the command-line tools its instructions call (npm). Our summary lists: The cc-wf-studio repository with npm available.

Does Workflow Schema Tuning access the network?

SKILL.md contains no URLs. Its commands use npm, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is Workflow Schema Tuning safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Workflow Schema Tuning use?

Workflow Schema Tuning has a licence file (the repository's licence) that doesn't match a standard licence. Read it on GitHub before reusing the skill.

How many tokens does Workflow Schema Tuning use?

About 1.3k tokens (SKILL.md is roughly 5.4k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Workflow Schema Tuning?

Skills that share tags, products or a category with Workflow Schema Tuning: Add Prompt (cyanheads/pubmed-mcp-server, 155 stars), Spring AI MCP Server Patterns (giuseppe-trisciuoglio/developer-kit, 355 stars), Cco Overhead (egorfedorov/claude-context-optimizer, 114 stars) and MCP Development (rohitg00/awesome-claude-code-toolkit, 2.7k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Workflow Schema Tuning?

breaking-brake (a GitHub user) maintains it in breaking-brake/cc-wf-studio, which has 5,393 GitHub stars. The repository holds 11 skills in this directory. The repository was last updated on October 7, 2026.

Source: breaking-brake/cc-wf-studio on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.