Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →breaking-brake/workflow-schema-tuning
Use when modifying `resources/workflow-schema.json` in cc-wf-studio to influence how AI agents generate workflows via the cc-workflow-ai-editor skill. Triggers include "AIが特定のノードタイプを選んでくれない", "ワークフロー生成のバイアスを調整したい", "スキーマの description を変えたい", "新しいノードタイプを追加したい", "嘘の制約がスキーマに混じっていないか確認したい". Covers what the schema actually does (instructions to AI, not runtime constraints), the design philosophy (align direction, do not prescribe rules), the build pipeline (.json → .toon auto-generated), and known bi
Passed 15 of 20 test cases with the skill, and 5 of 20 without it.
and 15 more in the full report
10 fixed6 passed either way6 still failing0 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 10 test cases the skill fixed. Same model, same prompt, with and without the skill.
After running npm run generate:toon during schema editing, what specific manual verification step should be performed to confirm the changes will be seen by the AI editor?
| Checked | Without skill | With skill |
|---|---|---|
| Recommends grepping the updated string directly inside resources/workflow-schema.toon. | Missed | Passed |
| Notes that the MCP tool delivers TOON format rather than JSON. | Missed | Passed |
The instructions your model reads when the skill loads.
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.
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."
Defaults:
aiGenerationGuidance lists of "when to use / when not to use / anti-patterns." They treat the AI as a rules engine, bloat tokens, and fail on unanticipated cases.Anti-pattern: writing detailed upgradeToSubAgentWhen / stayInPromptWhen lists. If you find yourself writing 3+ bullets explaining when to use a node, the description itself is probably wrong.
| File | Role | Editable? |
|---|---|---|
resources/workflow-schema.json | Single source of truth | YES |
resources/workflow-schema.toon | Token-efficient format consumed by AI via MCP | NO — auto-generated |
resources/ai-editing-skill-template.md | Skill template loaded at AI editor launch | YES |
scripts/generate-toon-schema.ts | TOON generator | YES (rare) |
After editing .json, regenerate .toon:
npm run generate:toon
The full build (npm run build) does this automatically as the first step.
When the AI consistently picks the wrong node type, look here in priority order:
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 schema. Keep this neutral.nodeTypes.<type>.description — the AI's first impression of what each node means. Keep terse, contrastive, role-focused.nodeTypes.<type>.aiGenerationGuidance — when present, this is read closely. Audit for stale "default" framings or anti-patterns that no longer apply.examples[] — the AI learns strongly from examples. If every example uses one node type, expect that node to dominate output.test cases passed, vs 5 / 20 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.