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 bias sources to audit.

Quality

92%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

92%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A tight, actionable body with executable commands, a concrete prioritized audit checklist, and a validation-gated workflow with feedback loops. The single weakness is mild redundancy of the core 'do not add rules' thesis across three sections.

Suggestions

Consolidate the 'align direction, do not prescribe rules' guidance into one section; the 'Test minimal first' bullet and the 'Anti-pattern' paragraph both restate the Core principle and could be trimmed or merged.

Dimension	Reasoning	Score
Conciseness	Lean and free of basic-concept padding, with a compact architecture table and prioritized checklist; not a 5 because the 'align direction, do not prescribe rules / avoid adding rules' thesis is restated three times (Core principle prose, the 'Test minimal first' bullet, and the 'Anti-pattern' paragraph).	4 / 5
Actionability	Provides copy-paste-ready commands (npm run generate:toon, npm run check && npm run build, npm run debug) plus a concrete audit checklist naming exact fields (nodeTypes.<type>.description, aiGenerationGuidance, examples[], connections.overview.forbidden) and a grep verification step, fully executable across common cases.	5 / 5
Workflow Clarity	The 'Workflow for making changes' is a numbered 7-step sequence with explicit validation (step 5: npm run check && npm run build), testing (step 6), and an iterate feedback loop (step 7), complemented by a prioritized audit checklist — matching the 5 anchor with validation checkpoints and error-recovery feedback.	5 / 5
Progressive Disclosure	No bundle files exist and none are needed; the single SKILL.md is organized into clearly headed sections (Core principle, Schema architecture, audit checklist, Workflow, constraints, commit conventions) with easy navigation, satisfying the simple-skill allowance for well-organized single-file skills.	5 / 5
	Total	19 / 20 Passed

Description

92%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A highly specific, well-triggered description that clearly states both what the skill does and when to use it, anchored to a precise niche with concrete Japanese trigger phrases. The only gap is the absence of natural English trigger synonyms alongside the Japanese ones.

Suggestions

Add 1-2 natural English trigger phrases (e.g., 'AI won't pick the right node type', 'tune workflow generation bias') alongside the Japanese triggers so the skill matches English-language invocations too.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions spanning edit, audit, and build concerns — 'modifying resources/workflow-schema.json to influence how AI agents generate workflows', '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', 'build pipeline (.json → .toon auto-generated)', and 'known bias sources to audit' — giving comprehensive coverage.	5 / 5
Completeness	Explicitly answers both what ('Covers what the schema actually does... the design philosophy... the build pipeline... and known bias sources to audit') and when ('Use when modifying... Triggers include...') with concrete trigger phrases, matching the 5 anchor exactly.	5 / 5
Trigger Term Quality	An explicit 'Use when' clause plus five natural user-quoted triggers ('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', etc.) give strong keyword coverage; not a 5 because English synonyms and phrasing variants are absent and coverage is Japanese-localized.	4 / 5
Distinctiveness Conflict Risk	Scoped to a named file in a named project (cc-wf-studio) influencing a named skill (cc-workflow-ai-editor) with triggers specific to schema tuning/bias, giving a clear niche with minimal overlap risk.	5 / 5
	Total	19 / 20 Passed

Validation

93%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
referenced_paths_exist	Referenced path issues: 1 missing	Warning

	Total	15 / 16 Passed

Repository: breaking-brake/cc-wf-studio
Path: .claude/skills/workflow-schema-tuning/SKILL.md
Commit: a7bf24a

Reviewed: 13 days ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.