Agent Skill

Workflow Schema Tuning skill

workflow-schema-tuningbreaking-brake/cc-wf-studio.claude/skills/workflow-schema-tuning/SKILL.md

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.

5.4k

always on

162 tokname + description

once used

1,100 tokSKILL.md body

bundled files

repo stars

5.4kGitHub

Install the Workflow Schema Tuning skill

Skills CLI (Claude Code, Codex, Cursor and others)

npx skills add https://github.com/breaking-brake/cc-wf-studio --skill workflow-schema-tuning

Claude Code, by hand (all projects)

git clone --depth 1 https://github.com/breaking-brake/cc-wf-studio.git /tmp/cc-wf-studio
mkdir -p ~/.claude/skills
cp -R /tmp/cc-wf-studio/.claude/skills/workflow-schema-tuning ~/.claude/skills/workflow-schema-tuning

For one project only, copy the folder into .claude/skills/ in that project instead. The agent picks it up when a task matches its description.

What it costs your context

Agent Skills load in three steps. Tokens counted with the o200k tokenizer; your model's count will differ a little.

When	What loads	Cost
Every session	Name and description	162 tok
When the agent uses it	The SKILL.md instructions	1,100 tok
Only if opened	No bundled files	—

Until it is used, workflow-schema-tuning costs about 8.4× less than the median MCP server we measured (1,362 tokens on every turn). Installing all 12 skills from breaking-brake/cc-wf-studio would load 1,152 tokens of descriptions. Skills vs MCP study

Checks

Our checks found nothing to flag: it follows the Agent Skills specification's naming and size guidelines and doesn't pipe downloads into a shell.

Checked 2026-10-22 · method

What's inside

The headings of its SKILL.md. Read the full file on GitHub.

Workflow Schema Tuning
Core principle: align direction, do not prescribe rules
Schema architecture
Where biases hide (audit checklist)
Workflow for making changes
Important constraints
Commit conventions for schema changes

More skills from breaking-brake/cc-wf-studio

All skills in this repo

cc-workflow-ai-editorbreaking-brake/cc-wf-studio
AI workflow editor for CC Workflow Studio. Create and edit visual AI agent workflows through interactive conversation using MCP tools (get_workflow_schema, get_current_workflow, apply_workflow, update_nodes). Use when the user wants to create a new workflow, modify an existing workflow, or edit the workflow canvas in CC Workflow Studio via the built-in MCP server.
5.4k77 tok idle · 491 in use
ccwf-clibreaking-brake/cc-wf-studio
Use the `ccwf` CLI (from @cc-wf-studio/cli) to render, validate, preview, export, or run cc-wf-studio workflow JSON files from the terminal. Apply whenever the user mentions viewing, visualizing, checking, executing, or converting a workflow under `.vscode/workflows/` (or any `*workflow*.json`), wants a Mermaid diagram of a workflow, asks to "see" / "preview" / "open" a workflow, or wants to run a workflow as a Claude Code Skill without opening VSCode.
5.4k121 tok idle · 3,025 in use
jira-driven-planningbreaking-brake/cc-wf-studio
Jiraチケットの要件とConfluenceの関連ドキュメントを基に、Frontend/Backend/Infrastructureに分割した実装計画を策定するプランニングスキル。Jiraチケット情報とConfluence検索結果が前段で取得済みであることを前提とし、構造化された実装計画を出力する。「プランニング」「実装計画策定」「タスク分割」などの文脈で使用。
5.4k111 tok idle · 316 in use
next-ideabreaking-brake/cc-wf-studio
Run one unattended IDEATION iteration of the autonomous value-creation loop — invent improvements a user of cc-wf-studio would notice, judge them against the value bar, and file the winners as locked `idea` issues. Never implements anything; the next-task skill builds from the queue this skill fills. Use when the user says "アイデア出して", "next idea", or wants proposals without implementation.
5.4k87 tok idle · 902 in use
next-qabreaking-brake/cc-wf-studio
Run one unattended iteration of the QUALITY-ASSURANCE loop — steward any in-flight QA PR, then build ONE queued `qa` issue (test infrastructure, unit tests, regression tests for known bugs) on a branch off auto-qa and open a PR that squash-merges on green CI. Adds tests and tooling only; never edits product source. Use when the user says "QAタスク", "next qa", "テストを進めて", or wants autonomous progress on the quality track.
5.4k105 tok idle · 2,379 in use
next-qa-ideabreaking-brake/cc-wf-studio
Run one unattended IDEATION iteration of the quality-assurance loop — find the highest-value untested behavior in the codebase, judge it against the QA value bar, and file ONE locked `qa` issue specifying the test to write. Never writes code or tests; the next-qa skill builds from the queue this skill fills. Use when the user says "QAアイデア", "next qa idea", or wants the QA backlog refilled without implementation.
5.4k98 tok idle · 1,518 in use
next-taskbreaking-brake/cc-wf-studio
Run one unattended IMPLEMENTATION iteration of the autonomous value-creation loop — steward any in-flight PR, fix interrupts (red CI / security / human bugs), or else build ONE queued `idea` issue on a branch off auto-dev and open a PR that squash-merges on green CI. Ideation lives in the next-idea skill; this skill consumes its queue. Use when the user says "次のタスク", "next task", "続きをやって", or wants autonomous progress without specifying what to do.
5.4k107 tok idle · 1,978 in use
pr-review-analysisbreaking-brake/cc-wf-studio
Analyze PR review comments from a GitHub PR URL. Fetch review comments, verify each finding against the actual codebase, assess validity (correct/incorrect/partial), present a structured summary with recommended actions, and optionally reply to each comment on GitHub. Use when given a PR review URL or when asked to check/analyze PR feedback.
5.4k72 tok idle · 1,021 in use