dev-flow
Orchestrates a multi-phase development process from requirement specification to final code review.
Install
mkdir -p .claude/skills/dev-flow && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/10562" && unzip -o skill.zip -d .claude/skills/dev-flow && rm skill.zipInstalls to .claude/skills/dev-flow
Activation
This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.
4-phase software development flow: Spec Writing → Spec Review → Implementation → Code Review. Used with the dev-flow-orchestrator extension.Key capabilities
- →Specify requirements
- →Review specifications
- →Implement features
- →Perform code reviews
How it works
Orchestrates a 4-phase development flow where specialized agents handle spec writing, review, implementation, and code review.
Inputs & outputs
When to use dev-flow
- →Generate a detailed feature specification
- →Review architectural requirements for clarity
- →Implement features based on approved specs
- →Perform structured code reviews against design documents
About this skill
ソフトウェア開発フロー (dev-flow)
このフローは要件から動作するコードまでの開発プロセスを自動化します。 オーケストレーターが各フェーズを専門エージェントに委任し、レビューフェーズで品質を担保します。
フロー概要
[要件] → spec-writer → spec-reviewer → developer → code-reviewer → [完成]
↑______________| ↑__________________|
差し戻し(最大3回) 差し戻し(最大3回)
フェーズ説明
| フェーズ | 担当スキル | 説明 |
|---|---|---|
| spec | spec-writer | 要件から機能仕様書 (spec.md) を作成 |
| spec-review | spec-reviewer | 仕様書の品質・完全性・アーキテクチャ適合性をレビュー |
| implementation | developer | 承認済み仕様に基づいて製品コード+ユニットテストを実装 |
| code-review | code-reviewer | 仕様適合・アーキテクチャ準拠・テストカバレッジをレビュー |
フロー定義
{
"name": "ソフトウェア開発フロー",
"phases": [
{
"id": "spec",
"name": "仕様策定",
"skill": "spec-writer",
"prompt": "以下の要件に基づいて、詳細な機能仕様書を作成してください。\n\n## 要件\n\n{requirement}",
"output_file": "spec.md"
},
{
"id": "spec-review",
"name": "仕様レビュー",
"skill": "spec-reviewer",
"prompt": "以下の機能仕様書をレビューしてください。明確性・完全性・正確性・アーキテクチャ適合性の観点で評価し、問題点があれば具体的に指摘してください。",
"input_files": ["spec.md"],
"review": true,
"on_reject": "spec",
"max_retries": 3
},
{
"id": "implementation",
"name": "実装",
"skill": "developer",
"prompt": "以下の承認済み機能仕様書に基づいて、製品コードとユニットテストを実装してください。",
"input_files": ["spec.md"],
"output_file": "implementation-summary.md"
},
{
"id": "code-review",
"name": "コードレビュー",
"skill": "code-reviewer",
"prompt": "以下の仕様書と実装サマリーを参照し、実装されたコードをレビューしてください。仕様適合・アーキテクチャ準拠・テストカバレッジを評価してください。",
"input_files": ["spec.md", "implementation-summary.md"],
"review": true,
"on_reject": "implementation",
"max_retries": 3
}
]
}
使い方
run_flow(flow_skill="dev-flow", requirement="タスク管理機能を追加したい。ユーザーがタスクを作成・編集・削除でき、期限でソートできること。")
オーケストレーター (dev-flow-orchestrator Extension の run_flow ツール) が上記フロー定義を読み込み、
各フェーズの専門エージェントを順番に起動します。
カスタマイズ
このフローをベースに独自のフローを作成する場合は、このファイルをコピーして
flow-definition の JSON ブロックを編集してください。各フェーズの skill フィールドに
対応する .github/skills/{skill}/SKILL.md が必要です。
When not to use it
- →Manual development flow
- →Skipping review phases
Prerequisites
Limitations
- →Max 3 retries per phase
- →Requires specialized skill agents
How it compares
Automates the entire development lifecycle with gated reviews.
Compared to similar skills
dev-flow side by side with the closest alternatives in the catalog.
| Skill | Installs | Updated | Safety | Difficulty |
|---|---|---|---|---|
| dev-flow (this skill) | 0 | 3mo | No flags | Intermediate |
| shellcheck-configuration | 9 | 2mo | No flags | Intermediate |
| wolf-scripts-core | 5 | 9mo | Review | Intermediate |
| final-release-review | 5 | 4mo | Review | Intermediate |
Try saying
Example prompts that trigger this skill in your AI assistant.
More by runceel
View all by runceel →You might also like
shellcheck-configuration
wshobson
Master ShellCheck static analysis configuration and usage for shell script quality. Use when setting up linting infrastructure, fixing code issues, or ensuring script portability.
wolf-scripts-core
Nice-Wolf-Studio
Core automation scripts for archetype selection, evidence validation, quality scoring, and safe bash execution
final-release-review
openai
Perform a release-readiness review by locating the previous release tag from remote tags and auditing the diff (e.g., v1.2.3...<commit>) for breaking changes, regressions, improvement opportunities, and risks before releasing openai-agents-python.
fix
Use when you have lint errors, formatting issues, or before committing code to ensure it passes CI.
verify
Use when you want to validate changes before committing, or when you need to check all React contribution requirements.
bash-defensive-patterns
wshobson
Master defensive Bash programming techniques for production-grade scripts. Use when writing robust shell scripts, CI/CD pipelines, or system utilities requiring fault tolerance and safety.