メニュー
Use to autonomously execute an approved implementation plan. Writes production code, creates tests, and modifies files in strict sequence. No explanations, no architectural discussion — pure high-density code execution.
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
SOC 職業分類に基づく
Use to audit, evaluate, and verify workspace configuration compliance and inheritance integrity against universal workstation standards.
Use to execute the implementation phase of onboarding an existing project workspace. Generates localized overrides, configuration snippets, and pre-commit hooks.
Use when onboarding an existing project workspace into our hierarchical workstation ecosystem. This skill performs gap analysis, local override mapping, and refactoring planning without generating code.
Check for untracked/modified changes in the workspace, draft a descriptive commit message, commit them, and push the commit.
Run the research and planning phase of development to produce a functional architecture, design spec, and checklist without modifying code or writing implementation files.
Provides a structured workflow for Document-Driven Design (DocDD) and development. Guides the agent to design functional architectures, identify technical pitfalls, and write token-efficient specs suitable for local models (e.g. Ollama) before coding.
| name | autonomous-dev-implementation |
| description | Use to autonomously execute an approved implementation plan. Writes production code, creates tests, and modifies files in strict sequence. No explanations, no architectural discussion — pure high-density code execution. |
Execute approved plan with full autonomy.
Do not narrate, explain, or state plans. Every token must produce code, tests, or configs. Run silently.
task.md checkbox status. Write complete code without placeholders.Update task.md. Create a 3-line walkthrough.md list of changes and test results.