メニュー
Execute one implementation phase with progress tracking and verification. Use when: implementing tasks from an SDD plan, logging discoveries, updating task tables, and running build/test verification per phase.
デフォルトでは、最初にソースを確認する Prompt が選択されています。直接コマンドに切り替えるか、ローカルコピーをダウンロードすることもできます。
インストールを決める前に、SKILL.md と SkillsMP に表示されている付属ファイルをお読みください。
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。
直接コマンドでは確認用 Prompt が省略されます。実行前にソースを確認してください。
npx skills add https://github.com/willvelida/biotrackr --skill sdd-5-implementコマンドは1行のまま表示されます。コピー前に横へスクロールして全体を確認してください。
ローカルで確認しますか？SkillsMP が現在取得できるファイルをダウンロードできます。
Blazor component architecture, Razor component patterns, Radzen UI library, and Blazor-specific UX patterns. Use when: building Blazor components, structuring Razor component hierarchy, using Radzen components, implementing Blazor forms, managing component state, Blazor rendering modes, Blazor layout design.
Ensure .NET/C# code meets best practices for the solution/project.
Quality gate review with structured findings and verdict. Use when: reviewing a completed implementation phase, checking spec compliance, convention adherence, test coverage, and issuing APPROVE or REQUEST_CHANGES verdicts.
SOC 職業分類に基づく
SKILL.md を表示中
| name | sdd-5-implement |
| description | Execute one implementation phase with progress tracking and verification. Use when: implementing tasks from an SDD plan, logging discoveries, updating task tables, and running build/test verification per phase. |
[!CAUTION] LOG DISCOVERIES IMMEDIATELY. After each task, update the task table and append to the execution log. Do not batch updates at the end.
[!IMPORTANT] UPDATE PROGRESS PER TASK. Every task requires a 3-step update: (1) task table checkbox, (2) notes column, (3) execution log entry.
Before starting, resolve project conventions:
docs/project-rules/ (constitution.md, rules.md, idioms.md, architecture.md)copilot-instructions.md, AGENTS.md, CONTRIBUTING.md, README.md[TODO].copilot-tracking/plans/{date}/{slug}/execution.log.md.For each task, before implementation:
.github/agents/ for a specialized agent matching that technology.Do not hardcode agent names or technology mappings. Detect both dynamically from the workspace.
For each task in the phase's task table, execute in order:
Update the task status from [ ] to [~] in the plan file's task table.
Execute the task (delegated or direct). Follow conventions and patterns identified during Doctrine Resolution.
Run the project's build command per doctrine. Run the project's test command per doctrine. Record pass/fail results.
Update the task status from [~] to [x] in the plan file's task table. Add a direct execution log link in the Notes column using this exact format: execution.log.md#task-{id}.
Append to execution.log.md:
<a id="task-{ID}"></a>
## Task {ID}: {Task Description}
* **Status**: Completed
* **Changes Made**: {List of files created, modified, or removed}
* **Verification**: {Build result, test result, coverage if applicable}
* **Measurement**: Verification: {pass|fail}, Discoveries: {N}
* **Discoveries**: {Any findings during implementation, or "None"}
If a task cannot proceed due to an unresolved dependency or ambiguity:
[!] (blocked).Independent subsequent tasks (no dependency on the blocked task) may continue only if the user explicitly approves.
Log discoveries immediately when encountered, not at the end. Each discovery includes a typed category:
| Category | Use When |
|---|---|
| gotcha | Surprising behavior that could trip up future work |
| research-needed | Knowledge gap requiring deeper investigation |
| unexpected-behavior | Runtime or build behavior differing from expectations |
| workaround | Temporary fix applied due to a known limitation |
| decision | Design choice made during implementation with rationale |
| debt | Technical debt introduced or identified for future resolution |
| insight | Reusable learning applicable beyond this task |
Format:
### Discovery: {Title}
* **Category**: {gotcha | research-needed | unexpected-behavior | workaround | decision | debt | insight}
* **Task**: {Task ID}
* **Evidence**: {file:line or command output}
* **Description**: {What happened and why it matters}
When all tasks in the phase are [x] (or [!] with user acknowledgment):
[!IMPORTANT] STOP. Present the phase completion summary and wait for user direction. Do not automatically proceed to the next phase or to review.