メニュー
Generate phased implementation blueprint with parallel research subagents. Use when: a clarified specification is ready for architecture planning, creating task tables, scoring complexity, and defining implementation phases.
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-4-architect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.
SKILL.md を表示中
SOC 職業分類に基づく
| name | sdd-4-architect |
| description | Generate phased implementation blueprint with parallel research subagents. Use when: a clarified specification is ready for architecture planning, creating task tables, scoring complexity, and defining implementation phases. |
[!IMPORTANT] NO TIME ESTIMATES. Use CS-1 through CS-5 complexity scoring exclusively. Never predict hours, days, or sprints.
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] markers — never assume silently.Read the specification and verify readiness:
[NEEDS CLARIFICATION] markers remain (warn if found but do not block).Select research depth based on workflow mode (from Clarifications section) and available artifacts.
Launch 2 parallel subagents when the user selected Simple mode in Clarify, or when a research dossier already exists:
Launch 4 parallel subagents when Full mode was selected and no research dossier exists:
Each subagent follows this investigation sequence:
Collect findings from all subagents, deduplicate, and order by impact. Produce a minimum of 10 final discoveries.
Each discovery follows this format:
### Discovery D-01: {Title}
* **Category**: {Pattern | Integration | Convention | Constraint}
* **Impact**: {Critical | High | Medium | Low}
* **Evidence**: {file:line reference}
* **Description**: {What was found}
* **Why It Matters**: {Impact on implementation}
* **Example**:
❌ WRONG:
{Incorrect pattern with brief explanation}
✅ CORRECT:
{Correct pattern with brief explanation}
* **Action Required**: {What the implementation must do}
Discoveries without file:line evidence become [UNVERIFIED] markers.
Assess complexity using the CS-1 through CS-5 rubric with six factors:
| Factor | Score (0-2) | Rationale |
|---|---|---|
| Surface Area (S) | ||
| Integration (I) | ||
| Data/State (D) | ||
| Novelty (N) | ||
| Non-Functional (F) | ||
| Testing (T) | ||
| Total | CS-{N} |
Create the plan file at .copilot-tracking/plans/{date}/{slug}/{slug}-plan.md using the template at .copilot-tracking/templates/sdd-design-template.md.
Break the implementation into ordered phases. Each phase should be independently buildable and testable when possible. Annotate phase dependencies explicitly.
Each phase uses the 6-column task table format with 4-state checkboxes:
| Status | ID | Task | Path(s) | Done When | Notes |
|--------|------|-------------------|-----------------|-----------------------|-------|
| [ ] | T001 | {Task description} | {/path/to/file} | {Success criteria} | |
Task status legend: [ ] pending, [~] in-progress, [x] completed, [!] blocked.
Reference the project's build command, test command, and coverage threshold from doctrine. Do not hardcode tool-specific commands. Use the format:
## Validation
* Build: {per doctrine build command}
* Test: {per doctrine test command}
* Coverage: {per doctrine threshold, or [TODO] if unknown}
Before finalizing the plan, scan for prior Cycle Measurement Summaries to inform planning:
.copilot-tracking/plans/*/ for directories containing reviews/review.md files.## Cycle Measurement Summary sections found in those review reports.### Historical Context subsection in the plan summarizing relevant prior metrics.Present the completed plan to the user with:
[TODO] markers that require user input.[!IMPORTANT] STOP. Present the plan to the user and wait for approval before proceeding to Phase 5 (Implement). The user may request adjustments to phase boundaries, task ordering, or scope.