Install any skill in seconds. Free to start, no credit card required.
Get Started Free →marimoダッシュボード・プロジェクト進捗可視化に使用。 「ダッシュボードを作って」「進捗を可視化して」「テスト結果を表示して」等のリクエストで発動。
.claude/skills/minicoohei-monitoring-dashboard/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-01 | ✗→✓ | ▲ Improved | 48% | 0% |
| case-02 | ✗→✓ | ▲ Improved | 12% | 0% |
| case-03 | ✗→✓ | ▲ Improved | 19% | 0% |
| case-07 | ✗→✓ | ▲ Improved | -43% | 0% |
| case-08 | ✗→✓ | ▲ Improved | 6% | 0% |
marimo Run Mode を使って、プロジェクト進捗・テスト結果・要件トレーサビリティを可視化するダッシュボードを生成します。
marimo run で起動し、ブラウザで確認WBS進捗データから以下を可視化:
データ形式: dummy-wbs-progress.json
json{ "tasks": [ { "id": "WBS-001", "name": "タスク名", "phase": "Phase A", "assignee": "担当者", "progress": 75, "start_date": "2025-01-01", "due_date": "2025-01-15", "status": "in_progress" } ] }
テスト実行結果から以下を可視化:
データ形式: dummy-test-results.json
json{ "suites": [ { "name": "スイート名", "tests": [ { "id": "TC-001", "name": "テスト名", "status": "passed", "duration_ms": 150, "severity": "high" } ] } ] }
要件→設計→テストの追跡:
pythonimport marimo as mo import pandas as pd import plotly.express as px import json app = mo.App() @app.cell def load_data(): """データ読み込み""" with open("path/to/data.json") as f: data = json.load(f) return pd.DataFrame(data["tasks"]) @app.cell def progress_chart(df): """進捗チャート""" fig = px.bar(df, x="name", y="progress", color="phase", title="タスク進捗率") mo.ui.plotly(fig) @app.cell def summary_metrics(df): """サマリーメトリクス""" total = len(df) completed = len(df[df["progress"] == 100]) mo.md(f""" ## プロジェクトサマリー - 総タスク数: **{total}** - 完了: **{completed}** - 完了率: **{completed/total*100:.1f}%** """)
| Parameter | Required | Default | Description | |-----------|----------|---------|-------------| | data_source | Yes | - | データファイルのパス(JSON/CSV) | | dashboard_type | No | integrated | ダッシュボード種別(progress/test/traceability/integrated) | | output | No | output/pm/dashboard.py | 出力ファイルパス | | title | No | Project Dashboard | ダッシュボードタイトル |
marimo ノートブック(.py)を生成:
output/pm/dashboard.py — marimo run output/pm/dashboard.py で起動uv add marimo)uv add pandas)uv add plotly)monitoring-dashboardスキルを使って、ダミーデータからプロジェクト統合ダッシュボードを作成してください。
データ: 任意の進捗 JSON または CSV
→ output/pm/dashboard.py が生成される → marimo run で起動| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→pass | 20,518 | 24,911 | +21% | 1 | 1 | 0% | 4,428 | 6,573 | +48% | 0 | 0 | — |
case-02 | fail→pass | 22,340 | 20,300 | -9% | 1 | 1 | 0% | 4,959 | 5,570 | +12% | 0 | 0 | — |
case-03 | fail→pass | 27,042 | 27,589 | +2% | 1 | 1 | 0% | 6,078 | 7,247 | +19% | 0 | 0 | — |
case-04 | pass→pass | 11,615 | 8,768 | -25% | 1 | 1 | 0% | 2,189 | 2,630 | +20% | 0 | 0 | — |
case-05 | pass→pass | 12,594 | 11,744 | -7% | 1 | 1 | 0% | 2,764 | 2,845 | +3% | 0 | 0 | — |
case-10 | pass→pass | 8,830 | 4,497 | -49% | 1 | 1 | 0% | 1,503 | 1,695 | +13% | 0 | 0 | — |
case-06 | pass→pass | 9,067 | 10,491 | +16% | 1 | 1 | 0% | 1,767 | 3,215 | +82% | 0 | 0 | — |
case-07 | fail→pass | 15,577 | 3,494 | -78% | 1 | 1 | 0% | 3,079 | 1,763 | -43% | 0 | 0 | — |
case-08 | fail→pass | 16,509 | 10,974 | -34% | 1 | 1 | 0% | 3,050 | 3,228 | +6% | 0 | 0 | — |
case-09 | fail→pass | 5,080 | 2,253 | -56% | 1 | 1 | 0% | 881 | 1,360 | +54% | 0 | 0 | — |
case-11 | pass→pass | 5,603 | 3,413 | -39% | 1 | 1 | 0% | 1,079 | 1,681 | +56% | 0 | 0 | — |
case-12 | fail→pass | 7,783 | 1,866 | -76% | 1 | 1 | 0% | 1,155 | 1,313 | +14% | 0 | 0 | — |
case-13 | fail→pass | 12,108 | 1,444 | -88% | 1 | 1 | 0% | 1,910 | 1,253 | -34% | 0 | 0 | — |
case-14 | fail→fail | 12,696 | 8,452 | -33% | 1 | 1 | 0% | 2,285 | 2,489 | +9% | 0 | 0 | — |
case-15 | pass→pass | 4,944 | 2,969 | -40% | 1 | 1 | 0% | 799 | 1,563 | +96% | 0 | 0 | — |
case-16 | fail→pass | 8,318 | 2,730 | -67% | 1 | 1 | 0% | 1,332 | 1,568 | +18% | 0 | 0 | — |
case-17 | fail→pass | 6,754 | 2,735 | -60% | 1 | 1 | 0% | 974 | 1,518 | +56% | 0 | 0 | — |
case-18 | fail→pass | 7,153 | 2,757 | -61% | 1 | 1 | 0% | 1,131 | 1,459 | +29% | 0 | 0 | — |
case-19 | pass→pass | 5,104 | 1,472 | -71% | 1 | 1 | 0% | 826 | 1,224 | +48% | 0 | 0 | — |
case-20 | fail→pass | 8,918 | 1,696 | -81% | 1 | 1 | 0% | 1,321 | 1,263 | -4% | 0 | 0 | — |
case-21 | pass→pass | 4,711 | 1,740 | -63% | 1 | 1 | 0% | 733 | 1,275 | +74% | 0 | 0 | — |
case-22 | pass→pass | 13,011 | 15,071 | +16% | 1 | 1 | 0% | 2,092 | 3,173 | +52% | 0 | 0 | — |
case-23 | pass→pass | 5,151 | 1,921 | -63% | 1 | 1 | 0% | 828 | 1,322 | +60% | 0 | 0 | — |
case-24 | pass→pass | 12,018 | 7,391 | -39% | 1 | 1 | 0% | 1,810 | 2,152 | +19% | 0 | 0 | — |
case-25 | fail→pass | 4,389 | 1,979 | -55% | 1 | 1 | 0% | 653 | 1,201 | +84% | 0 | 0 | — |
DecimalAI ran this skill against gemini-3.6-flash twice over the same eval suite — once with the skill loaded and once without — and compared the two runs case by case. 25 cases were attempted. The headline lift of +52 percentage points is the difference between those two pass rates over the 25 comparable cases.
Without the skill loaded, the model failed this case. With it loaded, the same prompt on the same model passed. This is one improved case from the latest verified run; every case, including any that regressed, is in the table above.
Other measured skills in the registry, with their headline benchmark lift.