スキル一覧に戻る

generate-status-report

pjt222
更新日 2 days ago
8 閲覧
17
2
17
GitHubで表示
メタdata

について

このスキルは、チャーターやバックログなどの既存成果物を分析し、メトリクスを算出して障害を特定することで、包括的なプロジェクト状況報告書を生成します。進捗状況を、スケジュール、範囲、予算、品質に関するRAG指標を用いて要約します。スプリント終了時、ガバナンス会議前、または新たなリスクが発生してステークホルダーへの更新が必要な際にご利用ください。

クイックインストール

Claude Code

推奨
メイン
npx skills add pjt222/agent-almanac -a claude-code
プラグインコマンド代替
/plugin add https://github.com/pjt222/agent-almanac
Git クローン代替
git clone https://github.com/pjt222/agent-almanac.git ~/.claude/skills/generate-status-report

このコマンドをClaude Codeにコピー&ペーストしてスキルをインストールします

ドキュメント

Generate a Project Status Report

Make periodic status report. Analyze project artifacts, compute progress metrics, summarize accomplishments, blockers, upcoming work with RAG (Red/Amber/Green) health indicators.

When Use

  • End of sprint or reporting period (weekly, biweekly, monthly)
  • Stakeholder asks for project health update
  • Before steering committee or governance meetings
  • Project health indicators change (new blocker or risk)
  • Periodic checkpoint vs charter milestones

Inputs

  • Required: Reporting period (start + end date)
  • Required: At least one project artifact (BACKLOG.md, SPRINT-PLAN.md, WBS.md, PROJECT-CHARTER.md)
  • Optional: Previous status reports (trend comparison)
  • Optional: Budget or resource tracking data
  • Optional: Risk register updates

Steps

Step 1: Read Existing Artifacts

Scan project directory for PM artifacts:

  • PROJECT-CHARTER.md — milestones, success criteria
  • BACKLOG.md — item counts by status, burn-down data
  • SPRINT-PLAN.md — sprint goal, committed items, task completion
  • WBS.md — work package completion percentages
  • Previous STATUS-REPORT-*.md files — trend data

Read available files. Not all will exist — adapt report to available data.

Got: At least one artifact read successful, key metrics extracted.

If fail: No artifacts exist? Report can't be generated. Create charter or backlog first with draft-project-charter or manage-backlog.

Step 2: Compute Progress Metrics

Compute metrics from available data:

Agile metrics (from BACKLOG.md / SPRINT-PLAN.md):

  • Velocity: story points done this sprint
  • Sprint completion: items done / items committed
  • Backlog burn-down: total remaining points vs previous period
  • Cycle time: average days from In Progress to Done

Classic metrics (from WBS.md):

  • % complete: work packages done / total
  • Schedule variance: planned milestone dates vs actual
  • Effort variance: estimated effort vs actual
## Metrics
| Metric | Value | Previous | Trend |
|--------|-------|----------|-------|
| Velocity | [N] pts | [N] pts | ↑/↓/→ |
| Sprint Completion | [N]% | [N]% | ↑/↓/→ |
| Backlog Remaining | [N] pts | [N] pts | ↓ (good) |
| Schedule Variance | [+/-N days] | [+/-N days] | |

Got: 3-5 metrics computed with previous period comparison.

If fail: No historical data (first report)? Skip Previous + Trend columns. Data incomplete → note gaps in report footer with actions to establish tracking.

Step 3: Find Blockers, Risks, Issues

List active blockers + risks:

## Blockers & Risks
| ID | Type | Description | Severity | Owner | Status | Action Required |
|----|------|------------|----------|-------|--------|----------------|
| R-001 | Risk | [Description] | High | [Name] | Open | [Action] |
| B-001 | Blocker | [Description] | Critical | [Name] | Active | [Action by date] |
| I-001 | Issue | [Description] | Medium | [Name] | Investigating | [Action] |

Cross-reference vs charter risk register. Flag new risks not previously identified.

Got: All active blockers + top risks documented with owners + actions.

If fail: No blockers? State "No active blockers" — no empty section. Blocker without owner? Escalate to project manager.

Step 4: Summarize Accomplishments + Next Period Plan

Write two sections:

## Accomplishments (This Period)
- [Completed item/milestone with evidence]
- [Completed item/milestone with evidence]
- [Completed item/milestone with evidence]

## Planned (Next Period)
- [Planned item/milestone with target]
- [Planned item/milestone with target]
- [Planned item/milestone with target]

Got: 3-5 accomplishments with concrete evidence, 3-5 planned items for next period.

If fail: No accomplishments? Report reason (blocked, re-planning, team unavailable). Next period plan unclear → list "Planning session scheduled for [date]" as primary.

Step 5: Assign RAG + Write Report

Assess project health across four dimensions:

DimensionGreenAmberRed
ScheduleOn track or ahead1-2 weeks behind>2 weeks behind or milestone missed
ScopeNo uncontrolled changesMinor scope adjustmentsScope creep affecting deliverables
BudgetWithin 5% of plan5-15% over plan>15% over plan or untracked
QualityTests pass, criteria metMinor quality issuesCritical defects or acceptance failures

Write complete report:

# Status Report: [Project Name]
## Report Date: [YYYY-MM-DD]
## Reporting Period: [Start] to [End]
## Document ID: SR-[PROJECT]-[YYYY-MM-DD]

### Overall Health
| Dimension | Status | Notes |
|-----------|--------|-------|
| Schedule | 🟢/🟡/🔴 | [One-line explanation] |
| Scope | 🟢/🟡/🔴 | [One-line explanation] |
| Budget | 🟢/🟡/🔴 | [One-line explanation] |
| Quality | 🟢/🟡/🔴 | [One-line explanation] |

### Executive Summary
[2-3 sentences: overall status, key achievement, biggest risk]

### Metrics
[From Step 2]

### Accomplishments
[From Step 4]

### Blockers & Risks
[From Step 3]

### Planned Next Period
[From Step 4]

### Decisions Needed
- [Decision 1 — needed by date, from whom]

---
*Report prepared by: [Name/Agent]*

Save as STATUS-REPORT-[YYYY-MM-DD].md.

Got: Complete status report saved with RAG indicators, metrics, narrative.

If fail: Data insufficient for RAG assessment? Use ⚪ (Grey) = "insufficient data", list what data needs collecting for next report.

Checks

  • Status report file created with date-stamped filename
  • RAG indicators assigned for all four dimensions with justification
  • At least 3 metrics computed from project artifacts
  • Blockers section present (even if "No active blockers")
  • Accomplishments listed with evidence
  • Next period plan included
  • Executive summary 2-3 sentences, not paragraph
  • Every blocker + risk has owner + action with deadline

Pitfalls

  • Report without data: Status reports must be evidence-based. Every claim references artifact or metric.
  • All green always: Persistent green RAG without evidence = not honest. Challenge green assessments.
  • Blocker without owner: Every blocker needs owner + action. Unowned blockers don't resolve.
  • Metric without context: "Velocity = 18" means nothing without comparison. Always include previous period or target.
  • Too long: Status report scannable in 2 min. Keep to 1-2 pages.
  • Missing decisions section: Project needs stakeholder decisions? Make explicit with deadlines.
  • Stale data: Outdated artifacts → misleading reports. Verify artifact dates match reporting period.
  • Missing trend data: First-time reports can't show trends, but subsequent reports must compare.

See Also

  • draft-project-charter — charter provides milestones + success criteria for status tracking
  • manage-backlog — backlog metrics feed status report
  • plan-sprint — sprint results provide velocity + completion data
  • create-work-breakdown-structure — WBS completion drives classic progress metrics
  • conduct-retrospective — status report data feeds retrospective

GitHub リポジトリ

pjt222/agent-almanac
パス: i18n/caveman/skills/generate-status-report
0
agentsagentskillsai-assisted-developmentclaude-codeskillsteams

関連スキル

content-collections

メタ

このスキルは、Content Collections(Markdown/MDXファイルを型安全なデータコレクションに変換するTypeScriptファーストのツール)の本番環境でテストされた設定を提供します。Zodバリデーションによる型安全性を実現し、ブログ、ドキュメントサイト、コンテンツ重視のVite + Reactアプリケーション構築時にご利用ください。Viteプラグインの設定、MDXコンパイルから、デプロイ最適化、スキーマバリデーションまで、すべてを網羅しています。

スキルを見る

polymarket

メタ

このスキルは、開発者がPolymarket予測市場プラットフォームを活用したアプリケーション構築を可能にします。API統合による取引や市場データの取得に加え、WebSocketを介したリアルタイムデータストリーミングにより、ライブ取引や市場活動を監視できます。取引戦略の実装や、ライブ市場更新を処理するツールの作成にご利用ください。

スキルを見る

creating-opencode-plugins

メタ

このスキルは、開発者がコマンド、ファイル、LSP操作など25種類以上のイベントタイプにフックするOpenCodeプラグインを作成することを支援します。JavaScript/TypeScriptモジュール向けに、プラグイン構造、イベントAPI仕様、および実装パターンを提供します。カスタムイベント駆動ロジックでOpenCode AIアシスタントのライフサイクルをインターセプト、監視、または拡張する必要がある場合にご利用ください。

スキルを見る

sglang

メタ

SGLangは、高性能なLLMサービングフレームワークであり、RadixAttentionプレフィックスキャッシュを活用したJSON、正規表現、エージェントワークフロー向けの高速で構造化された生成を特長とします。特にプレフィックスが繰り返されるタスクにおいて、大幅に高速な推論を実現し、複雑な構造化出力やマルチターン対話に最適です。制約付きデコードが必要な場合や、広範なプレフィックス共有を伴うアプリケーションを構築する場合は、vLLMなどの代替案ではなくSGLangを選択してください。

スキルを見る