anthropics/knowledge-work-plugins

quarterly-review

Generates a full QBR narrative — revenue trend, margin trend, customer health, top opportunities and risks — as a presentation-ready PDF or deck.

ソースを見る

使い方

  1. インストールコマンドをコピーし、自分の環境へ導入する前にソースを確認します。
  2. 必要なツール、認証情報、対応環境を原文で確認します。
  3. 入力と成果物を指定し、出力を資料と照合します。
npx skills add https://github.com/anthropics/knowledge-work-plugins --skill quarterly-review

開始前の確認

  • 導入にはモデル契約、API枠、ファイルへのアクセス許可は含まれません。
  • スター数や導入数は活動の指標であり、独立した品質・安全性試験ではありません。
リポジトリの原文

見出し、例、コード、表、リンク、参照画像を含む原文を表示しています。

Run the quarterly business review. Pull financial, sales, and customer data for the quarter, synthesize it into a narrative, and produce a presentation-ready document.

Parse arguments:

  • --quarter (default: previous calendar quarter) — format YYYY-QN (e.g., 2026-Q1)
  • --save-to (default: files) — files (Google Drive / OneDrive), desktop, or both

Step 1 — Financial performance

Using the business-pulse skill in deep mode:

  1. Pull QuickBooks P&L for the quarter: revenue, COGS, gross margin, operating expenses, net margin.
  2. Compare to prior quarter and same quarter last year (if available).
  3. Pull PayPal settlements for the same period to validate QB revenue.
  4. Calculate: revenue growth %, margin change in points, top 3 revenue categories.

Step 2 — Customer health

  1. Pull HubSpot deal data: new customers won, churned, average deal size, pipeline entering next quarter.
  2. Calculate customer acquisition cost (if data available) and revenue per customer.
  3. Flag any customers representing >20% of revenue (concentration risk).

Step 3 — Top opportunities

Identify 3 specific opportunities for next quarter based on the data:

  • Revenue upside (category, customer segment, or channel to double down on)
  • Margin upside (cost to cut or price to raise)
  • Customer upside (segment to target or churn to reduce)

Step 4 — Top risks

Identify 3 specific risks for next quarter:

  • Revenue risk (concentration, trend, seasonality)
  • Margin risk (rising cost, pricing pressure)
  • Operational risk (pipeline gap, vendor dependency)

Step 5 — QBR narrative

Write a 500–800 word narrative in plain business English with this structure:

  1. Quarter headline (one sentence)
  2. Revenue story (trend + why)
  3. Margin story (trend + why)
  4. Customer story (health + pipeline)
  5. Three opportunities
  6. Three risks
  7. One-paragraph call to action for next quarter

Step 6 — Export

Generate:

  1. `qbr-{YYYY-QN}.pdf` — formatted narrative + key charts (as ASCII tables if no chart tool available)
  2. Save to --save-to location

Connector failures

If QuickBooks is unreachable, stop — the QBR requires QB financial data as the foundation. If PayPal is missing, skip cross-validation and note "PayPal not connected — revenue validated from QB only." If HubSpot is missing, skip customer health (Step 2) and note "HubSpot not connected — customer health section skipped."

Approval gates

  • Never publish or email the QBR automatically. Always display for owner review first.
  • Flag if any data source returns incomplete data — note gaps in the narrative.

Output

Present the narrative in-line, then confirm export. End with a one-paragraph "what to focus on next quarter" summary.

タスクに関連する項目

同じリポジトリから

関連する Skills

すべての Skills
anthropics
公式

contract-review

Lightweight NDA, MSA, and vendor contract review for SMBs without legal on staff. Reads contracts from local files, mail attachments (Gmail or M365), a connected file store (Google Drive or M365), or DocuSign envelopes; flags non-standard terms; explains risks in plain English; and outputs a marked-up redline as a separate DOCX. Use when the user says "review this contract," "what am I signing," "red flags," "flag any concerns," "check the payment terms," or uploads/forwards a contract or legal

1時間の導入数
2
GitHub Stars
3.7万
更新日
11月21日
anthropics
公式

process-doc

Document a business process — flowcharts, RACI, and SOPs. Use when formalizing a process that lives in someone's head, building a RACI to clarify who owns what, writing an SOP for a handoff or audit, or capturing the exceptions and edge cases of how work actually gets done.

1時間の導入数
1
GitHub Stars
3.7万
更新日
11月20日
anthropics
公式

data-visualization

Create effective data visualizations with Python (matplotlib, seaborn, plotly). Use when building charts, choosing the right chart type for a dataset, creating publication-quality figures, or applying design principles like accessibility and color theory.

1時間の導入数
5
GitHub Stars
3.7万
更新日
11月20日
anthropics
公式

accessibility-review

Run a WCAG 2.1 AA accessibility audit on a design or page. Trigger with "audit accessibility", "check a11y", "is this accessible?", or when reviewing a design for color contrast, keyboard navigation, touch target size, or screen reader behavior before handoff.

1時間の導入数
4
GitHub Stars
3.7万
更新日
11月20日