MCPInstall

quarterly-review

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

Installs
1.4K
Last 24h
—
Trending rank
—
Security
Not audited

Install

Works with every agent the skills CLI supports.

npx skills add https://github.com/anthropics/knowledge-work-plugins --skill quarterly-review
  1. 01

    Install

    Run the command in your project. The CLI asks which agents to install for.

  2. 02

    Describe the task

    Ask your agent for something this skill covers. It loads quarterly-review automatically when relevant.

  3. 03

    Review the result

    The agent follows the SKILL.md steps, scripts and references bundled with the skill.

SKILL.md

The instructions your agent reads when the skill is triggered.

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.

FAQ

What does the quarterly-review skill do?

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

How do I install quarterly-review?

Run npx skills add https://github.com/anthropics/knowledge-work-plugins --skill quarterly-review in your project. The skills CLI detects the agents you use and copies the skill into the right folder. For Claude Code you can also place the skill folder at ~/.claude/skills/quarterly-review/ (personal) or .claude/skills/quarterly-review/ (project).

Which AI agents can use quarterly-review?

Any agent that supports the open Agent Skills format (a folder with a SKILL.md file), including Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, Windsurf, Cline, OpenCode and more.

Is quarterly-review safe to install?

No partner security audit is available yet. Skills can run commands and scripts, so read the SKILL.md and any bundled files before installing.

Who maintains quarterly-review?

It is published by anthropics in anthropics/knowledge-work-plugins, and it is an official skill from the maker of the technology it covers. It has 1,403 recorded installs.

More from anthropics/knowledge-work-plugins

View all →

data-visualization

anthropics/knowledge-work-plugins

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.

OfficialFrontend & Design13.8K installs

documentation

anthropics/knowledge-work-plugins

Write and maintain technical documentation. Trigger with "write docs for", "document this", "create a README", "write a runbook", "onboarding guide", or when the user needs help with any form of technical writing — API docs, architecture docs, or operational runbooks.

OfficialDocs & Writing10.3K installs

code-review

anthropics/knowledge-work-plugins

Review code changes for security, performance, and correctness. Trigger with a PR URL or diff, "review this before I merge", "is this code safe?", or when checking a change for N+1 queries, injection risks, missing edge cases, or error handling gaps.

OfficialCode Quality & Workflow9.9K installs

build-dashboard

anthropics/knowledge-work-plugins

Build an interactive HTML dashboard with charts, filters, and tables. Use when creating an executive overview with KPI cards, turning query results into a shareable self-contained report, building a team monitoring snapshot, or needing multiple charts with filters in one browser-openable file.

OfficialData & Databases9.1K installs

system-design

anthropics/knowledge-work-plugins

Design systems, services, and architectures. Trigger with "design a system for", "how should we architect", "system design for", "what's the right architecture for", or when the user needs help with API design, data modeling, or service boundaries.

OfficialFrontend & Design7.5K installs

memory-management

anthropics/knowledge-work-plugins

Two-tier memory system that makes Claude a true workplace collaborator. Decodes shorthand, acronyms, nicknames, and internal language so Claude understands requests like a colleague would. CLAUDE.md for working memory, memory/ directory for the full knowledge base.

Official7.5K installs

Popular code quality & workflow skills

View category →

grill-me

mattpocock/skills

A relentless interview to sharpen a plan or design.

Scan a codebase for deepening opportunities, present them as a visual HTML report, then grill through whichever one you pick.

handoff

mattpocock/skills

Compact the current conversation into a handoff document for another agent to pick up.

domain-modeling

mattpocock/skills

Build and sharpen a project's domain model. Use when discussing codebase terminology, writing or editing a GLOSSARY.md, or recording or editing an ADR.

codebase-design

mattpocock/skills

Shared vocabulary for designing deep modules. Use when the user wants to design or improve a module's interface, find deepening opportunities, decide where a seam goes, make code more testable or AI-navigable, or when another skill needs the deep-module vocabulary.

diagnosing-bugs

mattpocock/skills

Diagnosis loop for hard bugs and performance regressions. Use when the user says "diagnose"/"debug this", or reports something broken/throwing/failing/slow.