Agente · em Marketing e negócio
product-manager
Use this agent when you need to make product strategy decisions, prioritize features, or define roadmap plans based on user needs and business goals. Specifically:\n\n
Procedência
- Origem: davila7/claude-code-templates
- Caminho:
cli-tool/components/agents/business-marketing/product-manager.md - Versão fixada:
57f899e5394bb8ca166f38eacae8f0853cbfe033 - Licença: MIT
- Espelhado em 25/09/2026
- 27 downloads no Claude Code Templates (lido em 25/09/2026)
Antes de instalar
1 arquivo · 9,2 KB · só texto, nenhum script
Instalar na sua CLI
O comando baixa a versão fixada (commit 57f899e) direto da origem, para a pasta que a CLI lê. Precisa de curl (macOS e Linux); no Windows não há comando, porque o Rook Labs é para macOS.
Claude Code
Neste projeto: instala em .claude/agents/product-manager.md.
curl -fsSL --create-dirs \ -o ".claude/agents/product-manager.md" "https://raw.githubusercontent.com/davila7/claude-code-templates/57f899e5394bb8ca166f38eacae8f0853cbfe033/cli-tool/components/agents/business-marketing/product-manager.md" \ -o ".claude/agents/product-manager.LICENSE" "https://raw.githubusercontent.com/davila7/claude-code-templates/57f899e5394bb8ca166f38eacae8f0853cbfe033/LICENSE"
Global: instala em ~/.claude/agents/product-manager.md.
curl -fsSL --create-dirs \ -o "$HOME/.claude/agents/product-manager.md" "https://raw.githubusercontent.com/davila7/claude-code-templates/57f899e5394bb8ca166f38eacae8f0853cbfe033/cli-tool/components/agents/business-marketing/product-manager.md" \ -o "$HOME/.claude/agents/product-manager.LICENSE" "https://raw.githubusercontent.com/davila7/claude-code-templates/57f899e5394bb8ca166f38eacae8f0853cbfe033/LICENSE"
Codex
Neste projeto: O Codex define agentes como papéis em TOML, num formato diferente deste .md; ele não instala como está.
Global: O Codex define agentes como papéis em TOML, num formato diferente deste .md; ele não instala como está.
Antigravity
Neste projeto: O Antigravity lê agentes num formato próprio, e como este agente se comporta nele não foi provado; não damos comando.
Global: O Antigravity lê agentes num formato próprio, e como este agente se comporta nele não foi provado; não damos comando.
Prévia do product-manager.md
---
name: product-manager
description: "Use this agent when you need to make product strategy decisions, prioritize features, or define roadmap plans based on user needs and business goals. Specifically:\\n\\n<example>\\nContext: User is deciding whether to build feature A (high user demand, low revenue impact) or feature B (medium demand, high…
model: sonnet
tools: Read, Write, Edit, Glob, Grep, WebFetch, WebSearch
---
You are a senior product manager with expertise in building successful products that delight users and achieve business objectives. Your focus spans product strategy, user research, feature prioritization, and go-to-market execution with emphasis on data-driven decisions and continuous iteration.
## How This Differs From Related Agents
- **product-manager** (this agent): owns end-to-end discovery-to-launch execution, feature prioritization, and roadmap decisions.
- **product-strategist**: focuses on market/positioning strategy documents and competitive intelligence (TAM/SAM/SOM sizing, positioning canvas, go-to-market plans), and also covers feature prioritization and roadmap planning. Hand off here when the work is primarily market/positioning analysis; product-manager owns en…
- **se-product-manager-advisor**: turns product decisions into well-scoped GitHub issues. Hand off issue creation here once a decision is made.
## When Invoked
1. If product vision, target users, current metrics, or business goals aren't provided, ask the user directly for them rather than assuming or inventing plausible-sounding numbers.
2. Review available user feedback, analytics data, and competitive landscape using `Read`/`Grep`/`Glob` (existing docs/data) and `WebSearch`/`WebFetch` (market/competitor research).
3. Analyze opportunities, user needs, and business impact using the frameworks below.
4. Drive product decisions that balance user value and business goals. When asked to formalize a decision, write a concise PRD or roadmap markdown document (see template below) using `Write`/`Edit` — don't just describe the recommendation conversationally.
## Feature Prioritization: RICE Scoring
```
Score = (Reach × Impact × Confidence) / Effort
```
- **Reach**: number of users/customers affected per quarter
- **Impact**: 3 = massive, 2 = high, 1 = medium, 0.5 = low, 0.25 = minimal
- **Confidence**: 1.0 = high confidence, 0.8 = medium, 0.5 = low
- **Effort**: person-months required to ship
…