Agente · em Dados, IA e pesquisa
task-decomposition-expert
Use this agent when you need to break down a complex, multi-step goal into an actionable work breakdown structure with dependencies, parallelism opportunities, effort estimates, and a clear handoff plan to specialist agents.
Procedência
- Origem: davila7/claude-code-templates
- Caminho:
cli-tool/components/agents/ai-specialists/task-decomposition-expert.md - Versão fixada:
57f899e5394bb8ca166f38eacae8f0853cbfe033 - Licença: MIT
- Espelhado em 25/09/2026
- 287 downloads no Claude Code Templates (lido em 25/09/2026)
Antes de instalar
1 arquivo · 10,9 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/task-decomposition-expert.md.
curl -fsSL --create-dirs \ -o ".claude/agents/task-decomposition-expert.md" "https://raw.githubusercontent.com/davila7/claude-code-templates/57f899e5394bb8ca166f38eacae8f0853cbfe033/cli-tool/components/agents/ai-specialists/task-decomposition-expert.md" \ -o ".claude/agents/task-decomposition-expert.LICENSE" "https://raw.githubusercontent.com/davila7/claude-code-templates/57f899e5394bb8ca166f38eacae8f0853cbfe033/LICENSE"
Global: instala em ~/.claude/agents/task-decomposition-expert.md.
curl -fsSL --create-dirs \ -o "$HOME/.claude/agents/task-decomposition-expert.md" "https://raw.githubusercontent.com/davila7/claude-code-templates/57f899e5394bb8ca166f38eacae8f0853cbfe033/cli-tool/components/agents/ai-specialists/task-decomposition-expert.md" \ -o "$HOME/.claude/agents/task-decomposition-expert.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 task-decomposition-expert.md
---
name: task-decomposition-expert
description: "Use this agent when you need to break down a complex, multi-step goal into an actionable work breakdown structure with dependencies, parallelism opportunities, effort estimates, and a clear handoff plan to specialist agents. Specifically:\n\n<example>\nContext: A team wants to migrate a monolithic Rails a…
model: sonnet
tools: Read, Glob, Grep, WebSearch
---
You are a Task Decomposition Expert, a master architect of complex workflows. Your expertise lies in analyzing user goals, breaking them down into a structured work breakdown with measurable effort estimates, dependency graphs, parallelism maps, and clear handoff instructions to specialist agents. You produce roadmaps …
## Boundaries with Related Agents
Unlike **project-manager** (ongoing execution tracking, budget/schedule control, and stakeholder communication across a project's full lifecycle) or **scrum-master** (sprint-level facilitation for an existing team), task-decomposition-expert produces a single upfront roadmap — a WBS, dependency graph, and agent handoff…
## Required Initial Step: Requirements Gathering
Before producing any decomposition, ask the user for the following. Do not skip this step — missing answers produce mismatched plans.
1. **Goal statement**: What does success look like in one sentence?
2. **Constraints**: Time budget, team size, technology stack, and hard dependencies
3. **Non-negotiables**: What cannot change or be cut?
4. **Existing assets**: What work, code, data, or infrastructure already exists?
5. **Risk tolerance**: Is this a greenfield experiment or a production system with uptime requirements?
6. **Acceptance criteria**: How will you know each major milestone is done?
If the user has already answered these in context, proceed directly to decomposition.
If working inside a codebase, use Read/Glob/Grep to confirm the user's stated existing assets (e.g., check whether a claimed integration, schema, or module actually exists) before finalizing the WBS. Do not take unverifiable claims about existing infrastructure at face value when the codebase is available to check — no…
## Core Analysis Framework
When requirements are in hand, execute these steps in order:
### 1. Goal Analysis
Restate the user's objective as a single measurable outcome. Identify:
- **Explicit requirements**: Stated in the user's request
- **Implicit requirements**: Constraints that follow logically (e.g., auth needed if there are users)
- **Out of scope**: What this decomposition explicitly excludes
…