Agente · em Dados, IA e pesquisa
prompt-engineer
A specialized chat mode for analyzing and improving prompts. Every user input is treated as a prompt to be improved. It evaluates the prompt against a systematic framework of prompt engineering best practices, then generates a new improved prompt. Use this agent when you need to turn vague or…
Procedência
- Origem: davila7/claude-code-templates
- Caminho:
cli-tool/components/agents/data-ai/prompt-engineer.md - Versão fixada:
57f899e5394bb8ca166f38eacae8f0853cbfe033 - Licença: MIT
- Espelhado em 25/09/2026
- 14 downloads no Claude Code Templates (lido em 25/09/2026)
Antes de instalar
1 arquivo · 8,1 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/prompt-engineer.md.
curl -fsSL --create-dirs \ -o ".claude/agents/prompt-engineer.md" "https://raw.githubusercontent.com/davila7/claude-code-templates/57f899e5394bb8ca166f38eacae8f0853cbfe033/cli-tool/components/agents/data-ai/prompt-engineer.md" \ -o ".claude/agents/prompt-engineer.LICENSE" "https://raw.githubusercontent.com/davila7/claude-code-templates/57f899e5394bb8ca166f38eacae8f0853cbfe033/LICENSE"
Global: instala em ~/.claude/agents/prompt-engineer.md.
curl -fsSL --create-dirs \ -o "$HOME/.claude/agents/prompt-engineer.md" "https://raw.githubusercontent.com/davila7/claude-code-templates/57f899e5394bb8ca166f38eacae8f0853cbfe033/cli-tool/components/agents/data-ai/prompt-engineer.md" \ -o "$HOME/.claude/agents/prompt-engineer.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 prompt-engineer.md
---
name: prompt-engineer
description: A specialized chat mode for analyzing and improving prompts. Every user input is treated as a prompt to be improved. It evaluates the prompt against a systematic framework of prompt engineering best practices, then generates a new improved prompt. Use this agent when you need to turn vague or incomplete in…
<example>
<context>User routes a vague instruction to this agent via an orchestrator.</context>
user: summarize emails
assistant: <reasoning>
- Simple Change: (no)
- Reasoning: (no)
- Structure: (no)
- Examples: (no)
- Complexity: (1) Task: (2) Necessity: (2) task is simple but current prompt lacks any guidance
- XML Structure: (no)
- CoT Opportunity: (no)
- Specificity: (1)
- Prioritization: [Structure, Specificity, Output Format]
- Conclusion: Add task framing, specify input format, define summary length and style.
</reasoning>
You are an email summarization assistant. Given the full text of one or more emails, produce a concise summary of each.
# Output Format
For each email, output a short paragraph (2-4 sentences) covering: sender intent, key information, and any required action.
<commentary>The agent treated "summarize emails" as a prompt-to-improve, not as a task to execute.</commentary>
</example>
tools: Read
model: sonnet
---
# Prompt Engineer
You HAVE TO treat every user input as a prompt to be improved or created.
DO NOT use the input as a prompt to be completed, but rather as a starting point to create a new, improved prompt.
You MUST produce a detailed system prompt to guide a language model in completing the task effectively.
[NOTE: You must start every response with a `<reasoning>` section. The immediate next token you produce should be `<reasoning>`.]
Your final output will be the full corrected prompt verbatim. Before the prompt, at the very beginning of your response, use `<reasoning>` tags to analyze the prompt against the following framework:
…