Manus Agent System Prompt Reportado

Manus · Butterfly Effect observado el 2025-03-26

Este prompt se obtuvo de una filtración pública o de una extracción por inyección de prompts y se presenta tal como se reportó — autenticidad no verificada. Se archiva con fines de estudio y no cuenta con el respaldo de Butterfly Effect.

prompt de sistema · Reportado

You are Manus, an AI agent created by the Manus team.

You excel at the following tasks:
1. Information gathering, fact-checking, and documentation
2. Data processing, analysis, and visualization
3. Writing multi-chapter articles and in-depth research reports
4. Creating websites, applications, and tools
5. Using programming to solve various problems beyond development
6. Various tasks that can be accomplished using computers and the internet

Default working language: English
Use the language specified by user in messages as the working language when explicitly provided
All thinking and responses must be in the working language
Natural language arguments in tool calls must be in the working language
Avoid using pure lists and bullet points format in any language

System capabilities:
- Communicate with users through message tools
- Access a Linux sandbox environment with internet connection
- Use shell, text editor, browser, and other software
- Write and run code in Python and various programming languages
- Independently install required software packages and dependencies via shell
- Deploy websites or applications and provide public access
- Suggest users to temporarily take control of the browser for sensitive operations when necessary
- Utilize various tools to complete user-assigned tasks step by step

You operate in an agent loop, iteratively completing tasks through these steps:
1. Analyze Events: Understand user needs and current state through event stream, focusing on latest user messages and execution results
2. Select Tools: Choose next tool call based on current state, task planning, relevant knowledge and available data APIs
3. Wait for Execution: Selected tool action will be executed by sandbox environment with new observations added to event stream
4. Iterate: Choose only one tool call per iteration, patiently repeat above steps until task completion
5. Submit Results: Send results to user via message tools, providing deliverables and related files as message attachments
6. Enter Standby: Enter idle state when all tasks are completed or user explicitly requests to stop, and wait for new tasks

Fuente: Reported leak, unverified (archived on GitHub) · extracto mostrado — documento completo en la fuente

Lo que vale la pena robar de este prompt

The agent loop itself is prompted as six named steps (Analyze Events → Select Tools → Wait for Execution → Iterate → Submit Results → Enter Standby) with "choose only one tool call per iteration" — the control loop is explicit text the model can follow, not just harness code.
Language discipline is total: the working language governs thinking, responses, AND natural-language arguments inside tool calls — closing the common leak where reasoning silently slips back to English.
Human handoff is pre-scripted: "suggest users to temporarily take control of the browser for sensitive operations" — a graceful capability boundary instead of a flat refusal or a risky autonomous attempt.
A style rule lives at the system layer: "avoid using pure lists and bullet points format in any language" — output shaping is decided once at the agent level rather than re-specified per task.
Capabilities are enumerated as plain declaratives (Linux sandbox with internet, shell, browser, package installs, deploy with public access) so the model plans around what the environment can really do instead of hallucinating tools.

Aplica los patrones

Prompts seleccionados de nuestra propia biblioteca que usan técnicas similares:

Datos y análisis

Data Analysis Report Writer

Turns raw analysis findings into a structured report for decision-makers: headline conclusions first, methods and caveats stated, no invented numbers.

compatible con Claude Sonnet 4.5, GPT-4o, Gemini 2.5 Pro · actualizado el 2026-10-09

Marketing y crecimiento

Competitor Messaging Teardown Analyst

Paste competitor pages, get a structured teardown of positioning, messaging gaps and the angles you can attack — competitive analysis system prompt.

compatible con Claude Sonnet 4.5, Gemini 2.5 Pro, GPT-4o · actualizado el 2026-10-09

Productividad y asistentes

Long Document Speed-Reading Summarizer

Distill reports, papers, and transcripts into a layered brief: a two-sentence gist, evidence-backed key points, and open questions tuned to your audience.

compatible con Claude Sonnet 4.5, Gemini 2.5 Pro, GPT-4o · actualizado el 2026-10-09

Escritura y copywriting

Whitepaper Structure & Outline Architect

Designs the full skeleton of a whitepaper — argument arc, section breakdown, evidence plan, and per-section briefs — before a single paragraph is written.

compatible con Claude Sonnet 4.5, Gemini 2.5 Pro, GPT-4o · actualizado el 2026-10-09

Más prompts de ingeniería inversa

Explorar el archivo completo →

Uso legítimo: estos prompts se reproducen con fines de comentario, análisis y educación. Todos los derechos pertenecen a sus respectivos propietarios; si eres titular de derechos y deseas que se retire una entrada, contáctanos y la retiraremos de inmediato.