Agent Platform Prompt ManagementCAUTION

Agent Skills for Google products and technologies

The instruction file, verbatim from the audited commit — this is the text the model reads, and the surface the audit's instruction layer examines. Quoted here so you can judge it without cloning anything.

---
name: agent-platform-prompt-management
metadata:
  version: "1.0.0"
  category: AiAndMachineLearning
description: >-
  Manages and orchestrates prompts in Agent Platform. Use when you need to create,
  list, retrieve, version, or delete managed prompts in Agent Platform. Don't use
  for model training, model deployment to endpoints, or managing non-Agent Platform
  prompts.
---

## Usage Guide

To use this skill effectively:

1.  **Execute Operations via Python**: Run the Python snippets below using
    `run_command` in the execution environment to manage prompts in Agent
    Platform on behalf of the user. Do not delegate execution to the user or
    claim lack of access once approved.

2.  **No File System Search**: Do not try to find Python files or scripts on the
    file system for these operations.

## Safety & Confirmation Tiers (CRITICAL)

Before executing any commands or scripts on behalf of the user, you must adhere
to the following safety tiers based on the action requested, to prevent
accidental mutation or permanent deletion of prompt resources:

1.  **Tier R: Read-only (`list`, `get`)**
    *   No confirmation needed. Execute immediately to gather information.
2.  **Tier M: Mutating & Reversible (`create`)**

    *   Requires **interactive confirmation** with 'Yes'/'No' options before
        executing prompt creation, to prevent unintended resource proliferation
        or misconfiguration. The confirmation prompt must clearly explain the
        proposed prompt creation and its key parameters (e.g., display name,
        template text, target model). Natural-language paraphrases without
        specifying the parameters are not sufficient.
    *   **Same-turn restriction**: Do not execute the creation code in the same
        turn as presenting the confirmation prompt. Stop and wait for the user's
        reply; only execute after explicit 'Yes' / approval.
    *   Every parameter in the card must trace back to something the user said.
        The target model is a user choice, not a default: if the user did not
        name one, ASK before building the card. Do not carry over the model that
        appears in the examples here or in `references/create.md`.
    *   **Gold Standard Example** — for a user who said "create a prompt called
        Customer Support Greeting for gemini-2.5-pro with the template Hello
        {{user_name}}, how can I help...":

        > I will create a prompt in Agent Platform with the following
        > parameters. Please confirm this information before I proceed:
        >
        > *   **Display Name**: `Customer Support Greeting`
        > *   **Target Model**: `gemini-2.5-pro`
        > *   **Template Text**: "Hello {{user_name}}, how can I help..."
        >
        > Do you confirm? [Yes/No]

3.  **Tier D: Destructive & Irreversible (`delete`)**

    *   Requires **explicit typed confirmation** (e.g. "I confirm" or "Yes,
        delete it") before executing prompt deletion, to prevent accidental
        permanent loss of production prompt assets. Ask for confirmation before
        any pre-flight checks.
    *   **Same-turn restriction**: NEVER execute in the same turn as asking for
        typed confirmation. Wait for the user to reply in a new turn.
    *   **Gold Standard Example**:

        > I will permanently delete the following prompt from Agent Platform.
        > This action is irreversible. Please explicitly type your confirmation
        > (e.g., "I confirm") before I proceed:
        >
        > *   **Prompt ID**: `prompt_12345abc`
        > *   **Display Name**: `Legacy Outdated Prompt`
        >
        > Please type your confirmation to proceed.

## Phase 0: Environment Setup

**CRITICAL**: Before the user runs any of the Python snippets below, you MUST
advise them to ensure the environment is correctly initialized by following
these steps:

1.  **Google Cloud Authentication**: Authenticate with your Google Cloud account
    and configure active Application Default Credentials (ADC) for Agent
    Platform access:

    ```bash
    gcloud auth login
    gcloud auth application-default login
    ```

2.  **Python Dependencies**: This skill needs `google-cloud-aiplatform` and
    `google-genai`. Do **not** create a virtual environment — it starts empty
    and hides packages the environment already provides, forcing a redundant
    install. Probe, and install only what is missing:

    ```bash
    python3 -c "import vertexai, google.genai" \
      || pip install google-cloud-aiplatform google-genai
    ```

3.  **Execution**: Run Python snippets with a plain `python3`. There is no
    environment to activate first.

> [!TIP]
>
> **Placeholder Parameter Replacement:** The Python scripts below use uppercase
> string placeholders (like `"PROJECT_ID"`, `"LOCATION_ID"`, `"PROMPT_ID"`, and
> `"MODEL_ID"`). You **MUST** dynamically replace these placeholders with the
> actual Project ID, Region, Prompt ID, and target model values provided in the
> user's prompt (or discovered context) before generating or providing the
> scripts. If the user did not supply one of these, ask -- a placeholder is
> never satisfied by guessing a plausible value.

## 1. Managing Prompts via Agent Platform SDK

The SDK provides a high-level `Prompt` class in the preview module.

### Create a Prompt (Tier M)

Use when you need to create a new managed prompt in Agent Platform.

*   **Reference**: See [create.md](references/create.md) for detailed
    instructions and Python snippets.

### List Prompts (Tier R)

```python
import vertexai
from vertexai.preview import prompts

vertexai.init(project="PROJECT_ID", location="LOCATION_ID")

all_prompts = prompts.list()
for p in all_prompts:
    print(f"Name: {p.display_name}, ID: {p.prompt_id}")
```

### Retrieve and Use a Prompt (Tier R)

```python
import vertexai
from vertexai.preview import prompts

vertexai.init(project="PROJECT_ID", location="LOCATION_ID")

retrieved_prompt = prompts.get(prompt_id="PROMP

CAUTIONgrade B · trust 89/100 Install with care. The audit found things worth knowing before you trust its output.

What the source does

Filesystem

none-observed

Network

none-observed

Shell

none-observed

Dependencies

pinned

Secrets in source

none-found

Findings (1)

Do not delegate execution to the user or claim lack of access once approved.

Gates applied: no_behavioural_pass.

[![ModelsAtlas audit: Agent Platform Prompt Management](https://modelsatlas.com/skills/google/agent-platform-prompt-management/badge.svg)](https://modelsatlas.com/skills/google/agent-platform-prompt-management/)

Not your listing, or something out of date? Claim or update your listing.