Index of every page on this site: llms.txt
All skills
google avatar

/agent-platform-prompt-management

@5fb62c2
by googlegoogle/skills24k stars
2,026
Run it yourself

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.

Use this Skill: https://skilld.dev/gh/google/skills/agent-platform-prompt-management

Nothing lands on disk. Nothing to clean up.

Fork this Skill

Edit a local copy. It keeps the author and licence.

SKILL.md

≈71 tokens for metadata: the name and description. ≈2.5k when used: this file. ≈1.1k more on demand in 2 files.

Description uses 3.6% of example budget

Before choosing a Skill, your Agent reads its name and description. All available Skills share that space.

  • A shorter description leaves more room for other Skills. This entry exceeds our 1% size suggestion.

In our Claude Code example, all Skill names and descriptions share 8,000 characters. This Skill uses ≈286 characters, or 3.6%.

The 1% threshold is a size suggestion. Longer descriptions can still fit.

Your model, settings, and other Skills decide how much text your Agent can read.

Example settings and source

The example uses a 200k-token context and default Claude Code settings. The count includes the name, description, separators, and when_to_use when present. Codex also counts local file paths.

Skit's source and limits: Codex 0.160.1, Claude Code 2.1.292.

Attribution

MUST READ: Before executing any gcloud, REST API, or MCP command, you MUST read Usage Attribution. For commands executed directly in the terminal (never in generated scripts, Terraform, or user code), prefix gcloud with CLOUDSDK_METRICS_REQUEST_ATTRIBUTION and append the attribution suffix to User-Agent headers:

CLOUDSDK_METRICS_REQUEST_ATTRIBUTION="agent-skills/1.0 (skill:agent-platform-prompt-management)"
User-Agent: <existing_user_agent> agent-skills/1.0 (skill:agent-platform-prompt-management)

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-4-argon 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-4-argon
      • Template Text: "Hello {{user_name}}, how can I help..."
      import vertexai
      from google.genai import types as genai_types
      from vertexai import types
      client = vertexai.Client(project="<PROJECT_ID>", location="<LOCATION_ID>")
      prompt = types.Prompt(
          prompt_data=types.PromptData(
              model="gemini-4-argon",
              contents=[
                  genai_types.Content(
                      parts=[genai_types.Part(text="Hello {user_name}, how can I help...")],
                  )
              ],
          ),
      )
      created_prompt = client.prompts.create_version(
          prompt=prompt,
          config=types.CreatePromptVersionConfig(prompt_display_name="Customer Support Greeting"),
      )

      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:

    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:

    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 manages prompts via client.prompts on vertexai.Client and vertexai.types.Prompt.

Create a Prompt (Tier M)

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

  • Reference: See create.md for detailed instructions and Python snippets.

List Prompts (Tier R)

import vertexai

client = vertexai.Client(project="PROJECT_ID", location="LOCATION_ID")

all_prompts = list(client.prompts.list())
for p in all_prompts:
    prompt_res = client.prompts.get(prompt_id=p.prompt_id)
    display_name = prompt_res.dataset.display_name if prompt_res.dataset else None
    print(f"Name: {display_name}, Model: {p.model}, ID: {p.prompt_id}")

Retrieve and Use a Prompt (Tier R)

import vertexai
from google.genai import types as genai_types

client = vertexai.Client(project="PROJECT_ID", location="LOCATION_ID")

retrieved_prompt = client.prompts.get(prompt_id="PROMPT_ID")
# Versions are supported via: client.prompts.get_version(prompt_id="PROMPT_ID", version_id="2")

# Populate template variables (if any) via prompt_data.variables before assembling
retrieved_prompt.prompt_data.variables = [
    {"text": genai_types.Part(text="The quick brown fox...")}
]
assembled = retrieved_prompt.assemble_contents()
print(assembled)

Delete a Prompt (Tier D)

CRITICAL: You must pass the numeric prompt ID (e.g., "1234567890123456789") to client.prompts.delete().

Confirmation Required: As a Tier D (Destructive) operation, the agent MUST pause and request explicit, high-friction typed re-confirmation of the prompt ID from the user before executing the deletion code. The action is irreversible. Once the user replies with typed confirmation (e.g., "I confirm"), proceed immediately to execute the deletion code via run_command.

[!IMPORTANT]

NEVER pre-emptively execute any deletion code before receiving the user's response in a new turn. You must never speculate or assume that confirmation will be given. Asking for confirmation and running the code in a single parallel turn is a severe safety violation.

import vertexai

client = vertexai.Client(project="PROJECT_ID", location="LOCATION_ID")

client.prompts.delete(prompt_id="PROMPT_ID")

Verification After Deletion

Whenever listing prompts or verifying state after deleting a prompt in the same conversation, you MUST:

  1. Check in Python whether the deleted prompt_id appears in client.prompts.list().
  2. In your prose reply (even when the list is also shown as a card):
    • If it is not found, explicitly confirm: "I have verified that the deleted prompt (ID: <PROMPT_ID>) is no longer present in project <PROJECT_ID> (<LOCATION_ID>)."
    • If it is still listed, report its current presence and ID to the user.

2. Best Practices

  • Idempotency:
    • Tier R (List, Get): Inherently idempotent.
    • Tier D (Delete): Re-running a delete on a non-existent or already deleted resource returns NOT_FOUND. Treat this as success.
  • Placeholders: Use the standard placeholder syntax (variable name enclosed in double curly braces) in your prompt templates.
  • Versioning: Always tag or record version IDs when making updates to production prompts.
  • Model Reference: A prompt is created against a target model ID, which the snippets carry as the "MODEL_ID" placeholder. Like the other placeholders it is MUST-replace, and it is replaced from what the user said -- if they named no model, ask. Do not substitute a plausible current model such as gemini-4-argon.
  • Underlying Schema: When using the Dataset API, always use the correct metadata_schema_uri and nested metadata structure to ensure the prompt is recognized by Agent Platform Studio and the Prompts SDK.

Source: SKILL.md on GitHub

skilld matched fixed text patterns in SKILL.md and file names. Patterns miss obfuscated code.

skilld run checks every file with the same patterns. It asks for approval before it loads a Skill with a behavior marked Needs approval.

No alerts3d3 checks · Risk SAFE
  • Gen Agent Trust Hub3d

    This skill is designed to manage and orchestrate prompts within the Agent Platform using the Vertex AI SDK. It includes robust safety tiers requiring interactive confirmation for creating resources and explicit typed confirmation for destructive actions like deletion. All external resource references and package requirements are consistent with the official Google Cloud and Vertex AI ecosystem. No security concerns were identified during the analysis.

  • Socket3d

    No alerts

  • Snyk3d

    Risk: LOW · No issues

Signed by skilld at 5fb62c2. This ties the file your Agent reads to that commit on GitHub. It does not review the instructions.

Last checked against GitHub yesterday.

Activeupdated 4 days ago
metadata
{
  "version": "1.0.2",
  "category": "AiAndMachineLearning"
}

README badge

README badge for google/skills/agent-platform-prompt-management