Agent Platform Model Registry
Agent Platform Model Registry Management. Use when you need to upload, list, describe, update, or delete machine learning models (and their versions) in the Agent Platform Model Registry. Don't use for model training, model deployment to endpoints, or managing non-Agent Platform models.
Get the complete skill folder, including its scripts and reference files.
When to use this skill
Use Agent Platform Model Registry when an AI agent needs a reusable SKILL.md workflow for this job: Agent Platform Model Registry Management. Use when you need to upload, list, describe, update, or delete machine learning models (and their versions) in the Agent Platform Model Registry. Don't use for model training, model deployment to endpoints, or managing non-Agent Platform models.
When not to use it
Skip Agent Platform Model Registry when the task is outside the creativity category, or when a more specific skill in this directory already covers the same workflow with clearer triggers.
How to install
Where will you use it?
mkdir -p ~/.claude/skills/agent-platform-model-registry # Save SKILL.md to ~/.claude/skills/agent-platform-model-registry/SKILL.md
- Claude Code personal install: place the skill and its bundled files at ~/.claude/skills/agent-platform-model-registry/SKILL.md. For a shared project, commit the folder at .claude/skills/agent-platform-model-registry/ instead.
- Current Claude Code detects SKILL.md changes in watched directories during the session. If you just created a top-level skills directory, run /reload-skills. Check that the skill is listed before testing its trigger.
- For Claude chat or Cowork in the Desktop app, manage uploaded skills in Customize > Skills; copying files into a local Claude Code folder is not a Desktop install. Other agents may use different install locations.
Full install guide for Claude, Cursor, and Codex →
Try a starter prompt
After installing the skill, paste this starter prompt into your agent to verify it triggers on a small task.
Use the Agent Platform Model Registry skill for this task: Use Agent Platform Model Registry when this documented workflow matches the task. Confirm any required inputs or files before making changes.
What supports this recommendation?
71/100 provisional content score. This measures documentation, practical detail and source signals. It is not a measured task success rate or a security certification.
- Documentation
- 77/100
- Practical detail
- 68/100
- Source evidence
- 63/100
- Source signals
- 72/100
Model compatibility evidence
- claudeuntested
No model-specific signal or recorded compatibility test was found.
- chatgptuntested
No model-specific signal or recorded compatibility test was found.
- geminiinferred
The skill text mentions Gemini or a closely associated term. This is keyword-derived compatibility; no hands-on model test is recorded.
- copilotuntested
No model-specific signal or recorded compatibility test was found.
- llamauntested
No model-specific signal or recorded compatibility test was found.
- perplexityuntested
No model-specific signal or recorded compatibility test was found.
- mistraluntested
No model-specific signal or recorded compatibility test was found.
- grokuntested
No model-specific signal or recorded compatibility test was found.
Inferred compatibility is based on content signals. Check the app, its available tools and setup requirements before running a skill.
What this skill does
# Agent Platform Model Registry Management
## Overview
This skill provides instructions for managing machine learning models in the Agent Platform Model Registry. It covers listing models, describing model details, uploading new models or versions, updating metadata, and deleting models.
## Safety & Confirmation Tiers (CRITICAL)
Before executing any commands on behalf of the user, you MUST adhere to the following safety tiers based on the action requested:
1. **Tier R: Read-only (`list`, `describe`, `get`)** * No confirmation needed. Execute immediately to gather information. 2. **Tier M: Mutating & Reversible (`upload`, `update`)** * Requires **interactive confirmation** with 'Yes'/'No' options. The confirmation prompt MUST contain the exact, literal command string with all required flags (e.g. `--region=us-central1`, `--project=...`, `--display-name="..."`) — natural-language paraphrases are NOT sufficient. * **Same-turn restriction**: NEVER execute the command in the same turn as receiving the request or presenting the confirmation prompt! In Turn 1, you MUST ONLY present the interactive confirmation card with the exact, literal command string. Stop and wait for the user's reply; only execute in the subsequent turn after explicit 'Yes' / approval. Executing `upload` or `update` in Turn 1 without prior confirmation is strictly prohibited. * **Mid-flow parameter changes / rejection**: If the user rejects the prompt or changes any parameters (e.g., display name, description, parent model), do NOT execute the old command. Adapt immediately and present a NEW confirmation prompt with the updated literal command and wait for approval. 3. **Tier D: Destructive & Irreversible (`delete`)** * Requires **explicit typed confirmation** (e.g. "I confirm" or "Yes, delete it"). Ask for confirmation IMMEDIATELY — before any pre-flight checks (don't check if the model is deployed to endpoints first). * **Same-turn restriction**: NEVER execute in the same turn as asking for typed confirmation. Wait for the user to reply in a new turn. * **Mid-flow target changes**: If the user changes their mind (e.g., "delete the second model instead"), do NOT delete the first model. Present a fresh typed confirmation prompt for the newly selected model ID and wait for approval. 4. **Cost Estimation**: Model Registry operations manage catalog metadata and stored model artifacts without provisioning serving compute or endpoints. Do NOT call the `estimate_cost` tool for Model Registry actions, as `estimate_cost` is designed for serving infrastructure (endpoints/batch prediction) and will return an error if called for registry operations. If including cost in the preview card, state that Model Registry operations incur no serving compute charges ($0.00 compute charges; standard Cloud Storage pricing applies to model artifacts).
## Phase 0: Environment Setup & Parameter Resolution
**CRITICAL**: Before running any commands, verify that all necessary parameters are known:
1. **Missing Region or Project**: Follow the base environment grounding policy: if a session location or project is already set from prior turns, reuse it without re-asking. If missing from both prompt and session context, at most one direct lookup is permitted (e.g. `gcloud config get project` or `gcloud config get compute/region`). If still unresolved or ambiguous, pause and explicitly ask the user for the missing parameter before executing mutating or resource-specific commands. 2. **Missing Model ID**: If the user asks to update or describe a model without providing the model ID, pause and ask the user for the model ID, or offer to list models first to help them find it. 3. **Placeholder Substitution**: If the user's requested display name contains a placeholder token (e.g., `<unique-suffix>`, `[suffix]`, or `<timestamp>`), generate a short unique alphanumeric string or timestamp and substitute it cleanly. Never pass unexpanded literal placeholder tokens to the API. 4. **Region and Project Flags**: Always pass `--region=$LOCATION_ID` and `--project=$PROJECT_ID` explicitly on all `gcloud ai models` commands. Do NOT use `global`.
## 1. Listing Models (Tier R)
Use this command to discover existing models in the registry and retrieve their numeric IDs. No confirmation is required.
Always pass `--limit`. A project can hold thousands of models, and an unbounded list pages through every one of them, which can take over a minute and return hundreds of KB of output. Results come back most recently updated first, so `--limit=50` returns the newest models in a few seconds.
```bash gcloud ai models list \ --region=$LOCATION_ID \ --project=$PROJECT_ID \ --limit=50 ```
* Keep `--limit=50` when the user asks to list "all" models, and say the reply shows the 50 most recently updated models. Do NOT page through the whole registry (with gcloud or `Model.list()`) unless the user asks for a count or the complete inventory; offer to look up a specific model by display name instead. * If the user pushes back and asks for the complete inventory, drop `--limit` and print one compact line per model with `--format="value(name.basename(),displayName)"`. Warn that this can take a minute or more in a large project. * If the user asks how many models there are, count the IDs without printing the list. There is no count API, so this still pages through every model (about a minute per 1,500 models); tell the user it may take a while. Do not run a `--limit` list first.
```bash gcloud ai models list \ --region=$LOCATION_ID \ --project=$PROJECT_ID \ --format="value(name)" | wc -l ``` * Do NOT use `--filter` or `--sort-by` to narrow the list. gcloud applies both client-side after fetching every page, so they are as slow as an unbounded list. * To find a model by display name (e.g. to confirm an upload or deletion), filter on the server with the Python SDK:
```bash python3 - <<'PY' from google.cloud import aiplatform
aiplatform.init(project='<PROJECT_ID>', location='<LOCATION_ID>') for m in aiplatform.Model.list(filter='display_name="<DISPLAY_NAME>"'): print(m.name, m.display_name, m.create_time) PY ```
## 2. Describing a Model (Tier R)
Retrieve the full metadata for a specific model or version. No confirmation is required.
```bash gcloud ai models describe $MODEL_ID \ --region=$LOCATION_ID \ --project=$PROJECT_ID ```
To target a specific version:
```bash gcloud ai models describe ${MODEL_ID}@${VERSION_ID} \ --region=$LOCATION_ID \ --project=$PROJECT_ID ```
## 3. Uploading a Model (Tier M)
Register a new model or a new version of an existing model. This is a long-running operation. **Action requires an inline confirmation card before proceeding.**
### Example: Uploading a Custom Model
```bash gcloud ai models upload \ --region=$LOCATION_ID \ --project=$PROJECT_ID \ --display-name="<DISPLAY_NAME>" \ --container-image-uri="<CONTAINER_IMAGE_URI>" \ [--artifact-uri="<ARTIFACT_URI>"] ```
> [!IMPORTANT] > > This is a Tier M operation — see [Safety & Confirmation Tiers] above. > > - If the user specifies "with no artifact URI", omit `--artifact-uri`. > - If registering a new version of an existing model, include > `--parent-model=$PARENT_MODEL_ID`. > - Substitute `<DISPLAY_NAME>` with the exact name requested by the user.
## 4. Updating a Model (Tier M)
Update metadata fields like display name or description. Note that `gcloud ai models` does NOT have an `update` subcommand. Instead, model metadata updates MUST be executed using the Vertex AI Python SDK (`google.cloud.aiplatform.Model`).
**Action requires an inline confirmation card containing the exact script before proceeding.**
```bash python3 -c " from google.cloud import aiplatform
aiplatform.init(project='$PROJECT_ID', location='$LOCATION_ID') model = aiplatform.Model('$MODEL_ID') model.update(display_name='<NEW_DISPLAY_NAME>', description='<NEW_DESCRIPTION>') print(f'Successfully updated model: {model.resource_name}') " ```
> [!IMPORTANT] > > This is a Tier M operation — see [Safety & Confirmation Tiers] above. > > - If only updating the display name, pass > `model.update(display_name='<NEW_DISPLAY_NAME>')`. > - If only updating the description, pass > `model.update(description='<NEW_DESCRIPTION>')`. > - The confirmation card MUST display the exact python command snippet above. > NEVER execute in Turn 1; wait for explicit user approval.
## 5. Deleting a Model (Tier D)
Permanently delete a Model and all its versions. **Action requires explicit typed confirmation before proceeding.**
```bash gcloud ai models delete $MODEL_ID \ --region=$LOCATION_ID \ --project=$PROJECT_ID ```
> [!WARNING] > > This operation is irreversible. All model versions must be undeployed from all > Endpoints before deletion.
## 6. Searching Publisher Models (Tier R)
Before generating interactive model details, you MUST verify the `model_id` by searching Model Garden Publisher Models. No confirmation is required.
Use the `gcloud ai` CLI to search for matching publisher models.
```bash gcloud ai model-garden models list --model-filter="<model_name_or_query>" --full-resource-name --format=json ```
This will return a list of matching models. Extract the exact `name` field from the result (e.g., `publishers/google/models/gemma2` or `publishers/qwen/models/qwen3-coder`) to use as the verified `model_id`.
Intended uses
- Use Agent Platform Model Registry when this documented workflow matches the task.
Implementation notes
- Review the source instructions and adapt inputs before running the workflow.
Try it, then tell us how it went
A copied prompt does not tell us whether the task worked. Report your result after checking the output. We collect your tool and outcome, never your files or prompt.