Retail Product Search Agent
google/adk-recipes
Builds a retail product search agent on Google Cloud, from catalog ingestion into BigQuery and Vector Search to ADK scaffolding, evaluation and Cloud Run deployment.
Searches, manages and scaffolds skills in the Gemini Enterprise Agent Platform Skill Registry using bundled Python scripts and Google Cloud credentials.
Install Agent Platform Skill Registry
$ npx skills add google/skills --skill agent-platform-skill-registry -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install google/skills agent-platform-skill-registry --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/google/skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/cloud/agent-platform-skill-registry .claude/skills/agent-platform-skill-registry && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "agent-platform-skill-registry" agent skill from https://github.com/google/skills/tree/main/skills/cloud/agent-platform-skill-registry into .claude/skills/agent-platform-skill-registry/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "agent-platform-skill-registry", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/google/skills/tree/main/skills/cloud/agent-platform-skill-registryType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add google/skills --skill agent-platform-skill-registry -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install google/skills agent-platform-skill-registry --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/google/skills.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/cloud/agent-platform-skill-registry .agents/skills/agent-platform-skill-registry && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "agent-platform-skill-registry" agent skill from https://github.com/google/skills/tree/main/skills/cloud/agent-platform-skill-registry into .agents/skills/agent-platform-skill-registry/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "agent-platform-skill-registry", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add google/skills --skill agent-platform-skill-registry -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install google/skills agent-platform-skill-registry --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/google/skills.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/cloud/agent-platform-skill-registry .cursor/skills/agent-platform-skill-registry && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "agent-platform-skill-registry" agent skill from https://github.com/google/skills/tree/main/skills/cloud/agent-platform-skill-registry into .cursor/skills/agent-platform-skill-registry/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "agent-platform-skill-registry", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/google/skills.git --path skills/cloud/agent-platform-skill-registry--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add google/skills --skill agent-platform-skill-registry -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install google/skills agent-platform-skill-registry --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/google/skills.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/cloud/agent-platform-skill-registry .gemini/skills/agent-platform-skill-registry && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "agent-platform-skill-registry" agent skill from https://github.com/google/skills/tree/main/skills/cloud/agent-platform-skill-registry into .gemini/skills/agent-platform-skill-registry/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "agent-platform-skill-registry", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install google/skills agent-platform-skill-registryInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add google/skills --skill agent-platform-skill-registry -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/google/skills.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/cloud/agent-platform-skill-registry .github/skills/agent-platform-skill-registry && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "agent-platform-skill-registry" agent skill from https://github.com/google/skills/tree/main/skills/cloud/agent-platform-skill-registry into .github/skills/agent-platform-skill-registry/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "agent-platform-skill-registry", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add google/skills --skill agent-platform-skill-registry -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install google/skills agent-platform-skill-registry --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/google/skills.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/cloud/agent-platform-skill-registry .opencode/skills/agent-platform-skill-registry && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "agent-platform-skill-registry" agent skill from https://github.com/google/skills/tree/main/skills/cloud/agent-platform-skill-registry into .opencode/skills/agent-platform-skill-registry/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "agent-platform-skill-registry", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
agent-platform-skill-registry- GitHub stars
- 21k
- Token cost
- ~584 tokens
- SKILL.md length
- 156 words
- Files
- 8 (incl. scripts, references)
- Skills in repo
- 147
- Repo updated
- First seen
- Licence
- Apache-2.0
At a glance
Searches, manages and scaffolds skills in the Gemini Enterprise Agent Platform Skill Registry using bundled Python scripts and Google Cloud credentials.
- Searching the registry for an existing skill before building one
- SKILL.md covers Core Capabilities, Core Directives, Prerequisites & Authentication and Quickstart, plus 1 more section
- Runs Python scripts from its folder; calls pip, gcloud and python3
- Uploading or updating a skill in the registry
What it does
Four areas are covered for the Skill Registry on the Gemini Enterprise Agent Platform: discovering skills (search, list, get one and inspect revision history), lifecycle management (upload, update and permanently delete), monitoring long-running operations, and scaffolding a new skill locally. Each area has its own reference file, and scripts/skill_registry_ops.py is the main entry point.
Before any operation the agent must run scripts/validate_env.py. It expects GCP_PROJECT_ID and GCP_LOCATION, such as us-central1, to be set, plus the google-auth and requests libraries and current Google Cloud credentials. A quickstart search is python3 scripts/skill_registry_ops.py search with a --query and --top-k.
Because the lifecycle area includes permanently deleting skills, confirm the target before you ask for a removal. Long-running state changes return operations whose completion can be checked with the monitoring utility.
When your agent uses it
- Searching the registry for an existing skill before building one
- Uploading or updating a skill in the registry
- Checking whether a long-running registry operation has finished
- Scaffolding a new skill locally before registering it
Example prompts
- “Search the skill registry for skills that handle PDF forms.”
- “Upload my local skill folder to the registry and check that the operation completes.”
- “Show the revision history of the invoice-parser skill.”
- “Generate a starter skill for log analysis that I can register later.”
Requirements
- Python 3 with google-auth and requests
- Google Cloud credentials for the target project
- GCP_PROJECT_ID and GCP_LOCATION environment variables
What it can do on your machine
Read from SKILL.md and the folder at commit 7d97937. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
Ships 3 files in scripts/ (Python), which the agent can run.
Shell commands in SKILL.md call:
pipgcloudpython3
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md. Its commands use pip and gcloud, which can reach the network depending on how they are called.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Agent Platform Skill Registry loads about 584 tokens when it runs, and up to ~2.4k if it reads all its reference files. Until then it costs about 57 tokens; SKILL.md has 156 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.
SKILL.md
The full file from google/skills at commit 7d97937, republished under its Apache-2.0 licence (© google). 156 words, ~584 tokens.
Download SKILL.mdSave it as
.claude/skills/agent-platform-skill-registry/SKILL.md (or your agent's skills folder). This skill also uses 7 other files; get the full folder from GitHub.- name
- agent-platform-skill-registry
- description
- Interact with the Gemini Enterprise Agent Platform Skill Registry to create and search for available skills. Use this skill to enable agents to register functionality or discover new capabilities.
- metadata.version
- 1.0.0
- metadata.category
- AiAndMachineLearning
Skill Registry
This skill provides instructions for interacting with the Skill Registry on the Gemini Enterprise Agent Platform.
Core Capabilities
- Skill Discovery - Query the registry to easily search, list, get specific skills, and inspect revision histories.
- Skill Lifecycle Management - Upload, update, or permanently delete skills.
- Operation Monitoring - Utility to check the completion status of long-running state changes (LROs).
- Generate Skill - Automate the initial scaffolding of new agent skills locally.
Core Directives
Mandatory Validation: ALWAYS execute the environment validation check before performing any operations.
Before any operation, you must validate the core environment.
bash # Execute the validation script python3 scripts/validate_env.py
Prerequisites & Authentication
Library & Authentication
Ensure you have the latest Google Cloud credentials and libraries installed.
# Install required libraries
pip install google-auth requests
# Authenticate with Google Cloud
gcloud auth application-default loginEnvironment Variables
The following variables are required for operations:
GCP_PROJECT_ID: Your Google Cloud Project ID.GCP_LOCATION: The region (e.g.,us-central1).
Quickstart
Quickly search for available skills in the registry:
python3 scripts/skill_registry_ops.py search \
--query "test skill" \
--top-k 5Operations
- Skill Discovery: query-skills.md
- Skill Lifecycle: manage-skills.md
- Monitor Operations: monitor-operations.md
- Generate Skill: generate-skill.md
© google, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
SKILL.md and 7 other files (scripts, references) in skills/cloud/agent-platform-skill-registry of google/skills.
- SKILL.md
- references/generate-skill.md
- references/manage-skills.md
- references/monitor-operations.md
- references/query-skills.md
- scripts/requirements.txt
- scripts/skill_registry_ops.py
- scripts/validate_env.py
Open the folder on GitHubat commit 7d97937
Compare with similar skills
Agent Platform Skill Registry next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Agent Platform Skill Registry this skillgoogle/skills | 21k | — | ~584 | Automated safety check: Pass | Apache-2.0 | |
| Retail Product Search Agentgoogle/adk-recipes | 10k | — | ~3k | Automated safety check: Pass | Apache-2.0 | |
| Vertex AI API DevJetBrains/skills | 364 | 1 repos | ~2.4k | Automated safety check: Pass | None | |
| Google Antigravity SDKgoogle-antigravity/antigravity-sdk-python | 3.7k | — | ~2.1k | Automated safety check: Notes | Apache-2.0 | |
| SkillOpt-Sleep Self-Improvement Cyclemicrosoft/SkillOpt | 18k | — | ~2.3k | Automated safety check: Pass | MIT | |
| Publish Plugins Version Bumpvinta/hal-9000 | 138 | 1 repos | ~1k | Automated safety check: Pass | MIT |
Similar skills
- Official
- Official
Vertex AI API Dev
JetBrains/skills
Guides the usage of Gemini API on Google Cloud Vertex AI with the Gen AI SDK.
Google Antigravity SDK
google-antigravity/antigravity-sdk-python
Design, implement, and debug autonomous AI agents and multi-agent systems using the Google Antigravity (AGY) SDK.
- Official
SkillOpt-Sleep Self-Improvement Cycle
microsoft/SkillOpt
Runs a nightly or on-demand sleep cycle for a local Codex agent: review past sessions, replay recurring tasks and stage validated skill and memory edits for adoption.
Publish Plugins Version Bump
vinta/hal-9000
Finds which plugins in the repository changed, bumps only the ones not already bumped since origin/main, and checks that each plugin's two manifests stay in sync.
Install Skill From GitHub
niki914/zafiro
Install a skill from a public GitHub repository onto this device.
More from google/skills
All 147 skills in this repo- Official
Cloud Trace Querying
google/skills
Query Cloud Trace spans, filter by latency thresholds or error status, correlate distributed traces with Cloud Logging, and diagnose latency bottlenecks across Google Cloud services.
- Official
Google Cloud PAM Helper
google/skills
Manages Google Cloud Privileged Access Manager entitlements and grants: create and edit entitlements, request temporary access, and approve or deny pending grants.
- Official
Agent Platform Alert Configuration
google/skills
Writes Terraform alerting policies for AI agents that emit OpenTelemetry metrics, covering reliability, cost, safety, security and quality signals on Google Cloud.
- Official
Model Garden Deployment
google/skills
Deploys open models or custom weights from Model Garden to Agent Platform endpoints, checks deployment status and cleans up endpoints, confirming before any change.
- Official
GCP Application Design Center Deploy
google/skills
Designs GCP infrastructure as local Terraform, validates and scans it against best practices, then imports it to Application Design Center for deployment and troubleshooting.
- Official
BigQuery Slot and Cost Optimizer
google/skills
Analyzes BigQuery slot use, query costs and execution bottlenecks from INFORMATION_SCHEMA to diagnose slow queries, slot contention and unpartitioned scans.
Related
Works with
Categories
Questions about Agent Platform Skill Registry
What does Agent Platform Skill Registry do?
Searches, manages and scaffolds skills in the Gemini Enterprise Agent Platform Skill Registry using bundled Python scripts and Google Cloud credentials. Four areas are covered for the Skill Registry on the Gemini Enterprise Agent Platform: discovering skills (search, list, get one and inspect revision history), lifecycle management (upload, update and permanently delete), monitoring long-running operations, and scaffolding a new skill locally.py is the main entry point.
When should I use Agent Platform Skill Registry?
Agent Platform Skill Registry fits situations like: searching the registry for an existing skill before building one; uploading or updating a skill in the registry; checking whether a long-running registry operation has finished; scaffolding a new skill locally before registering it.
How do I install Agent Platform Skill Registry in Claude Code?
Run `npx skills add google/skills --skill agent-platform-skill-registry -a claude-code`. Or copy the skill folder (skills/cloud/agent-platform-skill-registry in google/skills) into .claude/skills/agent-platform-skill-registry in your project. Claude Code loads it when a task matches its description.
How do I install Agent Platform Skill Registry in Codex?
Run `npx skills add google/skills --skill agent-platform-skill-registry -a codex`. Or copy the skill folder (skills/cloud/agent-platform-skill-registry in google/skills) into .agents/skills/agent-platform-skill-registry in your project. Codex loads it when a task matches its description.
Can I use Agent Platform Skill Registry in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add google/skills --skill agent-platform-skill-registry -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/agent-platform-skill-registry, .gemini/skills/agent-platform-skill-registry, .github/skills/agent-platform-skill-registry and .opencode/skills/agent-platform-skill-registry in your project.
What does Agent Platform Skill Registry need to run?
Going by SKILL.md and its folder, Agent Platform Skill Registry needs Python for the scripts in its folder and the command-line tools its instructions call (pip, gcloud and python3). Our summary lists: Python 3 with google-auth and requests; Google Cloud credentials for the target project; GCP_PROJECT_ID and GCP_LOCATION environment variables.
Does Agent Platform Skill Registry access the network?
SKILL.md contains no URLs. Its commands use pip, which can reach the network depending on how they are called. This is read from the text; nothing was executed.
Is Agent Platform Skill Registry safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.
What licence does Agent Platform Skill Registry use?
Agent Platform Skill Registry is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Agent Platform Skill Registry use?
About 584 tokens (SKILL.md is roughly 2.3k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 1.8k tokens, read only when the agent opens those files.
What are the alternatives to Agent Platform Skill Registry?
Skills that share tags, products or a category with Agent Platform Skill Registry: Retail Product Search Agent (google/adk-recipes, 10k stars), Vertex AI API Dev (JetBrains/skills, 364 stars), Google Antigravity SDK (google-antigravity/antigravity-sdk-python, 3.7k stars) and SkillOpt-Sleep Self-Improvement Cycle (microsoft/SkillOpt, 18k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Agent Platform Skill Registry?
google (a GitHub organization, an official publisher) maintains it in google/skills, which has 21,032 GitHub stars. The repository holds 147 skills in this directory. The repository was last updated on October 8, 2026.
Source: google/skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.