[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M77SFDM5X8Z79P54XZRJGCE4":3,"skill-same:01M77SFDM5X8Z79P54XZRJGCE4":57},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":18,"publishedAt":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":29,"commitSha":30,"skillDirectory":31,"forksCount":32,"repositoryHtmlUrl":33,"repositoryHomepageUrl":6,"ownerHtmlUrl":34,"ownerBlogUrl":35,"ownerDescription":6,"updatedAt":36,"install":37,"resources":50},"01M77SFDM5X8Z79P54XZRJGCE4","google-agents-cli-scaffold",null,"This skill should be used when the user wants to \"create an agent project\", \"start a new ADK project\", \"build me a new agent\", \"add CI\u002FCD to my project\", \"add deployment\", \"enhance my project\", or \"upgrade my project\". Part of the Google ADK (Agent Development Kit) skills suite. Covers `agents-cli scaffold create`, `scaffold enhance`, and `scaffold upgrade` commands, template options, deployment targets, and the prototype-first workflow. Do NOT use for writing agent code (use google-agents-cli-adk-code) or deployment operations (use google-agents-cli-deploy).","Reihantt6\u002Fsns-myagent","Reihantt6","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F219822095?v=4","01M77KK94PV8B7C2D9XWXNS8DJ","Mohamad Reihan tegar prasetya","01M77KK958QFMTHYXGXFV7KZ79",2,"MIT","https:\u002F\u002Fgithub.com\u002FReihantt6\u002Fsns-myagent\u002Fblob\u002Fmain\u002Fagent\u002Fskills\u002Fgoogle-agents-cli-scaffold\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\ndescription: \"This skill should be used when the user wants to \\\"create an agent project\\\", \\\"start a new ADK project\\\", \\\"build me a new agent\\\", \\\"add CI\u002FCD to my project\\\", \\\"add deployment\\\", \\\"enhance my project\\\", or \\\"upgrade my project\\\". Part of the Google ADK (Agent Development Kit) skills suite. Covers `agents-cli scaffold create`, `scaffold enhance`, and `scaffold upgrade` commands, template options, deployment targets, and the prototype-first workflow. Do NOT use for writing agent code (use google-agents-cli-adk-code) or deployment operations (use google-agents-cli-deploy).\\n\"\nmetadata: {\"author\":\"Google\",\"license\":\"Apache-2.0\",\"version\":\"1.3.1\"}\n---\n# ADK Project Scaffolding Guide\n\n> **Requires:** `agents-cli` (`uv tool install google-agents-cli`) — [install uv](https:\u002F\u002Fdocs.astral.sh\u002Fuv\u002Fgetting-started\u002Finstallation\u002Findex.md) first if needed.\n\nUse the `agents-cli` CLI to create new ADK agent projects or enhance existing ones with deployment, CI\u002FCD, and infrastructure scaffolding.\n\n---\n\n## Prerequisite: Clarify Requirements (MANDATORY for new projects)\n\n**Before scaffolding a new project, load `\u002Fgoogle-agents-cli-workflow` and complete Phase 0** — clarify the user's requirements before running any `scaffold create` command. Ask what the agent should do, what tools\u002FAPIs it needs, and whether they want a prototype or full deployment.\n\n---\n\n## Step 1: Choose Architecture\n\n**Mapping user choices to CLI flags:**\n\n| Choice | CLI flag |\n|--------|----------|\n| Retrieval\u002FRAG, sandboxed execution, cross-session memory, OAuth consent, guardrails, scheduled runs | **No flag** — these come from clone-and-study recipes; see the topic index in `\u002Fgoogle-agents-cli-adk-code` → `references\u002Fsamples.md` |\n| A2A protocol | built into every ADK agent — scaffold normally (`--agent adk`) |\n| Prototype (no deployment) | `--prototype` |\n| Deployment target | `--deployment-target \u003Cagent_runtime\\|cloud_run\\|gke>` |\n| CI\u002FCD runner | `--cicd-runner \u003Cgithub_actions\\|google_cloud_build>` |\n| Session storage | `--session-type \u003Cin_memory\\|cloud_sql\\|agent_platform_sessions>` |\n\n### Product name mapping\n\nOlder names → CLI values (`vertexai` SDK package name unchanged):\n\n- Agent Engine \u002F Vertex AI Agent Engine → `--deployment-target agent_runtime`\n- Agent Engine sessions \u002F Agent Platform Sessions → `--session-type agent_platform_sessions`\n- Vertex AI Search \u002F Vertex AI Vector Search \u002F RAG → clone-and-study recipe, not a flag\n\n> **Removed flags.** `--datastore`, the `agentic_rag` template, and `agents-cli infra datastore` \u002F\n> `agents-cli data-ingestion` no longer exist. If you reach for one, you want a recipe instead.\n\n---\n\n## Step 2: Create or Enhance the Project\n\n### Create a New Project\n\n```bash\nagents-cli scaffold create \u003Cproject-name> \\\n  --agent \u003Ctemplate> \\\n  --deployment-target \u003Ctarget> \\\n  --region \u003Cregion> \\\n  --prototype\n```\n\n**Constraints:**\n- Project name must be **26 characters or less**, lowercase letters, numbers, and hyphens only.\n- Do NOT `mkdir` the project directory before running `create` — the CLI creates it automatically. If you mkdir first, `create` will fail or behave unexpectedly.\n- Auto-detect the guidance filename based on the IDE you are running in and pass `--agent-guidance-filename` accordingly (`GEMINI.md` for Antigravity CLI, `CLAUDE.md` for Claude Code, `AGENTS.md` for OpenAI Codex\u002Fother).\n- When enhancing an existing project, check where the agent code lives. If it's not in `app\u002F`, pass `--agent-directory \u003Cdir>` (e.g. `--agent-directory agent`). Getting this wrong causes enhance to miss or misplace files.\n\n### Reference Files\n\n| File | Contents |\n|------|----------|\n| `references\u002Fflags.md` | Full flag reference for `create` and `enhance` commands |\n\n### Enhance an Existing Project\n\n```bash\nagents-cli scaffold enhance . --deployment-target \u003Ctarget>\nagents-cli scaffold enhance . --cicd-runner \u003Crunner>\n```\n\nRun this from inside the project directory (or pass the path instead of `.`).\n\n### Upgrade a Project\n\nUpgrade an existing project to a newer agents-cli version, intelligently applying updates while preserving your customizations:\n\n```bash\nagents-cli scaffold upgrade                # Upgrade current directory\nagents-cli scaffold upgrade \u003Cproject-path> # Upgrade specific project\nagents-cli scaffold upgrade --dry-run      # Preview changes without applying\nagents-cli scaffold upgrade --auto-approve  # Auto-apply non-conflicting changes\n```\n\n### Execution Modes\n\nThe CLI defaults to **strict programmatic mode** — all required params must be supplied as CLI flags or a `UsageError` is raised. No approval flags needed. Pass all required params explicitly.\n\n### Common Workflows\n\n**Always ask the user before running these commands.** Present the options (CI\u002FCD runner, deployment target, etc.) and confirm before executing.\n\n```bash\n# Add deployment to an existing prototype (strict programmatic)\nagents-cli scaffold enhance . --deployment-target agent_runtime\n\n# Add CI\u002FCD pipeline (ask: GitHub Actions or Cloud Build?)\nagents-cli scaffold enhance . --cicd-runner github_actions\n```\n\n---\n\n## Template Options\n\n| Template | Deployment | Description |\n|----------|------------|-------------|\n| `adk` | Agent Runtime, Cloud Run, GKE | Standard ADK agent (default); A2A protocol built in |\n\n> **`adk` is the only template.** Capabilities beyond it — retrieval, sandboxed execution, memory,\n> OAuth, guardrails — are clone-and-study recipes, not templates. See the topic index in\n> `\u002Fgoogle-agents-cli-adk-code` → `references\u002Fsamples.md`.\n\n---\n\n## Deployment Options\n\n| Target | Description |\n|--------|-------------|\n| `agent_runtime` | Managed by Google (Vertex AI Agent Runtime). Container-based — Agent Engine builds the project Dockerfile. Sessions handled automatically. |\n| `cloud_run` | Container-based deployment. More control; you build and deploy the Dockerfile. |\n| `gke` | Container-based on GKE Autopilot. Full Kubernetes control. |\n| `none` | No deployment scaffolding. Code only (still includes a Dockerfile). |\n\n### \"Prototype First\" Pattern (Recommended)\n\nStart with `--prototype` to skip CI\u002FCD and Terraform. Focus on getting the agent working first, then add deployment later with `scaffold enhance`:\n\n```bash\n# Step 1: Create a prototype\nagents-cli scaffold create my-agent --agent adk --prototype\n\n# Step 2: Iterate on the agent code...\n\n# Step 3: Add deployment when ready\nagents-cli scaffold enhance . --deployment-target agent_runtime\n```\n\n### Agent Runtime and session_type\n\nWhen using `agent_runtime` as the deployment target, Agent Runtime manages sessions internally. If your code sets a `session_type`, clear it — Agent Runtime overrides it.\n\n---\n\n## Step 3: Load Dev Workflow\n\nAfter scaffolding, immediately load `\u002Fgoogle-agents-cli-workflow` — it contains the development workflow, coding guidelines, and operational rules you must follow when implementing the agent.\n\n**Key files to customize:** `app\u002Fagent.py` (instruction, tools, model), `app\u002Ftools.py` (custom tool functions), `.env` (project ID, location, API keys).\n**Files to preserve:** `agents-cli-manifest.yaml` (CLI reads this), deployment configs under `deployment\u002F`, `Makefile`, `app\u002F__init__.py` (the `App(name=...)` must match the directory name — default `app`), and the generated runtime\u002FA2A infra (`app\u002Ffast_api_app.py`, `app\u002Fapp_utils\u002Fa2a.py`, `app\u002Fapp_utils\u002Fservices.py`, `Dockerfile`) — these wire up serving, sessions, and the built-in A2A surface; don't hand-edit them.\n\n**Adapting a recipe:** copy its `app\u002F`, `infra\u002Fterraform\u002F`, and any ingestion or provisioning into\nyour scaffolded project, then run provisioning from the recipe's own `Makefile` (e.g.\n`make setup-infra`). Start from its `AGENTS.md`.\n\n**Verifying your agent works:** Use `agents-cli run \"test prompt\"` for quick smoke tests, then `agents-cli eval generate` and `agents-cli eval grade` for systematic validation. Do NOT write pytest tests that assert on LLM response content — that belongs in eval.\n\n---\n\n## Scaffold as Reference\n\nWhen you need specific files (Terraform, CI\u002FCD workflows, Dockerfile) but don't want to scaffold the current project directly, create a temporary reference project in `\u002Ftmp\u002F`:\n\n```bash\nagents-cli scaffold create \u002Ftmp\u002Fref-project \\\n  --agent adk \\\n  --deployment-target cloud_run\n```\n\nInspect the generated files, adapt what you need, and copy into the actual project. Delete the reference project when done.\n\nThis is useful for:\n- Non-standard project structures that `enhance` can't handle\n- Cherry-picking specific infrastructure files\n- Understanding what the CLI generates before committing to it\n\n---\n\n## Critical Rules\n\n- **NEVER skip requirements clarification** — load `\u002Fgoogle-agents-cli-workflow` Phase 0 and clarify the user's intent before running `scaffold create`\n- **NEVER change the model** in existing code unless explicitly asked\n- **NEVER `mkdir` before `create`** — the CLI creates the directory; pre-creating it causes enhance mode instead of create mode\n- **NEVER create a Git repo or push to remote without asking** — confirm repo name, public vs private, and whether the user wants it created at all\n- **Always ask before choosing CI\u002FCD runner** — present GitHub Actions and Cloud Build as options, don't default silently\n- **Agent Runtime clears session_type** — if deploying to `agent_runtime`, remove any `session_type` setting from your code\n- **Start with `--prototype`** for quick iteration — add deployment later with `enhance`\n- **Project names** must be ≤26 characters, lowercase, letters\u002Fnumbers\u002Fhyphens only\n- **NEVER write A2A code from scratch** — A2A is built into every Python ADK agent (`adk`); the A2A Python API surface (import paths, `AgentCard` schema, `to_a2a()` signature) is non-trivial and changes across versions. Scaffold normally; never hand-write the A2A surface.\n\n---\n\n# Examples\n\nUsing scaffold as reference:\nUser says: \"I need a Dockerfile for my non-standard project\"\nActions:\n1. Create temp project: `agents-cli scaffold create \u002Ftmp\u002Fref --agent adk --deployment-target cloud_run`\n2. Copy relevant files (Dockerfile, etc.) from \u002Ftmp\u002Fref\n3. Delete temp project\nResult: Infrastructure files adapted to the actual project\n\n---\n\nA2A project:\nUser says: \"Build me a Python agent that exposes A2A and deploys to Cloud Run\"\nActions:\n1. Follow the standard flow (understand requirements, choose architecture, scaffold)\n2. `agents-cli scaffold create my-a2a-agent --agent adk --deployment-target cloud_run --prototype`\nResult: Valid A2A imports and Dockerfile — no manual A2A code written.\n\n---\n\n## Troubleshooting\n\n### `agents-cli` command not found\n\nSee `\u002Fgoogle-agents-cli-workflow` → **Setup** section.\n\n---\n\n## Related Skills\n\n- `\u002Fgoogle-agents-cli-workflow` — Development workflow, coding guidelines, and the build-evaluate-deploy lifecycle\n- `\u002Fgoogle-agents-cli-adk-code` — ADK Python API quick reference for writing agent code\n- `\u002Fgoogle-agents-cli-deploy` — Deployment targets, CI\u002FCD pipelines, and production workflows\n- `\u002Fgoogle-agents-cli-eval` — Evaluation methodology, dataset schema, and the eval-fix loop\n","# ADK Project Scaffolding Guide\n\n> **Requires:** `agents-cli` (`uv tool install google-agents-cli`) — [install uv](https:\u002F\u002Fdocs.astral.sh\u002Fuv\u002Fgetting-started\u002Finstallation\u002Findex.md) first if needed.\n\nUse the `agents-cli` CLI to create new ADK agent projects or enhance existing ones with deployment, CI\u002FCD, and infrastructure scaffolding.\n\n---\n\n## Prerequisite: Clarify Requirements (MANDATORY for new projects)\n\n**Before scaffolding a new project, load `\u002Fgoogle-agents-cli-workflow` and complete Phase 0** — clarify the user's requirements before running any `scaffold create` command. Ask what the agent should do, what tools\u002FAPIs it needs, and whether they want a prototype or full deployment.\n\n---\n\n## Step 1: Choose Architecture\n\n**Mapping user choices to CLI flags:**\n\n| Choice | CLI flag |\n|--------|----------|\n| Retrieval\u002FRAG, sandboxed execution, cross-session memory, OAuth consent, guardrails, scheduled runs | **No flag** — these come from clone-and-study recipes; see the topic index in `\u002Fgoogle-agents-cli-adk-code` → `references\u002Fsamples.md` |\n| A2A protocol | built into every ADK agent — scaffold normally (`--agent adk`) |\n| Prototype (no deployment) | `--prototype` |\n| Deployment target | `--deployment-target \u003Cagent_runtime\\|cloud_run\\|gke>` |\n| CI\u002FCD runner | `--cicd-runner \u003Cgithub_actions\\|google_cloud_build>` |\n| Session storage | `--session-type \u003Cin_memory\\|cloud_sql\\|agent_platform_sessions>` |\n\n### Product name mapping\n\nOlder names → CLI values (`vertexai` SDK package name unchanged):\n\n- Agent Engine \u002F Vertex AI Agent Engine → `--deployment-target agent_runtime`\n- Agent Engine sessions \u002F Agent Platform Sessions → `--session-type agent_platform_sessions`\n- Vertex AI Search \u002F Vertex AI Vector Search \u002F RAG → clone-and-study recipe, not a flag\n\n> **Removed flags.** `--datastore`, the `agentic_rag` template, and `agents-cli infra datastore` \u002F\n> `agents-cli data-ingestion` no longer exist. If you reach for one, you want a recipe instead.\n\n---\n\n## Step 2: Create or Enhance the Project\n\n### Create a New Project\n\n```bash\nagents-cli scaffold create \u003Cproject-name> \\\n  --agent \u003Ctemplate> \\\n  --deployment-target \u003Ctarget> \\\n  --region \u003Cregion> \\\n  --prototype\n```\n\n**Constraints:**\n- Project name must be **26 characters or less**, lowercase letters, numbers, and hyphens only.\n- Do NOT `mkdir` the project directory before running `create` — the CLI creates it automatically. If you mkdir first, `create` will fail or behave unexpectedly.\n- Auto-detect the guidance filename based on the IDE you are running in and pass `--agent-guidance-filename` accordingly (`GEMINI.md` for Antigravity CLI, `CLAUDE.md` for Claude Code, `AGENTS.md` for OpenAI Codex\u002Fother).\n- When enhancing an existing project, check where the agent code lives. If it's not in `app\u002F`, pass `--agent-directory \u003Cdir>` (e.g. `--agent-directory agent`). Getting this wrong causes enhance to miss or misplace files.\n\n### Reference Files\n\n| File | Contents |\n|------|----------|\n| `references\u002Fflags.md` | Full flag reference for `create` and `enhance` commands |\n\n### Enhance an Existing Project\n\n```bash\nagents-cli scaffold enhance . --deployment-target \u003Ctarget>\nagents-cli scaffold enhance . --cicd-runner \u003Crunner>\n```\n\nRun this from inside the project directory (or pass the path instead of `.`).\n\n### Upgrade a Project\n\nUpgrade an existing project to a newer agents-cli version, intelligently applying updates while preserving your customizations:\n\n```bash\nagents-cli scaffold upgrade                # Upgrade current directory\nagents-cli scaffold upgrade \u003Cproject-path> # Upgrade specific project\nagents-cli scaffold upgrade --dry-run      # Preview changes without applying\nagents-cli scaffold upgrade --auto-approve  # Auto-apply non-conflicting changes\n```\n\n### Execution Modes\n\nThe CLI defaults to **strict programmatic mode** — all required params must be supplied as CLI flags or a `UsageError` is raised. No approval flags needed. Pass all required params explicitly.\n\n### Common Workflows\n\n**Always ask the user before running these commands.** Present the options (CI\u002FCD runner, deployment target, etc.) and confirm before executing.\n\n```bash\n# Add deployment to an existing prototype (strict programmatic)\nagents-cli scaffold enhance . --deployment-target agent_runtime\n\n# Add CI\u002FCD pipeline (ask: GitHub Actions or Cloud Build?)\nagents-cli scaffold enhance . --cicd-runner github_actions\n```\n\n---\n\n## Template Options\n\n| Template | Deployment | Description |\n|----------|------------|-------------|\n| `adk` | Agent Runtime, Cloud Run, GKE | Standard ADK agent (default); A2A protocol built in |\n\n> **`adk` is the only template.** Capabilities beyond it — retrieval, sandboxed execution, memory,\n> OAuth, guardrails — are clone-and-study recipes, not templates. See the topic index in\n> `\u002Fgoogle-agents-cli-adk-code` → `references\u002Fsamples.md`.\n\n---\n\n## Deployment Options\n\n| Target | Description |\n|--------|-------------|\n| `agent_runtime` | Managed by Google (Vertex AI Agent Runtime). Container-based — Agent Engine builds the project Dockerfile. Sessions handled automatically. |\n| `cloud_run` | Container-based deployment. More control; you build and deploy the Dockerfile. |\n| `gke` | Container-based on GKE Autopilot. Full Kubernetes control. |\n| `none` | No deployment scaffolding. Code only (still includes a Dockerfile). |\n\n### \"Prototype First\" Pattern (Recommended)\n\nStart with `--prototype` to skip CI\u002FCD and Terraform. Focus on getting the agent working first, then add deployment later with `scaffold enhance`:\n\n```bash\n# Step 1: Create a prototype\nagents-cli scaffold create my-agent --agent adk --prototype\n\n# Step 2: Iterate on the agent code...\n\n# Step 3: Add deployment when ready\nagents-cli scaffold enhance . --deployment-target agent_runtime\n```\n\n### Agent Runtime and session_type\n\nWhen using `agent_runtime` as the deployment target, Agent Runtime manages sessions internally. If your code sets a `session_type`, clear it — Agent Runtime overrides it.\n\n---\n\n## Step 3: Load Dev Workflow\n\nAfter scaffolding, immediately load `\u002Fgoogle-agents-cli-workflow` — it contains the development workflow, coding guidelines, and operational rules you must follow when implementing the agent.\n\n**Key files to customize:** `app\u002Fagent.py` (instruction, tools, model), `app\u002Ftools.py` (custom tool functions), `.env` (project ID, location, API keys).\n**Files to preserve:** `agents-cli-manifest.yaml` (CLI reads this), deployment configs under `deployment\u002F`, `Makefile`, `app\u002F__init__.py` (the `App(name=...)` must match the directory name — default `app`), and the generated runtime\u002FA2A infra (`app\u002Ffast_api_app.py`, `app\u002Fapp_utils\u002Fa2a.py`, `app\u002Fapp_utils\u002Fservices.py`, `Dockerfile`) — these wire up serving, sessions, and the built-in A2A surface; don't hand-edit them.\n\n**Adapting a recipe:** copy its `app\u002F`, `infra\u002Fterraform\u002F`, and any ingestion or provisioning into\nyour scaffolded project, then run provisioning from the recipe's own `Makefile` (e.g.\n`make setup-infra`). Start from its `AGENTS.md`.\n\n**Verifying your agent works:** Use `agents-cli run \"test prompt\"` for quick smoke tests, then `agents-cli eval generate` and `agents-cli eval grade` for systematic validation. Do NOT write pytest tests that assert on LLM response content — that belongs in eval.\n\n---\n\n## Scaffold as Reference\n\nWhen you need specific files (Terraform, CI\u002FCD workflows, Dockerfile) but don't want to scaffold the current project directly, create a temporary reference project in `\u002Ftmp\u002F`:\n\n```bash\nagents-cli scaffold create \u002Ftmp\u002Fref-project \\\n  --agent adk \\\n  --deployment-target cloud_run\n```\n\nInspect the generated files, adapt what you need, and copy into the actual project. Delete the reference project when done.\n\nThis is useful for:\n- Non-standard project structures that `enhance` can't handle\n- Cherry-picking specific infrastructure files\n- Understanding what the CLI generates before committing to it\n\n---\n\n## Critical Rules\n\n- **NEVER skip requirements clarification** — load `\u002Fgoogle-agents-cli-workflow` Phase 0 and clarify the user's intent before running `scaffold create`\n- **NEVER change the model** in existing code unless explicitly asked\n- **NEVER `mkdir` before `create`** — the CLI creates the directory; pre-creating it causes enhance mode instead of create mode\n- **NEVER create a Git repo or push to remote without asking** — confirm repo name, public vs private, and whether the user wants it created at all\n- **Always ask before choosing CI\u002FCD runner** — present GitHub Actions and Cloud Build as options, don't default silently\n- **Agent Runtime clears session_type** — if deploying to `agent_runtime`, remove any `session_type` setting from your code\n- **Start with `--prototype`** for quick iteration — add deployment later with `enhance`\n- **Project names** must be ≤26 characters, lowercase, letters\u002Fnumbers\u002Fhyphens only\n- **NEVER write A2A code from scratch** — A2A is built into every Python ADK agent (`adk`); the A2A Python API surface (import paths, `AgentCard` schema, `to_a2a()` signature) is non-trivial and changes across versions. Scaffold normally; never hand-write the A2A surface.\n\n---\n\n# Examples\n\nUsing scaffold as reference:\nUser says: \"I need a Dockerfile for my non-standard project\"\nActions:\n1. Create temp project: `agents-cli scaffold create \u002Ftmp\u002Fref --agent adk --deployment-target cloud_run`\n2. Copy relevant files (Dockerfile, etc.) from \u002Ftmp\u002Fref\n3. Delete temp project\nResult: Infrastructure files adapted to the actual project\n\n---\n\nA2A project:\nUser says: \"Build me a Python agent that exposes A2A and deploys to Cloud Run\"\nActions:\n1. Follow the standard flow (understand requirements, choose architecture, scaffold)\n2. `agents-cli scaffold create my-a2a-agent --agent adk --deployment-target cloud_run --prototype`\nResult: Valid A2A imports and Dockerfile — no manual A2A code written.\n\n---\n\n## Troubleshooting\n\n### `agents-cli` command not found\n\nSee `\u002Fgoogle-agents-cli-workflow` → **Setup** section.\n\n---\n\n## Related Skills\n\n- `\u002Fgoogle-agents-cli-workflow` — Development workflow, coding guidelines, and the build-evaluate-deploy lifecycle\n- `\u002Fgoogle-agents-cli-adk-code` — ADK Python API quick reference for writing agent code\n- `\u002Fgoogle-agents-cli-deploy` — Deployment targets, CI\u002FCD pipelines, and production workflows\n- `\u002Fgoogle-agents-cli-eval` — Evaluation methodology, dataset schema, and the eval-fix loop\n",{"metadata":24,"description":28},{"author":25,"license":26,"version":27},"Google","Apache-2.0","1.3.1","This skill should be used when the user wants to \"create an agent project\", \"start a new ADK project\", \"build me a new agent\", \"add CI\u002FCD to my project\", \"add deployment\", \"enhance my project\", or \"upgrade my project\". Part of the Google ADK (Agent Development Kit) skills suite. Covers `agents-cli scaffold create`, `scaffold enhance`, and `scaffold upgrade` commands, template options, deployment targets, and the prototype-first workflow. Do NOT use for writing agent code (use google-agents-cli-adk-code) or deployment operations (use google-agents-cli-deploy).\n","main","58843b159d7a4050d6b785a98b908cce505c0b92","agent\u002Fskills\u002Fgoogle-agents-cli-scaffold",0,"https:\u002F\u002Fgithub.com\u002FReihantt6\u002Fsns-myagent","https:\u002F\u002Fgithub.com\u002FReihantt6","reihsns.web.id","2026-08-19 20:08:18",{"source":8,"skillName":5,"commands":38,"prompt":48,"zipAvailable":49},[39,42,45],{"tool":40,"command":41},"npx","npx skills add Reihantt6\u002Fsns-myagent --skill google-agents-cli-scaffold",{"tool":43,"command":44},"bunx","bunx skills add Reihantt6\u002Fsns-myagent --skill google-agents-cli-scaffold",{"tool":46,"command":47},"pnpm","pnpm dlx skills add Reihantt6\u002Fsns-myagent --skill google-agents-cli-scaffold","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FReihantt6\u002Fsns-myagent\u002Fblob\u002Fmain\u002Fagent\u002Fskills\u002Fgoogle-agents-cli-scaffold\u002FSKILL.md",true,[51],{"path":52,"resourceType":53,"resourceTypeDesc":54,"sizeBytes":55,"sourceHtmlUrl":56},"references\u002Fflags.md","REFERENCE","参考文档",3289,"https:\u002F\u002Fgithub.com\u002FReihantt6\u002Fsns-myagent\u002Fblob\u002Fmain\u002Fagent\u002Fskills\u002Fgoogle-agents-cli-scaffold\u002Freferences\u002Fflags.md",[58,65,72,79,86,93],{"skillNo":59,"name":60,"nameZh":6,"description":61,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":62,"categories":63,"keywords":64,"publishedAt":19},"01M77XDCYZ407XYMF2T4P6F7VT","youtube-transcript","Extract transcripts from YouTube videos. Use when the user asks for a transcript, subtitles, or captions of a YouTube video and provides a YouTube URL (youtube.com\u002Fwatch?v=, youtu.be\u002F, or similar). Supports output with or without timestamps.","https:\u002F\u002Fgithub.com\u002FReihantt6\u002Fsns-myagent\u002Fblob\u002Fmain\u002Fagent\u002Fskills\u002Fyoutube-transcript\u002FSKILL.md",[],[],{"skillNo":66,"name":67,"nameZh":6,"description":68,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":69,"categories":70,"keywords":71,"publishedAt":19},"01M77XD7PBC98J6MXGJJ2TJ8DX","youtube-thumbnail-design","YouTube thumbnail design with specific dimensions, contrast rules, and mobile preview optimization. Covers safe zones, text placement, face expression psychology, and A\u002FB testing. Use for: YouTube thumbnails, video cover images, click-through optimization. Triggers: youtube thumbnail, thumbnail design, video thumbnail, click through rate, ctr optimization, youtube cover, video cover image, thumbnail maker, thumbnail tips, youtube design, video preview image","https:\u002F\u002Fgithub.com\u002FReihantt6\u002Fsns-myagent\u002Fblob\u002Fmain\u002Fagent\u002Fskills\u002Fyoutube-thumbnail-design\u002FSKILL.md",[],[],{"skillNo":73,"name":74,"nameZh":6,"description":75,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":76,"categories":77,"keywords":78,"publishedAt":19},"01M77XD2541C8HXJ6RHYZP4NGJ","youtube-short-maker","Make YouTube Shorts that hold attention with Pexo — vertical 9:16, fast-paced, hook in the first 3 seconds. Describe your topic and Pexo writes the script, generates the shots, picks the models, and assembles a finished Short with music and captions. Use for YouTube Shorts: \"youtube short\", \"make a youtube short\", \"shorts video\", \"short-form video\". NOT for long-form or landscape video.","https:\u002F\u002Fgithub.com\u002FReihantt6\u002Fsns-myagent\u002Fblob\u002Fmain\u002Fagent\u002Fskills\u002Fyoutube-short-maker\u002FSKILL.md",[],[],{"skillNo":80,"name":81,"nameZh":6,"description":82,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":83,"categories":84,"keywords":85,"publishedAt":19},"01M77XCXKVSYK7KTZ3PQBVVGFD","xcode-project-setup","Safely modifies Xcode projects (.pbxproj) to add Swift Packages and link files. Use this skill whenever an iOS project needs dependencies installed (e.g. Firebase, Alamofire).","https:\u002F\u002Fgithub.com\u002FReihantt6\u002Fsns-myagent\u002Fblob\u002Fmain\u002Fagent\u002Fskills\u002Fxcode-project-setup\u002FSKILL.md",[],[],{"skillNo":87,"name":88,"nameZh":6,"description":89,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":90,"categories":91,"keywords":92,"publishedAt":19},"01M77XCR1DV8ZQK2NHWKVY4EWX","x402","Set up Browser Use Cloud payments with x402 — pay per request from a crypto wallet (USDC on Base mainnet), no signup or API key. Two setups it works out up front — \"just use it\" (set up a wallet so you or Claude Code can run cloud browser tasks paid from the wallet — Claude writes and runs throwaway scripts, nothing touches your codebase) or \"build it in\" (install the SDK and write the key + code into your project). Walks through wallet setup, funding, .env, and a ~$1 test run. Use when the user asks about x402, pay-per-use, USDC payments, or wants Browser Use Cloud without an API key. For the free-tier signup (reverse-CAPTCHA → API key), use `browser-use cloud signup` or the `cloud` skill instead.","https:\u002F\u002Fgithub.com\u002FReihantt6\u002Fsns-myagent\u002Fblob\u002Fmain\u002Fagent\u002Fskills\u002Fx402\u002FSKILL.md",[],[],{"skillNo":94,"name":95,"nameZh":6,"description":96,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":97,"categories":98,"keywords":99,"publishedAt":19},"01M77XCMD3R3ZBZQQSW6E0793B","x-twitter-scraper","Build GitHub Copilot workflows with Xquik X API SDKs, REST endpoints, hosted Apify Actor runs, MCP tools, TweetClaw OpenClaw plugin installs, signed webhooks, tweet search, user lookup, follower exports, media actions, and agent automation.","https:\u002F\u002Fgithub.com\u002FReihantt6\u002Fsns-myagent\u002Fblob\u002Fmain\u002Fagent\u002Fskills\u002Fx-twitter-scraper\u002FSKILL.md",[],[]]