[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M698ZX4ERWFKZ2M2TPZE8D97":3,"skill-same:01M698ZX4ERWFKZ2M2TPZE8D97":70},{"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":23,"publishedAt":27,"linkOnly":28,"markdownContent":29,"markdownBody":30,"frontMatter":31,"refName":32,"commitSha":33,"skillDirectory":34,"forksCount":35,"repositoryHtmlUrl":36,"repositoryHomepageUrl":37,"ownerHtmlUrl":38,"ownerBlogUrl":39,"ownerDescription":40,"updatedAt":41,"install":42,"resources":55},"01M698ZX4ERWFKZ2M2TPZE8D97","agents-cli-claude",null,"Use when working in this project — adding tools, editing the agent, running, evaluating, serving or deploying it — or when guidance mentions ADK, LlmAgent, google.adk, adk web, or an ADK runner. This project is a Claude Agent SDK agent scaffolded by agents-cli, so ADK-specific instructions do not apply.","google\u002Fagents-cli","google","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F1342004?v=4","01M698VYEFDM0VJBZDYYJ2T83S","Google","01M698ZVGDEBGAXVZGNKKKCRBQ",6339,"Apache-2.0","https:\u002F\u002Fgithub.com\u002Fgoogle\u002Fagents-cli\u002Fblob\u002Fmain\u002Fextensions\u002Fclaude\u002Ftemplate\u002F.agents\u002Fskills\u002Fagents-cli-claude\u002FSKILL.md",[18],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[24,25,9,26],"cli","agents cli claude","sdk","2026-11-10 10:12:30",false,"---\nname: agents-cli-claude\ndescription: >\n  Use when working in this project — adding tools, editing the agent, running,\n  evaluating, serving or deploying it — or when guidance mentions ADK, LlmAgent,\n  google.adk, adk web, or an ADK runner. This project is a Claude Agent SDK\n  agent scaffolded by agents-cli, so ADK-specific instructions do not apply.\n---\n\n# Claude Agent SDK project (agents-cli)\n\nThe agent is a `ClaudeAgentOptions` exported as `root_agent` from\n`app\u002Fagent.py`. There is no `google.adk` dependency and no ADK runner. Other\n`google-agents-cli-*` skills assume ADK; where they describe the agent itself,\nthis skill wins.\n\n**Experimental.** Deploy to agent_runtime (limits: `references\u002Fclaude.md`) or cloud_run.\nThe model runs on Claude on Gemini platform and must be enabled in Model Garden.\n\n## What ADK guidance maps to here\n\n| ADK guidance | This project |\n|---|---|\n| `LlmAgent`, `Agent` | `ClaudeAgentOptions(model=..., system_prompt=..., ...)` assigned to `root_agent` |\n| `Agent(name=...)` | `AGENT_NAME` in `app\u002Fapp_utils\u002Fsettings.py` (`ClaudeAgentOptions` has no name); keep it equal to `create_params.root_agent_name` in `agents-cli-manifest.yaml` |\n| `google.adk.tools`, `FunctionTool` | `@tool(...)` async functions, served by `create_sdk_mcp_server` and passed in `mcp_servers` |\n| `adk web`, `agents-cli playground` | Unavailable (no SDK dev UI). Use `agents-cli run`, or `uv run uvicorn app.fast_api_app:app --port 8080` |\n| ADK runner behind `agents-cli run` | `agents-cli run` runs `root_agent` in process |\n| `agents-cli eval dataset synthesize`, `eval optimize` | Unavailable: both drive the agent through ADK. The command says so and exits |\n| `agents-cli eval generate --url` (traces from a served agent) | Unavailable: the server speaks A2A, not ADK's `\u002Frun_sse`. `eval generate` runs `root_agent` in process; the command refuses `--url` |\n| ADK sessions | Claude sessions, one per A2A conversation; scaffold with `--session-type cloud_sql` to keep them across instances |\n\n## The contract\n\n- `app\u002Fagent.py` exports `root_agent: ClaudeAgentOptions`. Only it changes when\n  you change the agent.\n- `app\u002Fapp_utils\u002Fclaude.py` runs it. Leave `app\u002Fapp_utils\u002F` alone.\n- The served agent's own `CLAUDE.md`, `.claude\u002F` and `.mcp.json` go in `agent_config\u002F`.\n- `app\u002Ffast_api_app.py` exposes `app`. Every deployment target runs\n  `uvicorn app.fast_api_app:app`.\n\n## Adding a tool\n\n```python\n@tool(\"lookup_order\", \"Look up an order by id.\", {\"order_id\": str})\nasync def lookup_order(args: dict[str, Any]) -> dict[str, Any]:\n    return {\"content\": [{\"type\": \"text\", \"text\": f\"Order {args['order_id']}: shipped\"}]}\n\n\nserver = create_sdk_mcp_server(name=\"orders\", tools=[lookup_order])\n\nroot_agent = ClaudeAgentOptions(\n    ...,\n    mcp_servers={\"orders\": server},\n    tools=[],  # no built-in Claude Code tools\n    allowed_tools=[\"mcp__orders__lookup_order\"],  # mcp__\u003Cserver>__\u003Ctool>\n)\n```\n\nA tool missing from `allowed_tools` is not available to the agent. Subagents (`agents=`\nor `agent_config\u002F.claude\u002Fagents\u002F`) run through the built-in `Agent` tool: add `\"Agent\"` to both\n`tools` and `allowed_tools`. Built-in tools\n(`WebFetch`, `WebSearch`, `Read`, `Bash`, ...) go in both `tools` and `allowed_tools`;\nkeep `Bash` and file-editing tools out of a served agent unless the user asks.\n\n## Commands\n\n```bash\nagents-cli install                  # uv sync\nagents-cli run \"hello\"              # run root_agent in process; prints a session id\nagents-cli run \"and?\" --session-id \u003Cid>   # continue that conversation\nagents-cli eval generate --dataset tests\u002Feval\u002Fdatasets\u002Fbasic-dataset.json -o tests\u002Feval\u002Foutput\u002F\nagents-cli eval grade --traces tests\u002Feval\u002Foutput\u002F\u003Cdataset>.json --config tests\u002Feval\u002Feval_config.yaml\nagents-cli deploy\nagents-cli scaffold enhance -d cloud_run --cicd-runner github_actions   # add infra later\n```\n\n`run`, `eval generate`, `publish gemini`, `playground`, `eval dataset` and\n`eval optimize` are overridden by `agents-cli-extension.yaml` at the project root.\nPrefix any command with `AGENTS_CLI_DISABLE_OVERRIDES=1` to reach the built-in instead.\n\n## Serving\n\nA2A: JSON-RPC at `POST \u002Fa2a\u002Fapp`, card at `\u002Fa2a\u002Fapp\u002F.well-known\u002Fagent-card.json`,\nhealth at `\u002Fhealth`; over A2A, text streams as it is generated. On Agent Runtime, also\n`:query` and `:streamQuery` (new sessions and turns), which `agents-cli run --mode adk`\nand an ingress Agent Gateway use. See `references\u002Fclaude.md` for sessions, telemetry\nand deployment.\n\n## Common mistakes\n\n- Renaming `root_agent` or `app`, which breaks `run`, eval and deploy.\n- Leaving `tools` unset: the agent then gets every built-in Claude Code tool.\n- Using a model id that is not enabled on Gemini platform for the project.\n- Reaching for `eval dataset synthesize` or `eval optimize`: they need ADK.\n  Write cases into `tests\u002Feval\u002Fdatasets\u002F` and use `eval generate` + `eval grade`.\n- Expecting `\u002Frun_sse` or ADK's REST session routes; this server serves A2A and\n  Agent Runtime's `:query` \u002F `:streamQuery`.\n\n## References\n\n- `references\u002Fclaude.md` — how a turn runs, model access, project settings, sessions,\n  calling other agents, telemetry and logs.\n- `references\u002Fmigrate-claude-agent.md` — moving an existing Claude Agent SDK agent into\n  this project and onto GCP.\n- `references\u002Fmigrate-from-aws.md` — extra migration steps for an agent running on AWS.\n","# Claude Agent SDK project (agents-cli)\n\nThe agent is a `ClaudeAgentOptions` exported as `root_agent` from\n`app\u002Fagent.py`. There is no `google.adk` dependency and no ADK runner. Other\n`google-agents-cli-*` skills assume ADK; where they describe the agent itself,\nthis skill wins.\n\n**Experimental.** Deploy to agent_runtime (limits: `references\u002Fclaude.md`) or cloud_run.\nThe model runs on Claude on Gemini platform and must be enabled in Model Garden.\n\n## What ADK guidance maps to here\n\n| ADK guidance | This project |\n|---|---|\n| `LlmAgent`, `Agent` | `ClaudeAgentOptions(model=..., system_prompt=..., ...)` assigned to `root_agent` |\n| `Agent(name=...)` | `AGENT_NAME` in `app\u002Fapp_utils\u002Fsettings.py` (`ClaudeAgentOptions` has no name); keep it equal to `create_params.root_agent_name` in `agents-cli-manifest.yaml` |\n| `google.adk.tools`, `FunctionTool` | `@tool(...)` async functions, served by `create_sdk_mcp_server` and passed in `mcp_servers` |\n| `adk web`, `agents-cli playground` | Unavailable (no SDK dev UI). Use `agents-cli run`, or `uv run uvicorn app.fast_api_app:app --port 8080` |\n| ADK runner behind `agents-cli run` | `agents-cli run` runs `root_agent` in process |\n| `agents-cli eval dataset synthesize`, `eval optimize` | Unavailable: both drive the agent through ADK. The command says so and exits |\n| `agents-cli eval generate --url` (traces from a served agent) | Unavailable: the server speaks A2A, not ADK's `\u002Frun_sse`. `eval generate` runs `root_agent` in process; the command refuses `--url` |\n| ADK sessions | Claude sessions, one per A2A conversation; scaffold with `--session-type cloud_sql` to keep them across instances |\n\n## The contract\n\n- `app\u002Fagent.py` exports `root_agent: ClaudeAgentOptions`. Only it changes when\n  you change the agent.\n- `app\u002Fapp_utils\u002Fclaude.py` runs it. Leave `app\u002Fapp_utils\u002F` alone.\n- The served agent's own `CLAUDE.md`, `.claude\u002F` and `.mcp.json` go in `agent_config\u002F`.\n- `app\u002Ffast_api_app.py` exposes `app`. Every deployment target runs\n  `uvicorn app.fast_api_app:app`.\n\n## Adding a tool\n\n```python\n@tool(\"lookup_order\", \"Look up an order by id.\", {\"order_id\": str})\nasync def lookup_order(args: dict[str, Any]) -> dict[str, Any]:\n    return {\"content\": [{\"type\": \"text\", \"text\": f\"Order {args['order_id']}: shipped\"}]}\n\n\nserver = create_sdk_mcp_server(name=\"orders\", tools=[lookup_order])\n\nroot_agent = ClaudeAgentOptions(\n    ...,\n    mcp_servers={\"orders\": server},\n    tools=[],  # no built-in Claude Code tools\n    allowed_tools=[\"mcp__orders__lookup_order\"],  # mcp__\u003Cserver>__\u003Ctool>\n)\n```\n\nA tool missing from `allowed_tools` is not available to the agent. Subagents (`agents=`\nor `agent_config\u002F.claude\u002Fagents\u002F`) run through the built-in `Agent` tool: add `\"Agent\"` to both\n`tools` and `allowed_tools`. Built-in tools\n(`WebFetch`, `WebSearch`, `Read`, `Bash`, ...) go in both `tools` and `allowed_tools`;\nkeep `Bash` and file-editing tools out of a served agent unless the user asks.\n\n## Commands\n\n```bash\nagents-cli install                  # uv sync\nagents-cli run \"hello\"              # run root_agent in process; prints a session id\nagents-cli run \"and?\" --session-id \u003Cid>   # continue that conversation\nagents-cli eval generate --dataset tests\u002Feval\u002Fdatasets\u002Fbasic-dataset.json -o tests\u002Feval\u002Foutput\u002F\nagents-cli eval grade --traces tests\u002Feval\u002Foutput\u002F\u003Cdataset>.json --config tests\u002Feval\u002Feval_config.yaml\nagents-cli deploy\nagents-cli scaffold enhance -d cloud_run --cicd-runner github_actions   # add infra later\n```\n\n`run`, `eval generate`, `publish gemini`, `playground`, `eval dataset` and\n`eval optimize` are overridden by `agents-cli-extension.yaml` at the project root.\nPrefix any command with `AGENTS_CLI_DISABLE_OVERRIDES=1` to reach the built-in instead.\n\n## Serving\n\nA2A: JSON-RPC at `POST \u002Fa2a\u002Fapp`, card at `\u002Fa2a\u002Fapp\u002F.well-known\u002Fagent-card.json`,\nhealth at `\u002Fhealth`; over A2A, text streams as it is generated. On Agent Runtime, also\n`:query` and `:streamQuery` (new sessions and turns), which `agents-cli run --mode adk`\nand an ingress Agent Gateway use. See `references\u002Fclaude.md` for sessions, telemetry\nand deployment.\n\n## Common mistakes\n\n- Renaming `root_agent` or `app`, which breaks `run`, eval and deploy.\n- Leaving `tools` unset: the agent then gets every built-in Claude Code tool.\n- Using a model id that is not enabled on Gemini platform for the project.\n- Reaching for `eval dataset synthesize` or `eval optimize`: they need ADK.\n  Write cases into `tests\u002Feval\u002Fdatasets\u002F` and use `eval generate` + `eval grade`.\n- Expecting `\u002Frun_sse` or ADK's REST session routes; this server serves A2A and\n  Agent Runtime's `:query` \u002F `:streamQuery`.\n\n## References\n\n- `references\u002Fclaude.md` — how a turn runs, model access, project settings, sessions,\n  calling other agents, telemetry and logs.\n- `references\u002Fmigrate-claude-agent.md` — moving an existing Claude Agent SDK agent into\n  this project and onto GCP.\n- `references\u002Fmigrate-from-aws.md` — extra migration steps for an agent running on AWS.\n",{"name":5,"description":7},"main","f4e994044164ff6617f0799900dba0fc091ef0e3","extensions\u002Fclaude\u002Ftemplate\u002F.agents\u002Fskills\u002Fagents-cli-claude",734,"https:\u002F\u002Fgithub.com\u002Fgoogle\u002Fagents-cli","https:\u002F\u002Fgoogle.github.io\u002Fagents-cli\u002F","https:\u002F\u002Fgithub.com\u002Fgoogle","https:\u002F\u002Fopensource.google\u002F","Google ❤️ Open Source","2026-11-05 01:44:59",{"source":8,"skillName":5,"commands":43,"prompt":53,"zipAvailable":54},[44,47,50],{"tool":45,"command":46},"npx","npx skills add google\u002Fagents-cli --skill agents-cli-claude",{"tool":48,"command":49},"bunx","bunx skills add google\u002Fagents-cli --skill agents-cli-claude",{"tool":51,"command":52},"pnpm","pnpm dlx skills add google\u002Fagents-cli --skill agents-cli-claude","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fgoogle\u002Fagents-cli\u002Fblob\u002Fmain\u002Fextensions\u002Fclaude\u002Ftemplate\u002F.agents\u002Fskills\u002Fagents-cli-claude\u002FSKILL.md",true,[56,62,66],{"path":57,"resourceType":58,"resourceTypeDesc":59,"sizeBytes":60,"sourceHtmlUrl":61},"references\u002Fclaude.md","REFERENCE","参考文档",19124,"https:\u002F\u002Fgithub.com\u002Fgoogle\u002Fagents-cli\u002Fblob\u002Fmain\u002Fextensions\u002Fclaude\u002Ftemplate\u002F.agents\u002Fskills\u002Fagents-cli-claude\u002Freferences\u002Fclaude.md",{"path":63,"resourceType":58,"resourceTypeDesc":59,"sizeBytes":64,"sourceHtmlUrl":65},"references\u002Fmigrate-claude-agent.md",21409,"https:\u002F\u002Fgithub.com\u002Fgoogle\u002Fagents-cli\u002Fblob\u002Fmain\u002Fextensions\u002Fclaude\u002Ftemplate\u002F.agents\u002Fskills\u002Fagents-cli-claude\u002Freferences\u002Fmigrate-claude-agent.md",{"path":67,"resourceType":58,"resourceTypeDesc":59,"sizeBytes":68,"sourceHtmlUrl":69},"references\u002Fmigrate-from-aws.md",7993,"https:\u002F\u002Fgithub.com\u002Fgoogle\u002Fagents-cli\u002Fblob\u002Fmain\u002Fextensions\u002Fclaude\u002Ftemplate\u002F.agents\u002Fskills\u002Fagents-cli-claude\u002Freferences\u002Fmigrate-from-aws.md",[71,105,127,150,175,194],{"skillNo":72,"name":73,"nameZh":6,"description":74,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":75,"categories":76,"keywords":86,"publishedAt":27},"01M6990ZGJV6CHR6CZK81S58CN","google-agents-cli-workflow","This skill should be used when the user wants to \"develop an agent\", \"build an agent using ADK\", \"run the agent locally\", \"debug agent code\", \"test an agent\", \"deploy an agent\", \"publish an agent\", \"monitor an agent\", or needs the ADK (Agent Development Kit) development lifecycle and coding guidelines. Entrypoint for building ADK agents. Always active — provides the full workflow (scaffold, build, evaluate, deploy, publish, observe), code preservation rules, model selection guidance, and troubleshooting steps for ADK or any agent development.","https:\u002F\u002Fgithub.com\u002Fgoogle\u002Fagents-cli\u002Fblob\u002Fmain\u002Fsrc\u002Fgoogle\u002Fagents\u002Fcli\u002Fskills\u002Fdata\u002Fgoogle-agents-cli-workflow\u002FSKILL.md",[77,80,81],{"categoryNo":78,"categoryName":79,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000011","运维与部署",{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":82,"categoryName":83,"taxonomyType":84,"taxonomyTypeDesc":85},"01JBSEEDCAT000000000000030","开发工程师","PROFESSION","适用职业",[9,87,24,88,89,90,91,92,93,94,95,96,97,98,99,100,101,102,103,104],"google agents cli workflow","workflow","adk","agent development kit","agent development","development lifecycle","model","observe","selection","model selection","kit","uv","code","debug agent","publish","apache","active","run",{"skillNo":106,"name":107,"nameZh":6,"description":108,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":109,"categories":110,"keywords":113,"publishedAt":27},"01M6990XH0S4MNS7YTDAMNAAEW","google-agents-cli-scaffold","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 agents-cli 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 (ADK projects: use google-agents-cli-adk-code) or deployment operations (use google-agents-cli-deploy).","https:\u002F\u002Fgithub.com\u002Fgoogle\u002Fagents-cli\u002Fblob\u002Fmain\u002Fsrc\u002Fgoogle\u002Fagents\u002Fcli\u002Fskills\u002Fdata\u002Fgoogle-agents-cli-scaffold\u002FSKILL.md",[111,112],{"categoryNo":78,"categoryName":79,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[114,9,24,115,89,116,117,118,119,120,98,121,88,99,122,123,102,124,125,126],"google agents cli scaffold","scaffold","writing","projects","new agent","project","ci","upgrade","create","me","options","template","CI\u002FCD",{"skillNo":128,"name":129,"nameZh":6,"description":130,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":131,"categories":132,"keywords":135,"publishedAt":27},"01M6990VP634A9G6052KQCZNYJ","google-agents-cli-publish","This skill should be used when the user wants to \"publish an agent\", \"publish my ADK agent\", \"register an agent with Gemini\", \"publish to Gemini\" (formerly Gemini Enterprise), or needs guidance on the agents-cli publish gemini command. Also use when the user wants to \"manage agents in Agent Registry\", \"list\u002Fupdate\u002Fdelete registered agents\", or \"register an MCP server\". Covers ADK vs A2A registration modes, programmatic and interactive usage, flag reference, auto-detection from deployment metadata, Agent Registry fleet management, and troubleshooting. Part of the agents-cli skills suite. Do NOT use for deployment (use google-agents-cli-deploy).","https:\u002F\u002Fgithub.com\u002Fgoogle\u002Fagents-cli\u002Fblob\u002Fmain\u002Fsrc\u002Fgoogle\u002Fagents\u002Fcli\u002Fskills\u002Fdata\u002Fgoogle-agents-cli-publish\u002FSKILL.md",[133,134],{"categoryNo":78,"categoryName":79,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[9,24,136,101,89,137,138,98,139,140,141,142,143,102,144,145,146,147,148,149],"google agents cli publish","MCP","programmatic","auto","mcp server","agent registry","server","delete","command","update","install","suite","fleet","registry",{"skillNo":151,"name":152,"nameZh":6,"description":153,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":154,"categories":155,"keywords":164,"publishedAt":27},"01M6990SFDY0JKXYP921BKRJYE","google-agents-cli-observability","This skill should be used when the user wants to \"set up tracing\", \"monitor my agent\", \"configure logging\", \"add observability\", \"debug production traffic\", or needs guidance on monitoring deployed agents, including ADK (Agent Development Kit) agents. Covers Cloud Trace, prompt-response logging, BigQuery Agent Analytics, third-party integrations (AgentOps, Phoenix, MLflow, etc.), and troubleshooting. Part of the agents-cli skills suite. Do NOT use for deployment setup (use google-agents-cli-deploy) or API code patterns (use google-agents-cli-adk-code).","https:\u002F\u002Fgithub.com\u002Fgoogle\u002Fagents-cli\u002Fblob\u002Fmain\u002Fsrc\u002Fgoogle\u002Fagents\u002Fcli\u002Fskills\u002Fdata\u002Fgoogle-agents-cli-observability\u002FSKILL.md",[156,159,160,161],{"categoryNo":157,"categoryName":158,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000013","分析与可视化",{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":82,"categoryName":83,"taxonomyType":84,"taxonomyTypeDesc":85},{"categoryNo":162,"categoryName":163,"taxonomyType":84,"taxonomyTypeDesc":85},"01JBSEEDCAT000000000000033","数据分析师",[9,24,165,166,89,90,91,167,168,97,98,169,170,171,99,172,173,102,146,174],"google agents cli observability","observability","SET","up","traffic","configure","code patterns","api","monitoring","mlflow",{"skillNo":176,"name":177,"nameZh":6,"description":178,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":179,"categories":180,"keywords":183,"publishedAt":27},"01M6990PXZ0S6NHYV8PGGVFT6E","google-agents-cli-eval","This skill should be used when the user wants to \"run an evaluation\", \"evaluate my agent\", \"evaluate my ADK agent\", \"write an eval dataset\", \"analyze eval failures\", \"compare eval results\", \"optimize agent\", or needs guidance on the Gemini platform eval methodology and the Quality Flywheel. Covers eval metrics, dataset schema, LLM-as-judge scoring, and common failure causes. Applies to any agents-cli project, whatever framework the agent is written in. Do NOT use for agent API code patterns (ADK: use google-agents-cli-adk-code), deployment (use google-agents-cli-deploy), or project scaffolding (use google-agents-cli-scaffold).","https:\u002F\u002Fgithub.com\u002Fgoogle\u002Fagents-cli\u002Fblob\u002Fmain\u002Fsrc\u002Fgoogle\u002Fagents\u002Fcli\u002Fskills\u002Fdata\u002Fgoogle-agents-cli-eval\u002FSKILL.md",[181,182],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":82,"categoryName":83,"taxonomyType":84,"taxonomyTypeDesc":85},[9,24,184,185,89,186,119,187,98,188,171,99,189,172,190,191,192,102,104,193],"google agents cli eval","eval","project scaffolding","scaffolding","dataset","scoring","common","analyze","optimize","write",{"skillNo":195,"name":196,"nameZh":6,"description":197,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":198,"categories":199,"keywords":206,"publishedAt":27},"01M6990MAHH0X6XCNVB74Q67P6","google-agents-cli-deploy","This skill should be used when the user wants to \"deploy an agent\", \"deploy my ADK agent\", \"set up CI\u002FCD\", \"configure secrets\", \"troubleshoot a deployment\", or needs guidance on Agent Runtime, Cloud Run, or GKE deployment targets, or binding an agent to an Agent Gateway. Covers deployment workflows, service accounts, rollback, and production infrastructure. Applies to any framework agents-cli deploys (ADK, LangChain, ...). Part of the agents-cli skills suite. Do NOT use for agent API code patterns (ADK: use google-agents-cli-adk-code), evaluation (use google-agents-cli-eval), or project scaffolding (use google-agents-cli-scaffold).","https:\u002F\u002Fgithub.com\u002Fgoogle\u002Fagents-cli\u002Fblob\u002Fmain\u002Fsrc\u002Fgoogle\u002Fagents\u002Fcli\u002Fskills\u002Fdata\u002Fgoogle-agents-cli-deploy\u002FSKILL.md",[200,203,204,205],{"categoryNo":201,"categoryName":202,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000010","后端与接口",{"categoryNo":78,"categoryName":79,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":82,"categoryName":83,"taxonomyType":84,"taxonomyTypeDesc":85},[9,207,24,208,89,119,120,185,98,209,171,210,104,211,212,213,214,215,216,217],"google agents cli deploy","deploy","workflows","gke","Evaluation","langchain","infrastructure","do","cloud run","for","deployment"]