[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7EVTC4CD9ZG7PCT164DCJ7Y":3,"skill-same:01M7EVTC4CD9ZG7PCT164DCJ7Y":52},{"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":24,"commitSha":25,"skillDirectory":26,"forksCount":27,"repositoryHtmlUrl":28,"repositoryHomepageUrl":6,"ownerHtmlUrl":29,"ownerBlogUrl":6,"ownerDescription":30,"updatedAt":31,"install":32,"resources":45},"01M7EVTC4CD9ZG7PCT164DCJ7Y","adk-sample-creator",null,"Creates a new sample agent in the ADK Python repository — the sample directory, its `agent.py`, and its `README.md` — following the conventions the existing samples already use. Use when the user wants to add a sample or example demonstrating a feature or agent pattern (dynamic nodes, fan-out\u002Ffan-in, a standalone tool-using agent), asks where a new sample belongs under `contributing\u002Fsamples\u002F`, or wants an existing sample's README brought up to the standard structure. Don't use for building a real working agent for the user's own project (use `adk-agent-builder`), or for checking whether the Python blocks in a Markdown file run (use `adk-verify-snippets`).","lza6\u002FArmor-piercing-system-prompts","lza6","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F128880206?v=4","01M7EB3K7WPX5T28EJ2NVHE6EG","Chinese-tingfeng","01M7EB3K97E1KQ16QWKJMFNGX8",11,"MIT","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F05-技能与代理开发\u002Fadk-sample-creator\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: adk-sample-creator\ndescription: >-\n  Creates a new sample agent in the ADK Python repository — the sample\n  directory, its `agent.py`, and its `README.md` — following the conventions\n  the existing samples already use. Use when the user wants to add a sample or\n  example demonstrating a feature or agent pattern (dynamic nodes,\n  fan-out\u002Ffan-in, a standalone tool-using agent), asks where a new sample\n  belongs under `contributing\u002Fsamples\u002F`, or wants an existing sample's README\n  brought up to the standard structure. Don't use for building a real working\n  agent for the user's own project (use `adk-agent-builder`), or for checking\n  whether the Python blocks in a Markdown file run (use `adk-verify-snippets`).\n---\n\n# ADK Sample Creator\n\nCreates samples under `contributing\u002Fsamples\u002F`. These are deliberately minimal\nagents that each exercise one or two features — distinct from the `adk-samples`\nrepository, which hosts full end-to-end applications.\n\nRead the `adk-style` skill first for ADK 2.0 conventions if you have not\nalready.\n\n## 1. Pick the category directory\n\nAlmost every sample lives at\n`contributing\u002Fsamples\u002F{category}\u002F{sample_name}\u002F`. List the categories and\nconfirm with the user which one the sample belongs in before creating\nanything — a workflow sample landing outside `workflows\u002F` is the usual mistake.\n\n```bash\nls contributing\u002Fsamples\u002F\n```\n\nCategories include `workflows`, `patterns`, `core`, `multi_agent`, `tools`,\n`models`, `live`, `mcp`, `a2a`, `evaluation`, and `plugins`. A handful of\nsamples nest one level further when a single feature needs several variants, as\n`plugins\u002Fplugin_reflect_tool_retry\u002Fbasic\u002F` does.\n\nName the sample directory in `snake_case` after the feature it demonstrates:\n`dynamic_nodes`, `fan_out_fan_in`, `streaming_tool_events`.\n\nDo not add an `_agent` suffix, and do not repeat the category as a prefix —\nevery sample is an agent, and the category is already in the path. Many existing\ndirectories still carry both; do not copy them.\n\n## 2. Write `agent.py`\n\nContents of a sample directory:\n\n| File | Required | Purpose |\n| --- | --- | --- |\n| `agent.py` | yes | The agent or workflow. Must expose `root_agent`. |\n| `README.md` | yes | See [readme-template.md](references\u002Freadme-template.md). |\n| `__init__.py` | sometimes | Present when the sample is imported as a package. |\n| `tests\u002F*.json` | no | Recorded sessions used as eval sets. |\n\nUse absolute imports so the file can be run and imported directly.\n\nDo not set `model=` on `Agent` instances. Samples inherit the\nsystem-configured model, which keeps them working when the default model\nchanges; hardcoding `model=\"gemini-2.5-flash\"` pins the sample to a model that\nwill be retired. Set it only when the user explicitly asks for a specific model.\n\nThen pick one of the two shapes.\n\n### Pattern A — Workflow, for multi-step graphs\n\nUse when the sample needs multiple nodes, routing, or parallel execution.\n\n```python\nfrom google.adk import Agent\nfrom google.adk import Context\nfrom google.adk import Event\nfrom google.adk import Workflow\nfrom google.adk.workflow import JoinNode\nfrom google.adk.workflow import node\n```\n\nImport `Workflow` from `google.adk`, not from a private\n`google.adk.workflow._*` module.\n\n```python\nmy_agent = Agent(name=\"my_agent\", instruction=\"...\")\n\n\n@node()\nasync def my_node(node_input: str) -> str:\n  return \"result\"\n\n\nroot_agent = Workflow(\n    name=\"root_agent\",\n    edges=[(\"START\", my_node)],\n)\n```\n\nA plain function can be used as a node directly in `edges`; reach for the\n`@node(...)` decorator when you need one of its options, such as\n`rerun_on_resume=True` for a node that calls `ctx.run_node`.\n\n### Pattern B — Standalone agent, for single-agent or simple tool use\n\nUse when there is no graph and the agent drives its own loop.\n\n```python\nfrom google.adk import Agent\nfrom google.adk.tools import google_search\n\nroot_agent = Agent(\n    name=\"standalone_assistant\",\n    instruction=\"You are a helpful assistant.\",\n    description=\"An assistant that can help with queries.\",\n    tools=[google_search],\n)\n```\n\n## 3. Write `README.md`\n\nFollow [readme-template.md](references\u002Freadme-template.md) — section order,\nprompt formatting, the Mermaid topology rules, and the relative link depth for\n`docs\u002Fguides\u002F`.\n\n## Worked examples\n\nRead these two before writing a new Pattern A sample — one dynamic graph, one\nstatic one.\n\n-   `contributing\u002Fsamples\u002Fworkflows\u002Fdynamic_nodes\u002Fagent.py` — a Python node\n    driving a `while` loop with `ctx.run_node`, so the number of agent calls is\n    decided at runtime rather than by the edges.\n\n    ```python\n    @node(rerun_on_resume=True)\n    async def orchestrate(ctx: Context, node_input: str) -> str:\n      yield Event(state={\"topic\": node_input})\n\n      while True:\n        headline = await ctx.run_node(generate_headline)\n        # ...\n    ```\n\n-   `contributing\u002Fsamples\u002Fworkflows\u002Ffan_out_fan_in\u002Fagent.py` — three functions\n    run in parallel from `START`, collected by a `JoinNode`, then aggregated.\n\n    ```python\n    join_node = JoinNode(name=\"join_for_results\")\n\n    root_agent = Workflow(\n        name=\"root_agent\",\n        edges=[(\n            \"START\",\n            (make_uppercase, count_characters, reverse_string),\n            join_node,\n            aggregate,\n        )],\n    )\n    ```\n","# ADK Sample Creator\n\nCreates samples under `contributing\u002Fsamples\u002F`. These are deliberately minimal\nagents that each exercise one or two features — distinct from the `adk-samples`\nrepository, which hosts full end-to-end applications.\n\nRead the `adk-style` skill first for ADK 2.0 conventions if you have not\nalready.\n\n## 1. Pick the category directory\n\nAlmost every sample lives at\n`contributing\u002Fsamples\u002F{category}\u002F{sample_name}\u002F`. List the categories and\nconfirm with the user which one the sample belongs in before creating\nanything — a workflow sample landing outside `workflows\u002F` is the usual mistake.\n\n```bash\nls contributing\u002Fsamples\u002F\n```\n\nCategories include `workflows`, `patterns`, `core`, `multi_agent`, `tools`,\n`models`, `live`, `mcp`, `a2a`, `evaluation`, and `plugins`. A handful of\nsamples nest one level further when a single feature needs several variants, as\n`plugins\u002Fplugin_reflect_tool_retry\u002Fbasic\u002F` does.\n\nName the sample directory in `snake_case` after the feature it demonstrates:\n`dynamic_nodes`, `fan_out_fan_in`, `streaming_tool_events`.\n\nDo not add an `_agent` suffix, and do not repeat the category as a prefix —\nevery sample is an agent, and the category is already in the path. Many existing\ndirectories still carry both; do not copy them.\n\n## 2. Write `agent.py`\n\nContents of a sample directory:\n\n| File | Required | Purpose |\n| --- | --- | --- |\n| `agent.py` | yes | The agent or workflow. Must expose `root_agent`. |\n| `README.md` | yes | See [readme-template.md](references\u002Freadme-template.md). |\n| `__init__.py` | sometimes | Present when the sample is imported as a package. |\n| `tests\u002F*.json` | no | Recorded sessions used as eval sets. |\n\nUse absolute imports so the file can be run and imported directly.\n\nDo not set `model=` on `Agent` instances. Samples inherit the\nsystem-configured model, which keeps them working when the default model\nchanges; hardcoding `model=\"gemini-2.5-flash\"` pins the sample to a model that\nwill be retired. Set it only when the user explicitly asks for a specific model.\n\nThen pick one of the two shapes.\n\n### Pattern A — Workflow, for multi-step graphs\n\nUse when the sample needs multiple nodes, routing, or parallel execution.\n\n```python\nfrom google.adk import Agent\nfrom google.adk import Context\nfrom google.adk import Event\nfrom google.adk import Workflow\nfrom google.adk.workflow import JoinNode\nfrom google.adk.workflow import node\n```\n\nImport `Workflow` from `google.adk`, not from a private\n`google.adk.workflow._*` module.\n\n```python\nmy_agent = Agent(name=\"my_agent\", instruction=\"...\")\n\n\n@node()\nasync def my_node(node_input: str) -> str:\n  return \"result\"\n\n\nroot_agent = Workflow(\n    name=\"root_agent\",\n    edges=[(\"START\", my_node)],\n)\n```\n\nA plain function can be used as a node directly in `edges`; reach for the\n`@node(...)` decorator when you need one of its options, such as\n`rerun_on_resume=True` for a node that calls `ctx.run_node`.\n\n### Pattern B — Standalone agent, for single-agent or simple tool use\n\nUse when there is no graph and the agent drives its own loop.\n\n```python\nfrom google.adk import Agent\nfrom google.adk.tools import google_search\n\nroot_agent = Agent(\n    name=\"standalone_assistant\",\n    instruction=\"You are a helpful assistant.\",\n    description=\"An assistant that can help with queries.\",\n    tools=[google_search],\n)\n```\n\n## 3. Write `README.md`\n\nFollow [readme-template.md](references\u002Freadme-template.md) — section order,\nprompt formatting, the Mermaid topology rules, and the relative link depth for\n`docs\u002Fguides\u002F`.\n\n## Worked examples\n\nRead these two before writing a new Pattern A sample — one dynamic graph, one\nstatic one.\n\n-   `contributing\u002Fsamples\u002Fworkflows\u002Fdynamic_nodes\u002Fagent.py` — a Python node\n    driving a `while` loop with `ctx.run_node`, so the number of agent calls is\n    decided at runtime rather than by the edges.\n\n    ```python\n    @node(rerun_on_resume=True)\n    async def orchestrate(ctx: Context, node_input: str) -> str:\n      yield Event(state={\"topic\": node_input})\n\n      while True:\n        headline = await ctx.run_node(generate_headline)\n        # ...\n    ```\n\n-   `contributing\u002Fsamples\u002Fworkflows\u002Ffan_out_fan_in\u002Fagent.py` — three functions\n    run in parallel from `START`, collected by a `JoinNode`, then aggregated.\n\n    ```python\n    join_node = JoinNode(name=\"join_for_results\")\n\n    root_agent = Workflow(\n        name=\"root_agent\",\n        edges=[(\n            \"START\",\n            (make_uppercase, count_characters, reverse_string),\n            join_node,\n            aggregate,\n        )],\n    )\n    ```\n",{"name":5,"description":7},"main","d69096e239f2a89aabc2cd078c47664a9d3b1e11","05-技能与代理开发\u002Fadk-sample-creator",3,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts","https:\u002F\u002Fgithub.com\u002Flza6","个人vx：Tf00798\r\n个人✈：@TFGY999","2026-10-08 14:29:22",{"source":8,"skillName":5,"commands":33,"prompt":43,"zipAvailable":44},[34,37,40],{"tool":35,"command":36},"npx","npx skills add lza6\u002FArmor-piercing-system-prompts --skill adk-sample-creator",{"tool":38,"command":39},"bunx","bunx skills add lza6\u002FArmor-piercing-system-prompts --skill adk-sample-creator",{"tool":41,"command":42},"pnpm","pnpm dlx skills add lza6\u002FArmor-piercing-system-prompts --skill adk-sample-creator","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F05-技能与代理开发\u002Fadk-sample-creator\u002FSKILL.md",true,[46],{"path":47,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":50,"sourceHtmlUrl":51},"references\u002Freadme-template.md","REFERENCE","参考文档",1985,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F05-技能与代理开发\u002Fadk-sample-creator\u002Freferences\u002Freadme-template.md",[53,61,66,73,80,87],{"skillNo":54,"name":55,"nameZh":6,"description":56,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":57,"categories":58,"keywords":59,"publishedAt":60},"01M7FFG485KY83TD6HSC4YPCMC","obsidian-clipper-template-creator","Guide for creating templates for the Obsidian Web Clipper. Use when you want to create a new clipping template, understand available variables, or format clipped content.","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fobsidian-clipper-template-creator\u002FSKILL.md",[],[],"2026-11-16 10:05:34",{"skillNo":62,"name":55,"nameZh":6,"description":56,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":63,"categories":64,"keywords":65,"publishedAt":60},"01M7FFG0T6AZ0STEJPSB3CX84K","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fobsidian-clipper-template-creator-antigravity-awesome-skills-main\u002FSKILL.md",[],[],{"skillNo":67,"name":68,"nameZh":6,"description":69,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":70,"categories":71,"keywords":72,"publishedAt":60},"01M7FFFY0QEM14SKWPDYGMXM2P","python-api","Programmatic Object-Detection-Metrics API guidance for BoundingBox, BoundingBoxes, Evaluator, enums, coordinate conversion, AP\u002FmAP semantics, and source-style import diagnostics.","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fobject-detection-metrics\u002Fsub-skills\u002Fpython-api\u002FSKILL.md",[],[],{"skillNo":74,"name":75,"nameZh":6,"description":76,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":77,"categories":78,"keywords":79,"publishedAt":60},"01M7FFFVZQZ2GJ0C0TGP7JHD20","file-evaluation","Folder-based PASCAL VOC AP\u002FmAP evaluation from ground-truth and detection text files.","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fobject-detection-metrics\u002Fsub-skills\u002Ffile-evaluation\u002FSKILL.md",[],[],{"skillNo":81,"name":82,"nameZh":6,"description":83,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":84,"categories":85,"keywords":86,"publishedAt":60},"01M7FFFSFNYSE77SJ6PE1CK2DA","object-detection-metrics","Guides legacy Object-Detection-Metrics PASCAL VOC AP\u002FmAP evaluation from detection text folders and direct Python API classes.","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fobject-detection-metrics\u002FSKILL.md",[],[],{"skillNo":88,"name":89,"nameZh":6,"description":90,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":91,"categories":92,"keywords":93,"publishedAt":60},"01M7FFFP0GCK1RVXBCPQ8APBMT","nx-workspace-patterns","Configure and optimize Nx monorepo workspaces. Use when setting up Nx, configuring project boundaries, optimizing build caching, or implementing affected commands.","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fnx-workspace-patterns\u002FSKILL.md",[],[]]