[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M787YF12SFE9YNXQESK1W07A":3,"skill-same:01M787YF12SFE9YNXQESK1W07A":101},{"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":26,"commitSha":27,"skillDirectory":28,"forksCount":14,"repositoryHtmlUrl":29,"repositoryHomepageUrl":30,"ownerHtmlUrl":31,"ownerBlogUrl":32,"ownerDescription":33,"updatedAt":34,"install":35,"resources":48},"01M787YF12SFE9YNXQESK1W07A","agent-platform-tuning",null,"Agent Platform Model Tuning. Use when you need to fine-tune open models or Gemini models using Agent Platform infrastructure. Don't use for model training outside Agent Platform, model deployment to endpoints (use `agent-platform-deploy`), or managing serving endpoints (use `agent-platform-endpoint-management`).","Solizardking\u002Fskillhub-main","Solizardking","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F108096810?v=4","01M786KDB10AYV042N0F9BD5B5","Clawd","01M786NYYXSZK1D05WM8JQPC48",0,"MIT","https:\u002F\u002Fgithub.com\u002FSolizardking\u002Fskillhub-main\u002Fblob\u002Fmain\u002Fpublic\u002Fapi\u002Fskills\u002Fgoogle\u002Fcloud\u002Fagent-platform-tuning\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: agent-platform-tuning\nmetadata:\n  category: AiAndMachineLearning\ndescription: >-\n  Agent Platform Model Tuning. Use when you need to fine-tune open models\n  or Gemini models using Agent Platform infrastructure. Don't use for model\n  training outside Agent Platform, model deployment to endpoints (use\n  `agent-platform-deploy`), or managing serving endpoints (use\n  `agent-platform-endpoint-management`).\n---\n\n# Agent Platform Model Tuning\n\n## Overview\n\nThis skill provides procedural knowledge for fine-tuning Large Language Models\n(both Open Models and Gemini Models) using Agent Platform's tuning service. It\ncovers the entire lifecycle from environment setup and data preparation to job\nconfiguration, monitoring, and deployment.\n\n## Workflow Decision Tree\n\n1.  **Model Category Identification**: Has the user explicitly stated whether\n    they want to tune an **Open Model** or a **Gemini Model**?\n\n    -   **No** → **STOP**. Ask the user if they want to tune an Open Model or a\n        Gemini Model. **CRITICAL EXCEPTION for Environment Setup Requests:** If\n        the user is specifically asking for environment setup instructions (e.g.\n        \"What environment setup is needed?\"), you **MUST** provide the full\n        [Phase 0 environment setup](#phase-0) instructions in your initial\n        response, *simultaneously* with asking clarifying questions about the\n        model category.\n    -   If the user provides a specific tuning purpose, you should\n        recommend three models: one Open Model, one Gemini Model, and a third\n        generally recommended choice. Briefly list the pros and cons of each\n        (e.g., Gemini models might be more expensive, etc.). **CRITICAL:** You\n        must read `references\u002Fmodels.md` during this step and only recommend\n        models explicitly listed in that catalog. Do not recommend unsupported\n        models like Mistral. Do not proceed with model configuration until the\n        category is confirmed.\n    -   **Yes** → Proceed.\n\n2.  **Environment Check**: Has the environment (Auth, APIs, IAM, Venv) been\n    initialized?\n\n    -   **No** → Go to [Phase 0: Environment & IAM Setup](#phase-0).\n    -   **Yes** → Proceed.\n\n3.  **Dataset Status**: Is the dataset ready in JSONL format, **is its structure\n    valid for tuning**, and is it uploaded to Google Cloud Storage?\n\n        -   **No** → Go to [Phase 1: Dataset Preparation & Upload](#phase-1).\n        -   **Yes** → Proceed.\n\n4.  **Column Selection Confirmation**: Have you presented the columns to the\n    user and confirmed the mapping?\n\n    -   **No** → **STOP**. You must show samples and get user confirmation on\n        column mapping as described in Phase 1.0 before proceeding.\n    -   **Yes** → Proceed.\n\n5.  **Configuration**: Has the user provided the target model and\n    hyperparameters, or explicitly agreed to your recommendations?\n\n    -   **No** → Go to\n        [Phase 2: Model Configuration & Recommendation](#phase-2).\n    -   **Yes** → Proceed.\n\n6.  **Job Status**: Has the tuning job been submitted?\n\n        -   **No** → Go to\n            [Phase 3: Tuning Job Execution](#phase-3-tuning-job-execution).\n        -   **Yes** → Proceed.\n\n7.  **Job Completion**: Is the tuning job complete?\n\n        -   **No** → Go to [Phase 4: Monitoring](#phase-4-monitoring).\n        -   **Yes** → Proceed.\n\n8.  **Deployment**: Has the tuned model been deployed (if required)?\n\n        -   **No** → Go to [Phase 5: Model Deployment](#phase-5-model-deployment).\n        -   **Yes** → Task Complete.\n\n## Phase 0: Environment & IAM Setup {#phase-0}\n\nEnsure the foundational environment is ready before proceeding.\n\n### 0.1 Authentication & Project Context\n\n-   Check if `gcloud` CLI is installed. If it is not installed, prompt the\n    user for permission to install it before proceeding. If it is installed,\n    update it:\n\n```bash\ngcloud components update --quiet > \u002Fdev\u002Fnull 2>&1\n```\n\n-   Verify `gcloud auth list`. If not authenticated, run `gcloud auth login`.\n-   Ensure `project` and `location` are known. Use `gcloud config get project`\n    to retrieve the current project (and `gcloud config get compute\u002Fregion` for\n    region).\n-   **CRITICAL: Ask for Confirmation.** You must prompt the user to confirm the\n    retrieved project and region before proceeding, in case they want to switch\n    to a different one.\n\n### 0.2 Possible Locations\n\nThe following locations are available for tuning:\n\n-   us-central1\n-   europe-west4\n-   us-west1\n-   us-east5\n-   asia-southeast1\n\nNo other values are supported for this section, ensure that the location is\nlisted above.\n\n### 0.3 Enable APIs\n\nEnsure `aiplatform.googleapis.com` and `storage.googleapis.com` are enabled.\n\n```bash\ngcloud services enable aiplatform.googleapis.com storage.googleapis.com \\\n    --project=YOUR_PROJECT\n```\n\n### 0.4 IAM Permissions\n\nVerify the following identities have the required roles.\n\n-   **Agent Platform Service Agent**:\n    `service-PROJECT_NUMBER@gcp-sa-aiplatform.iam.gserviceaccount.com`\n-   **Managed OSS Fine Tuning Service Agent**:\n    `service-PROJECT_NUMBER@gcp-sa-vertex-moss-ft.iam.gserviceaccount.com`\n-   **User Identity**: The account running the commands.\n\n### 0.5 Virtual Environment\n\nCreate and use a virtual environment named `tuning_agent_venv` in the home\ndirectory. Install dependencies from `references\u002Frequirements.txt`.\n\n```bash\npython3 -m venv ~\u002Ftuning_agent_venv\nsource ~\u002Ftuning_agent_venv\u002Fbin\u002Factivate\npip install -r references\u002Frequirements.txt\n```\n\n**CRITICAL AGENT INSTRUCTION:** You **MUST** ensure that every Python command or\nscript execution (e.g., `python3 scripts\u002F...`, `pip install ...`) is prefixed\nwith the virtual environment activation command: `source\n~\u002Ftuning_agent_venv\u002Fbin\u002Factivate &&`. Additionally, advise the user that every\nsingle time they run a Python command, execute a script, or inspect data inline,\nthey **MUST** also activate this virtual environment first in their bash\nexecution. For example: `source ~\u002Ftuning_agent_venv\u002Fbin\u002Factivate && python3\n...`. Do not run standalone `python3` commands without activating the\nenvironment, as they will encounter `ModuleNotFoundError` issues.\n\n## Phase 1: Dataset Preparation & Upload {#phase-1}\n\n### 1.0 Dataset Discovery & Confirmation\n\n-   **User-Provided Dataset Verification:** If the user specifies a dataset\n    filename or path in their prompt, verify its existence in the workspace\n    (e.g. via script execution or checking for typos).\n    *   **If the file cannot be found anywhere**, you **MUST** inform the user\n    that the dataset file does not exist or cannot be accessed. You **MUST**\n    prompt the user to provide a valid dataset path. Alternatively, if candidate\n    dataset files are found in the workspace during your search, you **MUST**\n    present the candidates to the user and ask them to select one. You **MUST**\n    stop tool execution immediately after reporting the missing file or\n    presenting candidates, and wait for the user's response. Do **NOT** ask for\n    80\u002F20 validation split permission, and do **NOT** attempt to upload the\n    dataset before receiving a valid dataset file selection from the user.\n    *   **If the file is found and verified**, proceed to Step 1.1 Formatting &\n    Validation below.\n-   **Auto-Discovery: From User Bucket:** If the user does not have a dataset\n    and no suitable alternative is found in the Hugging Face reference, offer to\n    search the user's GCS buckets for potential training data. Prioritize\n    searching for files with extensions like `.jsonl`, `.json`, `.csv`, and\n    `.parquet`. If such files are found, read the first few lines\u002Frecords of\n    each to determine if they contain text-based data suitable for tuning\n    (e.g., prompt\u002Fcompletion pairs) that can be modified to follow\n    [Data Preparation Guide](references\u002Fdata_prep.md) and is related to the\n    tuning task requested. **DO NOT** search without prompting first.\n-   **Auto-Discovery: From Task to Huggingface:** If the user has a specific\n    task, refer to [Huggingface Datasets Reference](references\u002Fhf_datasets.md)\n    and recommend a dataset from this if one exists. For each dataset\n    recommended, provide some information about the dataset and provide some\n    reasonable splits. > [!IMPORTANT] > **CRITICAL: Ask for Confirmation and\n    Column Selection.** Do not proceed > with dataset preparation or upload\n    until you perform the following > steps and get user confirmation: > 1.\n    **Dataset and Split Confirmation:** Present the dataset and > available\n    splits to the user and have them confirm which to use. > 2. **Column\n    Selection (Hugging Face or Custom Datasets):** You must: > - Provide a list\n    of all available columns in the selected dataset > split. > - **Show a few\n    samples from the dataset** to help the user > understand the content and\n    make the choice of columns. > - Recommend which columns should be mapped to\n    `prompt` (or user > message) and `completion` (or assistant response),\n    offering a few > reasonable options if applicable. > - Ask the user to\n    confirm the column mapping or specify which > columns to use.\n\n### 1.1 Formatting & Validation\n\n-   **Conversion**: If data is in CSV, JSON, or Parquet, use\n    `scripts\u002Fprepare_dataset.py` to convert.\n-   **Validation Split Confirmation**: If the user only provides a training\n    dataset, **you must prompt the user** to seek permission to split the\n    training dataset 80\u002F20 to form a validation dataset (using\n    `--validation_split 0.2`). If they agree, proceed with the split. If they\n    decline, just use the training dataset without a validation dataset.\n-   **Validation**: If data is already in JSONL, validate it before uploading.\n    Simply having a `.jsonl` extension is not enough. You must verify that the\n    content schema is valid for tuning (e.g. correct system\u002Fuser\u002Fmodel roles).\n\n```bash\npython3 scripts\u002Fprepare_dataset.py \\\n    --input my_data.jsonl \\\n    --format \u003Cmessages|messages_gemini> \\\n    --validate_only\n```\n\n*(Use `--format messages` for open models and `--format messages_gemini` for\nGemini models.)* - Refer to [Data Preparation Guide](references\u002Fdata_prep.md)\nfor required schemas.\n\n### 1.2 Upload\n\nUpload formatted `.jsonl` files to GCS using a unique directory (e.g., with a\ndatetime timestamp) to avoid overwriting outputs from different runs.\n\u003C!-- disableFinding(LINE_OVER_80) --> `bash\nARTIFACTS=\"gs:\u002F\u002FYOUR_BUCKET\u002Ftuning_agent_job_\u003Cdatetime>\u002Fdataset.jsonl\" gcloud\nstorage cp dataset.jsonl $ARTIFACTS` \u003C!-- enableFinding(LINE_OVER_80) -->\n\n## Phase 2: Model Configuration & Recommendation {#phase-2}\n\nHelp the user choose the best model and parameters. **Always seek user\nconfirmation before submitting the job.**\n\n-   If the user does not specify a specific model in their prompt, calculate\n    recommendations based on the **Models Catalog**.\n-   **Prompt for Confirmation:** Present the recommended model to the user and\n    ask for their confirmation before configuring hyperparameters.\n\n### 2.1 Configuration\n\n#### For Open Models\n\n-   Recommend `tuning_mode`, `epochs`, `learning_rate`, and `adapter_size`\n    based on the [Tuning Guide](references\u002Ftuning_guide.md) and model-specific\n    baselines in the [Models Catalog](references\u002Fmodels.md).\n\n### 2.2 Calculating Cost (Open Models Only)\n\n-   We can calculate a rough estimate of cost of tuning based on the dataset and\n    the selected model in the [Models Catalog](references\u002Fmodels.md):\n\n    ```bash\n    python3 scripts\u002Fcalculate_cost.py \\\n        --input my_data.jsonl \\\n        --model MODEL_NAME \\\n        --tuning_mode TUNING_MODE \\\n        --epochs epochs\n    ```\n\n> [!NOTE]\n> **Handling Missing Dataset Errors:** If `scripts\u002Fcalculate_cost.py` fails\n> because the dataset file (e.g. `my_data.jsonl` or `dummy_data.jsonl`) cannot\n> be found, you **MUST** inform the user that the dataset file does not exist or\n> cannot be accessed. You **MUST** prompt the user to provide a valid dataset\n> path, and stop tool execution immediately to wait for their response. Do\n> **NOT** retry or loop, do **NOT** invent a specific cost number, and do\n> **NOT** prompt for job submission approval before receiving a valid dataset\n> from the user.\n\n-   **Prompt for Confirmation:** Present the recommended hyperparameter\n    configuration and estimated cost to the user and ask for their approval\n    before proceeding to job submission. Make sure to note that the estimated\n    cost is just an estimate and can vary from actual billing costs.\n\n## Phase 3: Tuning Job Execution {#phase-3-tuning-job-execution}\n\n**CRITICAL Pre-Flight Check (GCS Verification):** Before you propose a\nconfirmation prompt or submit any tuning job, you **MUST** verify that the\nspecified training dataset GCS URI (e.g. `gs:\u002F\u002Fdummy_bucket\u002Fdataset.jsonl` or\n`gs:\u002F\u002FYOUR_BUCKET\u002F...`) actually exists and is accessible. Run\n`gcloud storage ls $DATASET_URI` (or `gsutil ls`).\n\n*   **If the verification fails** (e.g. `BucketNotFound`, `404`, `AccessDenied`,\n    or indicating a dummy\u002Fmissing bucket), you **MUST** inform the user that the\n    GCS bucket or dataset does not exist or cannot be accessed. You **MUST**\n    prompt the user to provide a valid GCS URI for the dataset, and stop tool\n    execution immediately to wait for their response. Do **NOT** propose a\n    confirmation prompt and do **NOT** execute any tuning scripts before\n    receiving a valid dataset URI from the user.\n*   **If the verification succeeds**, proceed to propose the confirmation prompt\n    below.\n\n### For Gemini Models\n\nCheck if `scripts\u002Ftune_gemini_model.py` exists.\n\n-   **If `scripts\u002Ftune_gemini_model.py` exists:** Submit the Gemini model tuning\n    job using this script.\n\n    ```bash\n    python3 scripts\u002Ftune_gemini_model.py\n    ```\n\n-   **If `scripts\u002Ftune_gemini_model.py` does not exist:** Instruct the user to\n    manually configure and submit the tuning job via the Google Cloud Console\n    UI or using the Agent Platform SDK for Python.\n\n### For Open Models\n\nSubmit the open model tuning job using `scripts\u002Ftune_open_model.py`. Identify\nthe model id using available models documentation at\n\u003C!-- disableFinding(LINE_OVER_80) -->\n[documentation](https:\u002F\u002Fdocs.cloud.google.com\u002Fgemini-enterprise-agent-platform\u002Fmodels\u002Fopen-model-tuning.md.txt).\n\u003C!-- enableFinding(LINE_OVER_80) -->\n\n```bash\npython3 scripts\u002Ftune_open_model.py \\\n    --project YOUR_PROJECT \\\n    --location YOUR_LOCATION \\\n    --base_model BASE_MODEL_ID \\\n    --train_dataset gs:\u002F\u002FYOUR_BUCKET\u002Ftuning_agent_job_\u003Cdatetime>\u002Fdataset.jsonl \\\n    --output_uri gs:\u002F\u002FYOUR_BUCKET\u002Ftuning_agent_job_\u003Cdatetime>\u002Foutput \\\n    --epochs EPOCHS \\\n    --learning_rate LR \\\n    --tuning_mode MODE\n```\n\n> [!IMPORTANT]\n> **Interactive Confirmation Required (Tier M):** Before proceeding with job\n> submission, you **MUST** present the proposed command string showing all\n> literal flags in a confirmation prompt to the user with 'Yes' and 'No'\n> options.\n\n> **CRITICAL:** When presenting this confirmation prompt to the user, you MUST\n> output it as a direct plain text response and stop tool execution immediately.\n> Do NOT call any command execution or interactive tools in the same turn, as\n> unexpected tool calls may be auto-replied by the simulation harness and cause\n> an infinite loop. Yield immediately for the user's reply.\n\n## Phase 4: Monitoring {#phase-4-monitoring}\n\nMonitor the job via the Cloud Console link provided in the script output.\nAdditionally, ask the user if they want you to monitor the job status for them\nin the background. If they agree, execute `scripts\u002Fmonitor_tuning_job.py` as\na background task to periodically poll the job status and notify the user to\nshow the status. If the user declines, leave it completely to the user to\ncheck on the status.\n\n## Phase 5: Model Deployment {#phase-5-model-deployment}\n\nOnce the tuning job is `SUCCEEDED`, deploy the model.\n\n```bash\nARTIFACTS=\"gs:\u002F\u002FYOUR_BUCKET\u002Ftuning_agent_job_\u003Cdatetime>\u002Foutput\u002Fpostprocess\u002Fnode-0\u002Fcheckpoints\u002Ffinal\"\ngcloud ai model-garden models deploy \\\n    --project=YOUR_PROJECT \\\n    --region=YOUR_LOCATION \\\n    --model=\"$ARTIFACTS\" \\\n    --machine-type=MACHINE_TYPE \\\n    --accelerator-type=ACCELERATOR_TYPE \\\n    --accelerator-count=COUNT\n```\n\n> [!IMPORTANT]\n> **Interactive Confirmation Required (Tier M):** Before proceeding with\n> deployment, you **MUST** present the proposed command string showing all\n> literal flags in a confirmation prompt to the user with 'Yes' and 'No'\n> options.\n\n> **CRITICAL:** When presenting this confirmation prompt to the user, you MUST\n> output it as a direct plain text response and stop tool execution immediately.\n> Do NOT call any command execution or interactive tools in the same turn, as\n> unexpected tool calls may be auto-replied by the simulation harness and cause\n> an infinite loop. Yield immediately for the user's reply.\n\nRefer to [Models Catalog](references\u002Fmodels.md) for hardware recommendations for\nspecific open models.\n\n## Resources\n\n-   [Data Preparation Guide](references\u002Fdata_prep.md)\n-   [Models Catalog](references\u002Fmodels.md)\n-   [Tuning Guide](references\u002Ftuning_guide.md)\n-   `scripts\u002Fprepare_dataset.py`: Data conversion & validation.\n-   `scripts\u002Ftune_open_model.py`: Open model tuning job submission.","# Agent Platform Model Tuning\n\n## Overview\n\nThis skill provides procedural knowledge for fine-tuning Large Language Models\n(both Open Models and Gemini Models) using Agent Platform's tuning service. It\ncovers the entire lifecycle from environment setup and data preparation to job\nconfiguration, monitoring, and deployment.\n\n## Workflow Decision Tree\n\n1.  **Model Category Identification**: Has the user explicitly stated whether\n    they want to tune an **Open Model** or a **Gemini Model**?\n\n    -   **No** → **STOP**. Ask the user if they want to tune an Open Model or a\n        Gemini Model. **CRITICAL EXCEPTION for Environment Setup Requests:** If\n        the user is specifically asking for environment setup instructions (e.g.\n        \"What environment setup is needed?\"), you **MUST** provide the full\n        [Phase 0 environment setup](#phase-0) instructions in your initial\n        response, *simultaneously* with asking clarifying questions about the\n        model category.\n    -   If the user provides a specific tuning purpose, you should\n        recommend three models: one Open Model, one Gemini Model, and a third\n        generally recommended choice. Briefly list the pros and cons of each\n        (e.g., Gemini models might be more expensive, etc.). **CRITICAL:** You\n        must read `references\u002Fmodels.md` during this step and only recommend\n        models explicitly listed in that catalog. Do not recommend unsupported\n        models like Mistral. Do not proceed with model configuration until the\n        category is confirmed.\n    -   **Yes** → Proceed.\n\n2.  **Environment Check**: Has the environment (Auth, APIs, IAM, Venv) been\n    initialized?\n\n    -   **No** → Go to [Phase 0: Environment & IAM Setup](#phase-0).\n    -   **Yes** → Proceed.\n\n3.  **Dataset Status**: Is the dataset ready in JSONL format, **is its structure\n    valid for tuning**, and is it uploaded to Google Cloud Storage?\n\n        -   **No** → Go to [Phase 1: Dataset Preparation & Upload](#phase-1).\n        -   **Yes** → Proceed.\n\n4.  **Column Selection Confirmation**: Have you presented the columns to the\n    user and confirmed the mapping?\n\n    -   **No** → **STOP**. You must show samples and get user confirmation on\n        column mapping as described in Phase 1.0 before proceeding.\n    -   **Yes** → Proceed.\n\n5.  **Configuration**: Has the user provided the target model and\n    hyperparameters, or explicitly agreed to your recommendations?\n\n    -   **No** → Go to\n        [Phase 2: Model Configuration & Recommendation](#phase-2).\n    -   **Yes** → Proceed.\n\n6.  **Job Status**: Has the tuning job been submitted?\n\n        -   **No** → Go to\n            [Phase 3: Tuning Job Execution](#phase-3-tuning-job-execution).\n        -   **Yes** → Proceed.\n\n7.  **Job Completion**: Is the tuning job complete?\n\n        -   **No** → Go to [Phase 4: Monitoring](#phase-4-monitoring).\n        -   **Yes** → Proceed.\n\n8.  **Deployment**: Has the tuned model been deployed (if required)?\n\n        -   **No** → Go to [Phase 5: Model Deployment](#phase-5-model-deployment).\n        -   **Yes** → Task Complete.\n\n## Phase 0: Environment & IAM Setup {#phase-0}\n\nEnsure the foundational environment is ready before proceeding.\n\n### 0.1 Authentication & Project Context\n\n-   Check if `gcloud` CLI is installed. If it is not installed, prompt the\n    user for permission to install it before proceeding. If it is installed,\n    update it:\n\n```bash\ngcloud components update --quiet > \u002Fdev\u002Fnull 2>&1\n```\n\n-   Verify `gcloud auth list`. If not authenticated, run `gcloud auth login`.\n-   Ensure `project` and `location` are known. Use `gcloud config get project`\n    to retrieve the current project (and `gcloud config get compute\u002Fregion` for\n    region).\n-   **CRITICAL: Ask for Confirmation.** You must prompt the user to confirm the\n    retrieved project and region before proceeding, in case they want to switch\n    to a different one.\n\n### 0.2 Possible Locations\n\nThe following locations are available for tuning:\n\n-   us-central1\n-   europe-west4\n-   us-west1\n-   us-east5\n-   asia-southeast1\n\nNo other values are supported for this section, ensure that the location is\nlisted above.\n\n### 0.3 Enable APIs\n\nEnsure `aiplatform.googleapis.com` and `storage.googleapis.com` are enabled.\n\n```bash\ngcloud services enable aiplatform.googleapis.com storage.googleapis.com \\\n    --project=YOUR_PROJECT\n```\n\n### 0.4 IAM Permissions\n\nVerify the following identities have the required roles.\n\n-   **Agent Platform Service Agent**:\n    `service-PROJECT_NUMBER@gcp-sa-aiplatform.iam.gserviceaccount.com`\n-   **Managed OSS Fine Tuning Service Agent**:\n    `service-PROJECT_NUMBER@gcp-sa-vertex-moss-ft.iam.gserviceaccount.com`\n-   **User Identity**: The account running the commands.\n\n### 0.5 Virtual Environment\n\nCreate and use a virtual environment named `tuning_agent_venv` in the home\ndirectory. Install dependencies from `references\u002Frequirements.txt`.\n\n```bash\npython3 -m venv ~\u002Ftuning_agent_venv\nsource ~\u002Ftuning_agent_venv\u002Fbin\u002Factivate\npip install -r references\u002Frequirements.txt\n```\n\n**CRITICAL AGENT INSTRUCTION:** You **MUST** ensure that every Python command or\nscript execution (e.g., `python3 scripts\u002F...`, `pip install ...`) is prefixed\nwith the virtual environment activation command: `source\n~\u002Ftuning_agent_venv\u002Fbin\u002Factivate &&`. Additionally, advise the user that every\nsingle time they run a Python command, execute a script, or inspect data inline,\nthey **MUST** also activate this virtual environment first in their bash\nexecution. For example: `source ~\u002Ftuning_agent_venv\u002Fbin\u002Factivate && python3\n...`. Do not run standalone `python3` commands without activating the\nenvironment, as they will encounter `ModuleNotFoundError` issues.\n\n## Phase 1: Dataset Preparation & Upload {#phase-1}\n\n### 1.0 Dataset Discovery & Confirmation\n\n-   **User-Provided Dataset Verification:** If the user specifies a dataset\n    filename or path in their prompt, verify its existence in the workspace\n    (e.g. via script execution or checking for typos).\n    *   **If the file cannot be found anywhere**, you **MUST** inform the user\n    that the dataset file does not exist or cannot be accessed. You **MUST**\n    prompt the user to provide a valid dataset path. Alternatively, if candidate\n    dataset files are found in the workspace during your search, you **MUST**\n    present the candidates to the user and ask them to select one. You **MUST**\n    stop tool execution immediately after reporting the missing file or\n    presenting candidates, and wait for the user's response. Do **NOT** ask for\n    80\u002F20 validation split permission, and do **NOT** attempt to upload the\n    dataset before receiving a valid dataset file selection from the user.\n    *   **If the file is found and verified**, proceed to Step 1.1 Formatting &\n    Validation below.\n-   **Auto-Discovery: From User Bucket:** If the user does not have a dataset\n    and no suitable alternative is found in the Hugging Face reference, offer to\n    search the user's GCS buckets for potential training data. Prioritize\n    searching for files with extensions like `.jsonl`, `.json`, `.csv`, and\n    `.parquet`. If such files are found, read the first few lines\u002Frecords of\n    each to determine if they contain text-based data suitable for tuning\n    (e.g., prompt\u002Fcompletion pairs) that can be modified to follow\n    [Data Preparation Guide](references\u002Fdata_prep.md) and is related to the\n    tuning task requested. **DO NOT** search without prompting first.\n-   **Auto-Discovery: From Task to Huggingface:** If the user has a specific\n    task, refer to [Huggingface Datasets Reference](references\u002Fhf_datasets.md)\n    and recommend a dataset from this if one exists. For each dataset\n    recommended, provide some information about the dataset and provide some\n    reasonable splits. > [!IMPORTANT] > **CRITICAL: Ask for Confirmation and\n    Column Selection.** Do not proceed > with dataset preparation or upload\n    until you perform the following > steps and get user confirmation: > 1.\n    **Dataset and Split Confirmation:** Present the dataset and > available\n    splits to the user and have them confirm which to use. > 2. **Column\n    Selection (Hugging Face or Custom Datasets):** You must: > - Provide a list\n    of all available columns in the selected dataset > split. > - **Show a few\n    samples from the dataset** to help the user > understand the content and\n    make the choice of columns. > - Recommend which columns should be mapped to\n    `prompt` (or user > message) and `completion` (or assistant response),\n    offering a few > reasonable options if applicable. > - Ask the user to\n    confirm the column mapping or specify which > columns to use.\n\n### 1.1 Formatting & Validation\n\n-   **Conversion**: If data is in CSV, JSON, or Parquet, use\n    `scripts\u002Fprepare_dataset.py` to convert.\n-   **Validation Split Confirmation**: If the user only provides a training\n    dataset, **you must prompt the user** to seek permission to split the\n    training dataset 80\u002F20 to form a validation dataset (using\n    `--validation_split 0.2`). If they agree, proceed with the split. If they\n    decline, just use the training dataset without a validation dataset.\n-   **Validation**: If data is already in JSONL, validate it before uploading.\n    Simply having a `.jsonl` extension is not enough. You must verify that the\n    content schema is valid for tuning (e.g. correct system\u002Fuser\u002Fmodel roles).\n\n```bash\npython3 scripts\u002Fprepare_dataset.py \\\n    --input my_data.jsonl \\\n    --format \u003Cmessages|messages_gemini> \\\n    --validate_only\n```\n\n*(Use `--format messages` for open models and `--format messages_gemini` for\nGemini models.)* - Refer to [Data Preparation Guide](references\u002Fdata_prep.md)\nfor required schemas.\n\n### 1.2 Upload\n\nUpload formatted `.jsonl` files to GCS using a unique directory (e.g., with a\ndatetime timestamp) to avoid overwriting outputs from different runs.\n\u003C!-- disableFinding(LINE_OVER_80) --> `bash\nARTIFACTS=\"gs:\u002F\u002FYOUR_BUCKET\u002Ftuning_agent_job_\u003Cdatetime>\u002Fdataset.jsonl\" gcloud\nstorage cp dataset.jsonl $ARTIFACTS` \u003C!-- enableFinding(LINE_OVER_80) -->\n\n## Phase 2: Model Configuration & Recommendation {#phase-2}\n\nHelp the user choose the best model and parameters. **Always seek user\nconfirmation before submitting the job.**\n\n-   If the user does not specify a specific model in their prompt, calculate\n    recommendations based on the **Models Catalog**.\n-   **Prompt for Confirmation:** Present the recommended model to the user and\n    ask for their confirmation before configuring hyperparameters.\n\n### 2.1 Configuration\n\n#### For Open Models\n\n-   Recommend `tuning_mode`, `epochs`, `learning_rate`, and `adapter_size`\n    based on the [Tuning Guide](references\u002Ftuning_guide.md) and model-specific\n    baselines in the [Models Catalog](references\u002Fmodels.md).\n\n### 2.2 Calculating Cost (Open Models Only)\n\n-   We can calculate a rough estimate of cost of tuning based on the dataset and\n    the selected model in the [Models Catalog](references\u002Fmodels.md):\n\n    ```bash\n    python3 scripts\u002Fcalculate_cost.py \\\n        --input my_data.jsonl \\\n        --model MODEL_NAME \\\n        --tuning_mode TUNING_MODE \\\n        --epochs epochs\n    ```\n\n> [!NOTE]\n> **Handling Missing Dataset Errors:** If `scripts\u002Fcalculate_cost.py` fails\n> because the dataset file (e.g. `my_data.jsonl` or `dummy_data.jsonl`) cannot\n> be found, you **MUST** inform the user that the dataset file does not exist or\n> cannot be accessed. You **MUST** prompt the user to provide a valid dataset\n> path, and stop tool execution immediately to wait for their response. Do\n> **NOT** retry or loop, do **NOT** invent a specific cost number, and do\n> **NOT** prompt for job submission approval before receiving a valid dataset\n> from the user.\n\n-   **Prompt for Confirmation:** Present the recommended hyperparameter\n    configuration and estimated cost to the user and ask for their approval\n    before proceeding to job submission. Make sure to note that the estimated\n    cost is just an estimate and can vary from actual billing costs.\n\n## Phase 3: Tuning Job Execution {#phase-3-tuning-job-execution}\n\n**CRITICAL Pre-Flight Check (GCS Verification):** Before you propose a\nconfirmation prompt or submit any tuning job, you **MUST** verify that the\nspecified training dataset GCS URI (e.g. `gs:\u002F\u002Fdummy_bucket\u002Fdataset.jsonl` or\n`gs:\u002F\u002FYOUR_BUCKET\u002F...`) actually exists and is accessible. Run\n`gcloud storage ls $DATASET_URI` (or `gsutil ls`).\n\n*   **If the verification fails** (e.g. `BucketNotFound`, `404`, `AccessDenied`,\n    or indicating a dummy\u002Fmissing bucket), you **MUST** inform the user that the\n    GCS bucket or dataset does not exist or cannot be accessed. You **MUST**\n    prompt the user to provide a valid GCS URI for the dataset, and stop tool\n    execution immediately to wait for their response. Do **NOT** propose a\n    confirmation prompt and do **NOT** execute any tuning scripts before\n    receiving a valid dataset URI from the user.\n*   **If the verification succeeds**, proceed to propose the confirmation prompt\n    below.\n\n### For Gemini Models\n\nCheck if `scripts\u002Ftune_gemini_model.py` exists.\n\n-   **If `scripts\u002Ftune_gemini_model.py` exists:** Submit the Gemini model tuning\n    job using this script.\n\n    ```bash\n    python3 scripts\u002Ftune_gemini_model.py\n    ```\n\n-   **If `scripts\u002Ftune_gemini_model.py` does not exist:** Instruct the user to\n    manually configure and submit the tuning job via the Google Cloud Console\n    UI or using the Agent Platform SDK for Python.\n\n### For Open Models\n\nSubmit the open model tuning job using `scripts\u002Ftune_open_model.py`. Identify\nthe model id using available models documentation at\n\u003C!-- disableFinding(LINE_OVER_80) -->\n[documentation](https:\u002F\u002Fdocs.cloud.google.com\u002Fgemini-enterprise-agent-platform\u002Fmodels\u002Fopen-model-tuning.md.txt).\n\u003C!-- enableFinding(LINE_OVER_80) -->\n\n```bash\npython3 scripts\u002Ftune_open_model.py \\\n    --project YOUR_PROJECT \\\n    --location YOUR_LOCATION \\\n    --base_model BASE_MODEL_ID \\\n    --train_dataset gs:\u002F\u002FYOUR_BUCKET\u002Ftuning_agent_job_\u003Cdatetime>\u002Fdataset.jsonl \\\n    --output_uri gs:\u002F\u002FYOUR_BUCKET\u002Ftuning_agent_job_\u003Cdatetime>\u002Foutput \\\n    --epochs EPOCHS \\\n    --learning_rate LR \\\n    --tuning_mode MODE\n```\n\n> [!IMPORTANT]\n> **Interactive Confirmation Required (Tier M):** Before proceeding with job\n> submission, you **MUST** present the proposed command string showing all\n> literal flags in a confirmation prompt to the user with 'Yes' and 'No'\n> options.\n\n> **CRITICAL:** When presenting this confirmation prompt to the user, you MUST\n> output it as a direct plain text response and stop tool execution immediately.\n> Do NOT call any command execution or interactive tools in the same turn, as\n> unexpected tool calls may be auto-replied by the simulation harness and cause\n> an infinite loop. Yield immediately for the user's reply.\n\n## Phase 4: Monitoring {#phase-4-monitoring}\n\nMonitor the job via the Cloud Console link provided in the script output.\nAdditionally, ask the user if they want you to monitor the job status for them\nin the background. If they agree, execute `scripts\u002Fmonitor_tuning_job.py` as\na background task to periodically poll the job status and notify the user to\nshow the status. If the user declines, leave it completely to the user to\ncheck on the status.\n\n## Phase 5: Model Deployment {#phase-5-model-deployment}\n\nOnce the tuning job is `SUCCEEDED`, deploy the model.\n\n```bash\nARTIFACTS=\"gs:\u002F\u002FYOUR_BUCKET\u002Ftuning_agent_job_\u003Cdatetime>\u002Foutput\u002Fpostprocess\u002Fnode-0\u002Fcheckpoints\u002Ffinal\"\ngcloud ai model-garden models deploy \\\n    --project=YOUR_PROJECT \\\n    --region=YOUR_LOCATION \\\n    --model=\"$ARTIFACTS\" \\\n    --machine-type=MACHINE_TYPE \\\n    --accelerator-type=ACCELERATOR_TYPE \\\n    --accelerator-count=COUNT\n```\n\n> [!IMPORTANT]\n> **Interactive Confirmation Required (Tier M):** Before proceeding with\n> deployment, you **MUST** present the proposed command string showing all\n> literal flags in a confirmation prompt to the user with 'Yes' and 'No'\n> options.\n\n> **CRITICAL:** When presenting this confirmation prompt to the user, you MUST\n> output it as a direct plain text response and stop tool execution immediately.\n> Do NOT call any command execution or interactive tools in the same turn, as\n> unexpected tool calls may be auto-replied by the simulation harness and cause\n> an infinite loop. Yield immediately for the user's reply.\n\nRefer to [Models Catalog](references\u002Fmodels.md) for hardware recommendations for\nspecific open models.\n\n## Resources\n\n-   [Data Preparation Guide](references\u002Fdata_prep.md)\n-   [Models Catalog](references\u002Fmodels.md)\n-   [Tuning Guide](references\u002Ftuning_guide.md)\n-   `scripts\u002Fprepare_dataset.py`: Data conversion & validation.\n-   `scripts\u002Ftune_open_model.py`: Open model tuning job submission.",{"name":5,"metadata":24,"description":7},{"category":25},"AiAndMachineLearning","main","be3de0244dc1a57e323d8160787ebb40fb64930e","public\u002Fapi\u002Fskills\u002Fgoogle\u002Fcloud\u002Fagent-platform-tuning","https:\u002F\u002Fgithub.com\u002FSolizardking\u002Fskillhub-main","https:\u002F\u002Fskills.x402.wtf","https:\u002F\u002Fgithub.com\u002FSolizardking","https:\u002F\u002Fmusebook.trade","Got a mile high and never came down","2026-10-08 23:20:13",{"source":8,"skillName":5,"commands":36,"prompt":46,"zipAvailable":47},[37,40,43],{"tool":38,"command":39},"npx","npx skills add Solizardking\u002Fskillhub-main --skill agent-platform-tuning",{"tool":41,"command":42},"bunx","bunx skills add Solizardking\u002Fskillhub-main --skill agent-platform-tuning",{"tool":44,"command":45},"pnpm","pnpm dlx skills add Solizardking\u002Fskillhub-main --skill agent-platform-tuning","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FSolizardking\u002Fskillhub-main\u002Fblob\u002Fmain\u002Fpublic\u002Fapi\u002Fskills\u002Fgoogle\u002Fcloud\u002Fagent-platform-tuning\u002FSKILL.md",true,[49,55,59,63,67,71,75,81,85,89,93,97],{"path":50,"resourceType":51,"resourceTypeDesc":52,"sizeBytes":53,"sourceHtmlUrl":54},"metadata.json","REFERENCE","参考文档",522,"https:\u002F\u002Fgithub.com\u002FSolizardking\u002Fskillhub-main\u002Fblob\u002Fmain\u002Fpublic\u002Fapi\u002Fskills\u002Fgoogle\u002Fcloud\u002Fagent-platform-tuning\u002Fmetadata.json",{"path":56,"resourceType":51,"resourceTypeDesc":52,"sizeBytes":57,"sourceHtmlUrl":58},"references\u002Fdata_prep.md",1676,"https:\u002F\u002Fgithub.com\u002FSolizardking\u002Fskillhub-main\u002Fblob\u002Fmain\u002Fpublic\u002Fapi\u002Fskills\u002Fgoogle\u002Fcloud\u002Fagent-platform-tuning\u002Freferences\u002Fdata_prep.md",{"path":60,"resourceType":51,"resourceTypeDesc":52,"sizeBytes":61,"sourceHtmlUrl":62},"references\u002Fhf_datasets.md",5021,"https:\u002F\u002Fgithub.com\u002FSolizardking\u002Fskillhub-main\u002Fblob\u002Fmain\u002Fpublic\u002Fapi\u002Fskills\u002Fgoogle\u002Fcloud\u002Fagent-platform-tuning\u002Freferences\u002Fhf_datasets.md",{"path":64,"resourceType":51,"resourceTypeDesc":52,"sizeBytes":65,"sourceHtmlUrl":66},"references\u002Fmodels.md",2811,"https:\u002F\u002Fgithub.com\u002FSolizardking\u002Fskillhub-main\u002Fblob\u002Fmain\u002Fpublic\u002Fapi\u002Fskills\u002Fgoogle\u002Fcloud\u002Fagent-platform-tuning\u002Freferences\u002Fmodels.md",{"path":68,"resourceType":51,"resourceTypeDesc":52,"sizeBytes":69,"sourceHtmlUrl":70},"references\u002Frequirements.txt",137,"https:\u002F\u002Fgithub.com\u002FSolizardking\u002Fskillhub-main\u002Fblob\u002Fmain\u002Fpublic\u002Fapi\u002Fskills\u002Fgoogle\u002Fcloud\u002Fagent-platform-tuning\u002Freferences\u002Frequirements.txt",{"path":72,"resourceType":51,"resourceTypeDesc":52,"sizeBytes":73,"sourceHtmlUrl":74},"references\u002Ftuning_guide.md",2206,"https:\u002F\u002Fgithub.com\u002FSolizardking\u002Fskillhub-main\u002Fblob\u002Fmain\u002Fpublic\u002Fapi\u002Fskills\u002Fgoogle\u002Fcloud\u002Fagent-platform-tuning\u002Freferences\u002Ftuning_guide.md",{"path":76,"resourceType":77,"resourceTypeDesc":78,"sizeBytes":79,"sourceHtmlUrl":80},"scripts\u002Fcalculate_cost.py","SCRIPT","脚本",4887,"https:\u002F\u002Fgithub.com\u002FSolizardking\u002Fskillhub-main\u002Fblob\u002Fmain\u002Fpublic\u002Fapi\u002Fskills\u002Fgoogle\u002Fcloud\u002Fagent-platform-tuning\u002Fscripts\u002Fcalculate_cost.py",{"path":82,"resourceType":77,"resourceTypeDesc":78,"sizeBytes":83,"sourceHtmlUrl":84},"scripts\u002Fcancel_tuning_job.py",999,"https:\u002F\u002Fgithub.com\u002FSolizardking\u002Fskillhub-main\u002Fblob\u002Fmain\u002Fpublic\u002Fapi\u002Fskills\u002Fgoogle\u002Fcloud\u002Fagent-platform-tuning\u002Fscripts\u002Fcancel_tuning_job.py",{"path":86,"resourceType":77,"resourceTypeDesc":78,"sizeBytes":87,"sourceHtmlUrl":88},"scripts\u002Fmonitor_tuning_job.py",2183,"https:\u002F\u002Fgithub.com\u002FSolizardking\u002Fskillhub-main\u002Fblob\u002Fmain\u002Fpublic\u002Fapi\u002Fskills\u002Fgoogle\u002Fcloud\u002Fagent-platform-tuning\u002Fscripts\u002Fmonitor_tuning_job.py",{"path":90,"resourceType":77,"resourceTypeDesc":78,"sizeBytes":91,"sourceHtmlUrl":92},"scripts\u002Fprepare_dataset.py",8242,"https:\u002F\u002Fgithub.com\u002FSolizardking\u002Fskillhub-main\u002Fblob\u002Fmain\u002Fpublic\u002Fapi\u002Fskills\u002Fgoogle\u002Fcloud\u002Fagent-platform-tuning\u002Fscripts\u002Fprepare_dataset.py",{"path":94,"resourceType":77,"resourceTypeDesc":78,"sizeBytes":95,"sourceHtmlUrl":96},"scripts\u002Ftune_open_model.py",3099,"https:\u002F\u002Fgithub.com\u002FSolizardking\u002Fskillhub-main\u002Fblob\u002Fmain\u002Fpublic\u002Fapi\u002Fskills\u002Fgoogle\u002Fcloud\u002Fagent-platform-tuning\u002Fscripts\u002Ftune_open_model.py",{"path":98,"resourceType":51,"resourceTypeDesc":52,"sizeBytes":99,"sourceHtmlUrl":100},"verification.json",2898,"https:\u002F\u002Fgithub.com\u002FSolizardking\u002Fskillhub-main\u002Fblob\u002Fmain\u002Fpublic\u002Fapi\u002Fskills\u002Fgoogle\u002Fcloud\u002Fagent-platform-tuning\u002Fverification.json",[102,109,116,123,130,138],{"skillNo":103,"name":104,"nameZh":6,"description":105,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":106,"categories":107,"keywords":108,"publishedAt":19},"01M78E0TGCAMNPS207BA3G07S7","zkrouter","Self-hosted OpenAI-compatible LLM router — smart tier-based routing, ZK-stamped routing decisions, mode overrides, free OpenRouter at install via the Birth bot. Save 60-80% on inference costs by routing to the cheapest capable model across 12+ OpenRouter models.","https:\u002F\u002Fgithub.com\u002FSolizardking\u002Fskillhub-main\u002Fblob\u002Fmain\u002Fskills\u002Fzkrouter\u002FSKILL.md",[],[],{"skillNo":110,"name":111,"nameZh":6,"description":112,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":113,"categories":114,"keywords":115,"publishedAt":19},"01M78E0R1Z8BDT6EDTHY17MTNB","zk","For custom ZK Solana programs and privacy-preserving applications to prevent double spending. Guide to integrate rent-free nullifier PDAs for double-spend prevention.","https:\u002F\u002Fgithub.com\u002FSolizardking\u002Fskillhub-main\u002Fblob\u002Fmain\u002Fskills\u002Fzk\u002FSKILL.md",[],[],{"skillNo":117,"name":118,"nameZh":6,"description":119,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":120,"categories":121,"keywords":122,"publishedAt":19},"01M78E0P3ZTZ1YWF8MD5MM23QE","zk-omni-messaging","Zero-knowledge omnichain messaging between Robinhood Chain and Solana using CheshireZkOmniMessenger (msgType 4) with nullifier anti-replay and the zk-omni-relayer service.","https:\u002F\u002Fgithub.com\u002FSolizardking\u002Fskillhub-main\u002Fblob\u002Fmain\u002Fskills\u002Fzk-omni-messaging\u002FSKILL.md",[],[],{"skillNo":124,"name":125,"nameZh":6,"description":126,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":127,"categories":128,"keywords":129,"publishedAt":19},"01M78E0JXZ2PNB1896VXAGDBWD","zerion-wallet-data","Use when the user asks to check a wallet's portfolio, token balances, DeFi positions, PnL, transaction history, or NFTs. Provides interpreted on-chain data across 40+ EVM chains and Solana via x402 pay-per-request or API key — no raw RPC decoding needed.","https:\u002F\u002Fgithub.com\u002FSolizardking\u002Fskillhub-main\u002Fblob\u002Fmain\u002Fskills\u002Fzerion-wallet-data\u002FSKILL.md",[],[],{"skillNo":131,"name":132,"nameZh":6,"description":133,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":134,"sourceHtmlUrl":135,"categories":136,"keywords":137,"publishedAt":19},"01M78E0G14FH9GRRTQYMKD5E59","youtube-clipper","YouTube 视频智能剪辑工具。下载视频和字幕，AI 分析生成精细章节（几分钟级别）， 用户选择片段后自动剪辑、翻译字幕为中英双语、烧录字幕到视频，并生成总结文案。 使用场景：当用户需要剪辑 YouTube 视频、生成短视频片段、制作双语字幕版本时。 关键词：视频剪辑、YouTube、字幕翻译、双语字幕、视频下载、clip video","https:\u002F\u002Fgithub.com\u002FSolizardking\u002Fskillhub-main\u002Fblob\u002Fmain\u002Fskills\u002Fyoutube-clipper\u002FLICENSE","https:\u002F\u002Fgithub.com\u002FSolizardking\u002Fskillhub-main\u002Fblob\u002Fmain\u002Fskills\u002Fyoutube-clipper\u002FSKILL.md",[],[],{"skillNo":139,"name":140,"nameZh":6,"description":141,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":142,"categories":143,"keywords":144,"publishedAt":19},"01M78E0C2ZYA99CFFDNB7ZMK5S","yield-optimization","Multi-chain yield optimization via yield.xyz (StakeKit). Discover 2,988+ yield opportunities across 75+ blockchains, build deposit\u002Fwithdrawal transactions with shell scripts, and sign them with a MoonPay wallet. Use when the user wants to earn yield, find the best lending or staking rate, enter\u002Fexit a position, or check portfolio balances.","https:\u002F\u002Fgithub.com\u002FSolizardking\u002Fskillhub-main\u002Fblob\u002Fmain\u002Fskills\u002Fyield-optimization\u002FSKILL.md",[],[]]