- name
SKILL.md
技能檔案保留在發布者的儲存庫中。
在終端機中貼上複製的指令。它會將這個 SKILL.md 安裝到對應的代理中。
npx skills add awslabs/agent-plugins --skill dataset-evaluation -a cursor -y在終端機中貼上複製的指令。它會將這個 SKILL.md 安裝到對應的代理中。
npx skills add awslabs/agent-plugins --skill dataset-evaluation -a claude-code -y在終端機中貼上複製的指令。它會將這個 SKILL.md 安裝到對應的代理中。
npx skills add awslabs/agent-plugins --skill dataset-evaluation -a codex -y在終端機中貼上複製的指令。它會將這個 SKILL.md 安裝到對應的代理中。
npx skills add awslabs/agent-plugins --skill dataset-evaluation -a grok -y在 Grok Bot 聊天中傳送複製的訊息。Bot 會從 GitHub 取得這個 SKILL.md,並加入你所有 Bot 共用的技能中。
Install this skill: https://github.com/awslabs/agent-plugins/tree/HEAD/plugins/sagemaker-ai/skills/dataset-evaluation來自發布者
Follow the workflow shown below. Locate the dataset, check the file type, and resolve any issues with missing files or wrong file types. Determine the fine-tuning model and fine-tuning strategy. Run the appropriate validation based on the model family. Summarize the results: is the dataset ready for fine-tuning?
sdk-getting-started skill first.Locate Dataset:
Determine strategy and model:
Check File Formatting: Run the tool format_detector.py to make sure the file conforms to formatting requirements.
Summarize Results: Tell the user if their data is ready
references/strategy_data_requirements.mdreferences/custom-scorer-evaluation-dataset-formats.md and validate against the scorer-specific schema. The scorer type should be known from conversation context (determined in the model-evaluation skill).# With the file path argument identified in workflow step 1
python scripts/format_detector.py local_path/to/dataset
scripts/format_detector.py — Self-contained format validation scriptreferences/strategy_data_requirements.md — Data format requirements per strategyValidates dataset formatting and quality for SageMaker model fine-tuning (SFT, DPO, or RLVR). Use when the user says "is my dataset okay", "evaluate my data", "check my training data", "I have my own
---name: dataset-evaluationdescription: Validates dataset formatting and quality for SageMaker model fine-tuning (SFT, DPO, or RLVR). Use when the…---# plugins/sagemaker-ai/skills/dataset-evaluation/SKILL.md總覽
Validates dataset formatting and quality for SageMaker model fine-tuning (SFT, DPO, or RLVR). Use when the user says "is my dataset okay", "evaluate my data", "check my training data", "I have my own data", or before starting any fine-tuning job. Detects file format, checks schema compliance against the selected model and technique, and reports whether the data is ready for training or evaluation.
常見問題
從發布者下載 plugins/sagemaker-ai/skills/dataset-evaluation/SKILL.md,或複製路徑後開啟儲存庫。PlugMCP 只收錄這項技能,不代管檔案。
發布者將它存放在 https://github.com/awslabs/agent-plugins。
Claude、Cursor、Codex 和 Grok Build 可以讀取你從發布者儲存庫加入的 SKILL.md。在聊天中傳送技能的 GitHub 資料夾連結,Grok Bot 就會安裝它。