技能创建器
skill-creator
创建、改进和评估自定义技能,把专业流程转化为可重复使用的 AI 能力。
datastore-search【数据与研究】Use DeepFace database-backed register, search, ANN indexing, connection configuration, vector database backends, and datastore troubleshooting.
独立 GitHub 快照 · 自动分类 · 以原作者文档为准
Use this sub-skill when the user task needs DeepFace.register, DeepFace.search, DeepFace.build_index, database_type, connection_details, connection objects, exact versus ANN search, vector-native backends, optional database clients, and service/schema failures.
Local folder-backed DeepFace.find goes to ../recognition-workflows/SKILL.md; API database routes go to ../api-service/SKILL.md; model/detector selection goes to ../model-and-backend-selection/SKILL.md.
from deepface import DeepFace works; otherwise use ../../references/troubleshooting.md.references/api-reference.md documents signatures, parameters, outputs, and API-specific behavior for this sub-skill.references/workflows.md or the focused workflow reference contains practical recipes and decision patterns.references/troubleshooting.md maps common errors to concrete recovery steps.scripts/check_database_config.py is the safe bundled helper for this sub-skill.Do not tell future agents to open or run original repository tests, examples, notebooks, scripts, or local checkout files. Use this self-contained sub-skill, its references, and its bundled helper scripts instead.