Loading...
Loading...
Found 680 Skills
Use when driving Xiaohongshu followers to private domains like WeChat, building offline communities, implementing follower retention strategies beyond platform, or creating sustainable audience ownership independent of platform algorithms
You are a real-time conversation expert who thrives in Twitter's fast-paced, information-rich environment. You understand that Twitter success comes from authentic participation in ongoing conversa...
Elicits and prioritises user needs (needs, pains, desires) as job stories — produces opportunities ready for product strategy
Connects user opportunities to business outcomes and solution bets — produces a strategy tree and prioritised experiments
Complete Operation Guide for Zsxq CLI (zsxq-cli), covering all scenarios of Zsxq (Knowledge Planet) and content management. This Skill must be used when users mention Zsxq, zsxq, Xiaomiquan (former name of Zsxq), login/authentication, posting, commenting, answering, editing, deleting topics, notes, digest, tags/hashtag, members, footprints, question records, share links, NPS feedback, group_id, topic_id; need to login/check authentication status, view/search/publish/edit/manage Zsxq content; perform operation scenarios such as daily patrol, comment section operation, question management, digest and tag organization, operation daily/weekly report & review, generating Zsxq daily poster images, generating vertical animated videos, negative content monitoring, batch tagging, renewal care for expiring members, archiving topics to columns; splice share links, directly call underlying APIs (api call / api raw), check member lists/member expiration dates/column lists; or need to check/migrate/clean up legacy Zsxq Skills (such as upgrading zsxq-shared, zsxq-group to a single zsxq). It should be triggered even if only a single operation is involved (e.g., obtaining group_id, viewing post details, replying to comments).
Use when asked to find skill opportunities in a codebase, audit a repo for automatable workflows, decide what skills to write, or mine git history and existing automation for recurring multi-step procedures worth turning into Claude Code skills.
MLflow 3 GenAI agent evaluation. Use when writing mlflow.genai.evaluate() code, creating @scorer functions, using built-in scorers (Guidelines, Correctness, Safety, RetrievalGroundedness), building eval datasets from traces, setting up trace ingestion and production monitoring, aligning judges with MemAlign from domain expert feedback, or running optimize_prompts() with GEPA for automated prompt improvement.
Train ML models on Databricks. Use for: classification/regression/deep-learning (XGBoost, scikit-learn, LightGBM, PyTorch) with Optuna, @prod/@challenger aliases, batch scoring (spark_udf for plain models, fe.score_batch for feature-store-backed), custom PyFunc, custom ResponsesAgent (LangGraph + UC Function/Vector Search); UC feature tables + FeatureLookup + point-in-time joins + Lakebase online store; declarative Feature Views (create_feature, DeltaTableSource, RollingWindow/SlidingWindow/TumblingWindow, materialize_features, streaming Kafka features). NOT for: endpoint ops (databricks-model-serving), MLflow evaluation (databricks-mlflow-evaluation).