{"id":"88b8f5e5-de00-4fe5-812c-b17cde0127df","slug":"clawhub-skills-1kalin-afrexai-ml-engineering","name":"afrexai-ml-engineering","description":"ML & AI Engineering System","canonicalUrl":"https://www.xpersona.co/agent/clawhub-skills-1kalin-afrexai-ml-engineering","sourceUrl":"https://github.com/openclaw/skills/tree/main/skills/1kalin/afrexai-ml-engineering","homepage":null,"source":"CLAWHUB","vendor":{"slug":"openclaw","label":"Openclaw","url":"https://github.com/openclaw/skills/tree/main/skills/1kalin/afrexai-ml-engineering"},"protocols":["OPENCLEW"],"capabilities":["update"],"trustScore":null,"trustConfidence":"unknown","artifactCount":0,"benchmarkCount":0,"lastRelease":null,"freshnessAt":"2026-02-25T06:17:44.083Z","freshnessLabel":"Feb 25, 2026","securityReviewed":true,"openapiReady":false,"stats":[{"label":"Trust score","value":"Unknown"},{"label":"Compatibility","value":"OpenClaw"},{"label":"Freshness","value":"Feb 25, 2026"},{"label":"Vendor","value":"Openclaw"},{"label":"Artifacts","value":"0"},{"label":"Benchmarks","value":"0"},{"label":"Last release","value":"Unpublished"}],"factsPreview":[{"factKey":"docs_crawl","category":"integration","label":"Crawlable docs","value":"6 indexed pages on the official domain","href":"https://github.com/login?return_to=https%3A%2F%2Fgithub.com%2Fopenclaw%2Fskills%2Ftree%2Fmain%2Fskills%2Fasleep123%2Fcaldav-calendar","sourceUrl":"https://github.com/login?return_to=https%3A%2F%2Fgithub.com%2Fopenclaw%2Fskills%2Ftree%2Fmain%2Fskills%2Fasleep123%2Fcaldav-calendar","sourceType":"search_document","confidence":"medium","observedAt":"2026-04-15T05:03:46.393Z","isPublic":true},{"factKey":"vendor","category":"vendor","label":"Vendor","value":"Openclaw","href":"https://github.com/openclaw/skills/tree/main/skills/1kalin/afrexai-ml-engineering","sourceUrl":"https://github.com/openclaw/skills/tree/main/skills/1kalin/afrexai-ml-engineering","sourceType":"profile","confidence":"medium","observedAt":"2026-04-15T00:45:39.800Z","isPublic":true},{"factKey":"protocols","category":"compatibility","label":"Protocol compatibility","value":"OpenClaw","href":"https://www.xpersona.co/api/v1/agents/clawhub-skills-1kalin-afrexai-ml-engineering/contract","sourceUrl":"https://www.xpersona.co/api/v1/agents/clawhub-skills-1kalin-afrexai-ml-engineering/contract","sourceType":"contract","confidence":"medium","observedAt":"2026-04-15T00:45:39.800Z","isPublic":true},{"factKey":"handshake_status","category":"security","label":"Handshake status","value":"UNKNOWN","href":"https://www.xpersona.co/api/v1/agents/clawhub-skills-1kalin-afrexai-ml-engineering/trust","sourceUrl":"https://www.xpersona.co/api/v1/agents/clawhub-skills-1kalin-afrexai-ml-engineering/trust","sourceType":"trust","confidence":"medium","observedAt":null,"isPublic":true}],"highlights":["Trust evidence available"],"agentCard":{"name":"afrexai-ml-engineering","description":"ML & AI Engineering System","source":"CLAWHUB","sourceId":"clawhub:skills:1kalin:afrexai-ml-engineering","repository":"https://github.com/openclaw/skills/tree/main/skills/1kalin/afrexai-ml-engineering","documentation":"https://www.xpersona.co/agent/clawhub-skills-1kalin-afrexai-ml-engineering","protocols":["OPENCLEW"],"capabilities":["update"],"languages":["typescript"],"examples":[{"kind":"example","language":"yaml","snippet":"problem_brief:\n  business_objective: \"\"          # What business metric improves?\n  success_metric: \"\"              # Quantified target (e.g., \"reduce churn 15%\")\n  baseline: \"\"                    # Current performance without ML\n  ml_task_type: \"\"                # classification | regression | ranking | generation | clustering | anomaly_detection | recommendation\n  prediction_target: \"\"           # What exactly are we predicting?\n  prediction_consumer: \"\"         # Who/what uses the prediction? (API | dashboard | email | automated action)\n  latency_requirement: \"\"         # real-time (<100ms) | near-real-time (<1s) | batch (minutes-hours)\n  data_available: \"\"              # What data exists today?\n  data_gaps: \"\"                   # What's missing?\n  ethical_considerations: \"\"      # Bias risks, fairness requirements, privacy\n  kill_criteria:                  # When to abandon the ML approach\n    - \"Baseline heuristic achieves >90% of ML performance\"\n    - \"Data quality too poor after 2 weeks of cleaning\"\n    - \"Model can't beat random by >10% on holdout set\""},{"kind":"example","language":"yaml","snippet":"feature_types:\n  numerical:\n    - raw_value           # Use as-is if normally distributed\n    - log_transform       # Right-skewed distributions (revenue, counts)\n    - standardize         # z-score for algorithms sensitive to scale (SVM, KNN, neural nets)\n    - bin_to_categorical  # When relationship is non-linear and data is limited\n  categorical:\n    - one_hot             # <20 categories, tree-based models handle natively\n    - target_encoding     # High-cardinality (>20 categories), use with K-fold to prevent leakage\n    - embedding           # Very high-cardinality (user IDs, product IDs) with deep learning\n  temporal:\n    - lag_features        # Value at t-1, t-7, t-30\n    - rolling_statistics  # Mean, std, min, max over windows\n    - time_since_event    # Days since last purchase, hours since login\n    - cyclical_encoding   # sin/cos for hour-of-day, day-of-week, month\n  text:\n    - tfidf               # Simple, interpretable, good baseline\n    - sentence_embeddings # semantic similarity, modern NLP\n    - llm_extraction      # Use LLM to extract structured fields from unstructured text\n  interaction:\n    - ratios              # Feature A / Feature B (e.g., clicks/impressions = CTR)\n    - differences         # Feature A - Feature B (e.g., price - competitor_price)\n    - polynomial          # A * B, A^2 (use sparingly, high-cardinality features)"}]}}