القائمة
Data pipelines, ingest, remediation, entity quality — PDF/docs through to vector store.
التثبيت باستخدام Codex أو Claude انسخ هذا Prompt والصقه في Codex أو Claude أو مساعد آخر ليراجع صفحة Skill ويثبّتها لك.
استنادا إلى تصنيف SOC المهني
AI feature engineering — llama, embeddings, RAG quality, inference reliability, cost/token discipline.
System architecture, structured code review bar, and technical documentation.
Backend HTTP API, SQLite, Qdrant, integration contracts, schema and migration safety.
Maturity / inspection pass over [ORG_NAME] code sections (BCS). Load your org’s code-sections ledger, run verify ladder, update shared_context summary on main when columns change.
Decision continuity, handoffs, supersession — Engineering Orchestrator (Mike) accountable; pair with session-notes.
Production frontend work — React 19, TypeScript, Vite, PrimeReact, [ORG_NAME] apps (client, system-console, dashboard).
| name | data-and-ingest |
| description | Data pipelines, ingest, remediation, entity quality — PDF/docs through to vector store. |
| when_to_use | Ingest path, converters, parsers, ETL, data quality, remediation, telemetry aggregation. |
Data Engineer and related specialists use this skill for content and data entering the system (Orchestrator coordinates cross-lane work).
[PRODUCT_CODE_ROOT]/ (paths per active architecture)[PRODUCT_CODE_ROOT]/docs/agent_method/phase1_legacy_ingest_delegate_briefs_v1.md — ephemeral subagent briefs L1 / L2 / L3org_engineering/agents/ specs + this skill.phase1_legacy_ingest_delegate_briefs_v1.md + product docs.ai-pipeline and backend-rag-integrationlegacy-audit-checkSubagents may trace one document class; River (Data Engineer) owns slice integrity; Mike owns end-to-end gate at release boundaries.