菜单
Pure routing table. Detects DB from context, hands off to the right curated specialist or dynamic-specialist. Carries zero specialist content itself.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
| name | db-router |
| description | Pure routing table. Detects DB from context, hands off to the right curated specialist or dynamic-specialist. Carries zero specialist content itself. |
| Keywords detected | Hand off to |
|---|---|
postgres psql pg neon supabase pgvector timescale cockroachdb | postgres-specialist |
redis valkey upstash elasticache keydb | redis-specialist |
oracle plsql autonomous db oracle 23ai | oracle-db-specialist |
kafka confluent redpanda msk | kafka-specialist |
qdrant pinecone weaviate chroma vector search vector db embeddings db | vector-db-specialist |
mysql mariadb aurora mysql planetscale | dynamic-specialist — platform: MySQL |
mongo mongodb atlas mongoose documentdb | dynamic-specialist — platform: MongoDB |
databricks delta lake spark sql unity catalog mlflow | dynamic-specialist — platform: Databricks |
snowflake snowpark cortex snowpipe | dynamic-specialist — platform: Snowflake |
dynamodb dynamo | dynamic-specialist — platform: DynamoDB |
cassandra scylladb astra db | dynamic-specialist — platform: Cassandra |
sqlite libsql turso | dynamic-specialist — platform: SQLite |
| anything else | dynamic-specialist — platform: [detected DB name] |
Multiple DBs in one message → ask which is primary before routing.
dynamic-specialist rates MySQL/Mongo/Databricks/Snowflake as HIGH confidence — no search agent needed.Initialize Raven for a new project. Andie-conversational — auto-scans project, asks at most 2 questions, generates manifest.json, validates, and commits with audit trail.
USE PROACTIVELY whenever the user asks for: planning, design, architecture decision, tradeoff analysis, comparing approaches, strategy, system design, refactor scope, deciding what to build, or any non-trivial request needing clarification. Also USE when user says 'should I', 'how do I approach', 'plan this', 'design', 'review options'. Compact plan-first orchestration. Routes work, runs triad (Functional/Technical/Data), HITL gated, OODA loop. Hands off plans, never implements. Brownfield bugs → andie-jr.
USE PROACTIVELY whenever the user reports: a bug, error, exception, stack trace, regression, test failure, 'not working', 'broken', 'why is X failing', 'X stopped working', 'doesn't behave', unexpected output. Brownfield debug assistant. Max 2 rounds, max 3 roles, returns problem · root cause · fix · why · audit note · commit suggestion. Do NOT use for greenfield design — that goes to andie.
USE PROACTIVELY whenever the user asks for: planning, design, architecture decision, tradeoff analysis, comparing approaches, strategy, system design, refactor scope, deciding what to build, or any non-trivial request needing clarification. Also USE when user says 'should I', 'how do I approach', 'plan this', 'design', 'review options'. Compact plan-first orchestration. Routes work, runs triad (Functional/Technical/Data), HITL gated, OODA loop. Hands off plans, never implements. Brownfield bugs → andie-jr.
Tool and product registry for Andie pre-flight. Maps problem types to tool options with tradeoffs. Covers LLMs, vector DBs, streaming, orchestration, IaC, monitoring, secrets, CI/CD, search, auth, open source infra, and cloud platforms. Load when a tool selection decision is in scope.
Tool and product registry for Andie pre-flight. Maps problem types to tool options with tradeoffs. Covers LLMs, vector DBs, streaming, orchestration, IaC, monitoring, secrets, CI/CD, search, auth, open source infra, and cloud platforms. Load when a tool selection decision is in scope.