polygres-retrieval-design
/polygres-retrieval-design
Design and review Polygres retrieval using available read-only MCP evidence across relational, graph, text, hybrid, and Polygres AI Context. Use for retrieval and embedding strategy selection, Context or graph design, grounded RAG planning, and compatibility review before implementation.
- Author
- evokoa ↗
- Repository
- polygres-skills ↗
- Licence
- Apache-2.0
- Last repository change
- 18.09.2026
Assessment and security
- Files in this package
- 11
- Scripts
- 0
- HTML comments
- 0
- URLs in SKILL.md
- 0
No signals detected. Repository changed on 18.09.2026, without references to retired models or APIs.
Apache-2.0, otwarta: można używać i zmieniać, z zachowaniem licencji i informacji o zmianach.
What it does and when to use it
Design and review Polygres retrieval using available read-only MCP evidence across relational, graph, text, hybrid, and Polygres AI Context. Use for retrieval and embedding strategy selection, Context or graph design, grounded RAG planning, and compatibility review before implementation.
Original author description
Design and review Polygres retrieval using available read-only MCP evidence across relational, graph, text, hybrid, and Polygres AI Context. Use for retrieval and embedding strategy selection, Context or graph design, grounded RAG planning, and compatibility review before implementation.
How it works
- Workflow
- Design rules
- Boundaries
- Completion
SKILL.md preview
--- name: polygres-retrieval-design description: Design and review Polygres retrieval using available read-only MCP evidence across relational, graph, text, hybrid, and Polygres AI Context. Use for retrieval and embedding strategy selection, Context or graph design, grounded RAG planning, and compatibility review before implementation. --- # Polygres Retrieval Design Produce a reviewable plan before retrieval configuration or application work. This skill is advisory: it must not mutate a project directly. When Polygres MCP tools are available, read [`references/mcp-tool-contract.md`](references/mcp-tool-contract.md) and use discovered read tools for bounded inspection. Call `whoami`, respect the connection's project boundary, and keep this skill read-only even when change tools are visible. ## Workflow 1. Extract the user outcome, authorization, latency, freshness, and expected result shape from the prompt and inspected application. Ask only for a missing fact that changes the recommendation; representative questions are useful evidence, not a mandatory interview. 2. Resolve project mode, then inspect the supplied schema, verified row identifiers, sample data, and existing retrieval configuration. Label missing evidence as unresolved; never infer production facts from a table or column name. 3. Select the smallest sufficient strategy using [`references/strategy-selection.md`](references/strategy-selection.md). Reject an unsupported strategy rather than inventing a capability. 4. For semantic retrieval, use [`references/embedding-design.md`](references/embedding-design.md) to compare Polygres generation, local or external generation, and existing vectors. For graph retrieval, apply [`references/graph-modeling.md`](references/graph-modeling.md). For an existing vector configuration, TSVector, or fuzzy retrieval, apply [`references/vector-and-text-design.md`](references/vector-and-text-design.md). When MCP Graph tools are available, also read [`references/mcp-graph-retrieval.md`](references/mcp-graph-retrieval.md) for evidence and handoff requirements. 5. For pgContext collections, point synchronization, registered filters, or Context retrieval modes, apply [`references/context-design.md`](references/context-design.md). 6. For multi-stage retrieval or RAG, apply [`references/hybrid-and-rag-plan.md`](references/hybrid-and-rag-plan.md). 7. Write the result with [`references/plan-template.md`](references/plan-template.md). When called by `$polygres-data-pipeline`, return the selected and omitted components plus exact public-interface handoffs in a machine-readable section so the caller can continue without another interview. 8. In a design-only request, return the plan. In an active data-pipeline setup, return control to the orchestrating skill with the user's existing authorization and any remaining decisions. ## Design rules - Prefer relational retrieval for exact predicates, joins, aggregates, and transactions that do not need a retrieval index. - For a synced project, keep exact SQL, transactions, and source mutations in the source PostgreSQL database. Use only the supported Runtime retrieval and retrieval-configuration surfaces on Polygres. - Treat graph, vector, text, and Context indexes and point mappings as derived project resources whose readiness and refresh behavior must be validated. - Use exact schema identifiers and stable row ID values from verified data. Do not use invented row IDs or fuzzy-match schema names. - Bound graph direction, depth, fan-out, result count, and cycle behavior. - Record who generates source and query embeddings, the saved model and revision, dimensions, metric, input construction, and separate generation and query budgets. Check the collection's selected vector before proposing query text through the existing SDK methods. - Default new semantic retrieval plans to a Polygres AI Context collection. Decide explicitly whether distinct embeddings belong as named vectors in one collection or require separate collection-level source and policy settings. Record any existing pgvector configuration that must remain compatible or needs a migration plan. Never treat those resources as interchangeable. On a synced project, choose either Polygres generation from an eligible synchronized text source or existing synchronized vectors. Polygres manages derived embedding output; source SQL and row writes stay in the source PostgreSQL database. - State TSVector language/configuration choices and fuzzy thresholds. - For hybrid retrieval, define stage order, provenance, deduplication, authorization, and token budget. - Include rebuild or reindex triggers, readiness checks, and rollback or fallback behavior. ## Boundaries - This skill must not mutate a project, generate secrets, or claim that a plan has been applied. - Do not write mutating command examples. Route approved configuration work to `$polygres-cli` and approved Python integration to `$polygres-sdk`. - Filters are not an authorization boundary. Apply access control before data enters retrieval and again when results are resolved. - If required columns, stable IDs, or a usable sample are absent, make a reversible provisional recommendation when possible. Stop only when the missing evidence makes every safe recommendation invalid. ## Completion Return the completed reviewable plan, unresolved assumptions, and public handoffs for setup and application queries. Identify any decision or approval still needed, taking the user's existing authorization into account.
Files in this package (11)
- SKILL.md 6 KB
- agents/openai.yaml 1 KB
- references/context-design.md 7 KB
- references/embedding-design.md 10 KB
- references/graph-modeling.md 2 KB
- references/hybrid-and-rag-plan.md 4 KB
- references/mcp-graph-retrieval.md 1 KB
- references/mcp-tool-contract.md 14 KB
- references/plan-template.md 7 KB
- references/strategy-selection.md 4 KB
- references/vector-and-text-design.md 4 KB
Versions
The database has no other skills named polygres-retrieval-design.
Identical content appears in 1 other GitHub folders. We show one copy with the highest score.
Database snapshot: 13.11.2026 · package version 704b0c5fa201 (SHA-256 digest of the entire package)
Downloads in the last 30 days: 0 · ranking
Report a problem with this skill: harmful content, incorrect descriptions or an author’s removal request.
Similar skills
- 100polygres-advisor
Find current Polygres guidance for setup, application integration, retrieval design, and troubleshooting by navigating the hosted skills library. Use when a task needs published Polygres guidance through web access. - 100polygres-data-pipeline
Set up or extend Polygres through available MCP tools and supported fallbacks for ingestion, memory, graph, embeddings, synchronization, retrieval, RAG, and agent integration. Use for personalized recommendations, complete data-pipeline setup, and verification from a short… - 90rag-architect
Use when the user asks to design RAG pipelines, optimize retrieval strategies, choose embedding models, implement vector search, or build knowledge retrieval systems. - 90rag-pipeline
Design a retrieval-augmented generation pipeline that answers from sources and can be trusted. Use when building or debugging RAG: chunking, embedding, retrieval, context assembly, and grounding. - 100rag-architect
Use when designing or modifying a RAG (Retrieval-Augmented Generation) pipeline — picking chunking strategy, embedding models, retrieval methods, reranking, fusion (RRF), abstention, multi-tenancy patterns, or evaluating whether RAG is the right tool at all. Triggers on phrases… - 100rag-architecture-designer
Design a Retrieval-Augmented Generation (RAG) pipeline architecture: ingestion, indexing, retrieval, generation, and evaluation components. Use when working on RAG architecture, retrieval pipelines, vector stores.