> ## Documentation Index > Fetch the complete documentation index at: https://docs.nodaldata.io/llms.txt > Use this file to discover all available pages before exploring further. # The skills > Seven small, composable agent workflows — build context, then plan, verify, and challenge answers. The open-source repo installs **seven skills** into your agent. They're small and composable — invoke one directly, or just ask a question and let the agent route to the right workflow. Three build and maintain your context; four govern how questions get answered against it. ## Build and maintain context Configures the project once: probes your read-only warehouse connection (read-query, metadata, query-history), discovers nearby dbt and context sources, and optionally binds a local browser for dashboard verification. Writes only sanitized paths and capability classifications to a gitignored `.nodal.local.json` — never credentials. Runs only when explicitly requested. The core workflow — interviews your analyst to [build or improve](/open-source/build-your-context) an ACF context repo, one domain at a time. Every confirmed disambiguation also becomes an eval seed. Captures critical domain knowledge when an analyst changes roles or leaves. Instead of an unstructured exit-interview transcript, it orchestrates the governed interview — so the departing analyst's knowledge lands as reviewable context and eval seeds. ## Ask and verify The question-answering path is deliberately reviewable: ```text theme={null} business question → analytics plan → read-only query → result verification → answer ↓ if challenged independent challenge → uphold or replan ``` Translates a business question into a reviewable plan *before any SQL runs* — the interpretation, grain, filters, time semantics, and query plan, grounded in your ACF, dbt, docs, and warehouse evidence. Missing definitions produce a clarification or an expert-escalation recommendation, not a falsely confident answer. After the read-only SQL runs, checks the executed query and result against the approved plan — metric, filter, grain, join, and time fidelity — then assesses plausibility and whether escalation is needed. A skeptical second review when an answer looks wrong or you want another take. It reconstructs the intended analysis, tests alternative interpretations and failure modes, and returns **upheld**, **inconclusive**, or **replan** — a replan goes back through `analytics-plan` for fresh approval. Reads a named BI dashboard in your own local, already-authenticated browser — capturing both the visible values and the active filters — so answers reconcile against your source of truth. It never handles credentials and is configured only with your consent. ## Why plan-then-verify SQL can execute successfully at the wrong grain, omit a mandatory filter, use a noncanonical metric, or fan out through a join. `analytics-plan` makes intent explicit before execution; `verify-result` checks whether the query and result actually satisfied that intent afterward. Plans and verified results carry an explicitly *uncalibrated* uncertainty estimate — it records unresolved semantics and evidence gaps and recommends expert escalation when a reliable answer can't be supported. It's a decision aid, not a statistical confidence score. ## Next Install the plugin and run the interview. Measure accuracy with vs. without your context.