Alteryx

View saved version →

---
name: alteryx-asset-discovery
description: Find and verify existing Alteryx assets and datasets before designing or building a solution. Use when a request depends on knowing what already exists — locating workflows, macros, or data related to a business question, checking whether logic is already implemented, grounding a build in real data, verifying a dataset's schema, or finding example XML for an unsupported tool. Read-only.
---

# Alteryx Asset Discovery

Answer one question: **what existing Alteryx assets or datasets could help solve this problem?**

Discover and verify candidates, then report the evidence. Never create, modify, or run an asset as part of this process. Deciding whether an asset should be reused, extended, or replaced, proposing a solution topology, and judging what the product supports are all out of scope: they come after discovery, once the evidence is in hand. Finish discovery and report first, then perform these follow-on tasks if required.

## Discovery Scope

- Governed Alteryx One datasets, workflows, and macros returned by asset search.
- Local Alteryx workflows (`.yxmd`) and macros (`.yxmc`).
- Local datasets such as CSV, Excel, and YXDB files.

Search governed assets whenever the relevant MCP tools are available, even for a request that started with a local file.

## Agent Workflow

1. **Frame the need.** Extract the business objective, domain terms, expected inputs and outputs, time range, geography, system names, and other constraints worth searching on. Establish which environments are in play: local files, cloud, or both.
2. **Search broadly.** Search governed cloud assets, local files, or both, depending on which environments are in play and the scope of the request.
3. **Inspect candidates.** Establish a workflow's or macro's analytical purpose, inputs, outputs, transformations, and referenced assets, and verify a dataset's column names and types before presenting it as grounded context.
4. **Use workflows as discovery evidence.** Treat workflow Input and Output tools as pointers to canonical datasets, and referenced macros as reusable-logic candidates. Follow them to assets that did not match the original query.
5. **Refine and repeat.** Re-search using names, business concepts, owners, tags, and tool usage learned during inspection.
6. **Return grounded candidates.** Report what was found, why each candidate is relevant, what was verified, and every gap.

## Cloud Discovery

Use the read-only tools below through the `alteryx` MCP server. Client prefixes vary; use the exact tool names the active client exposes rather than inventing names.

| Tool                                            | When to use it                                                 | Required handling                                                     |
|-------------------------------------------------|----------------------------------------------------------------|-----------------------------------------------------------------------|
| `assets__search_alteryx_assets(query)`          | Search governed assets with a focused natural-language query.  | Treat results as candidates, not verified facts; extract IDs carefully. Follow the required handling in the tool's own description for the specifics (URN extraction, refinement discipline). |
| `designer__get_condensed_workflow(workflow_id)` | Inspect a cloud workflow or macro.                             | This is the evidence that verifies a workflow candidate.              |
| `datasets__preview_dataset(datasetId, limit)`   | Verify a governed dataset's schema and inspect a small sample. | Pass the dataset ID in the current preview contract; respect returned limits and never use repeated previews to bulk-extract. |

Translate the business question into focused searches rather than broad ones. Search relevance depends on the metadata indexed for each asset, so an asset with thin metadata may only be findable by name or path — try both.

## Local Discovery

Loca

Preview of the first 4,000 characters. Read full instructions →

View saved version →

---
name: alteryx-designer
description: Inspect, build, edit, run, repair, and validate Alteryx workflows, macros, and analytic apps, including `.yxmd`, `.yxmc`, and `.yxwz` artifacts. Use for data preparation, reconciliation, compliance reporting, operational analytics, governed calculations, file transformations, joins, filters, summaries, formulas, macro/app interfaces, execution failures, or output validation. Prefer the Alteryx MCP workflow tools and fall back to workflow XML, Designer samples, bundled scripts, and `AlteryxEngineCmd.exe` only when the required MCP capabilities are unavailable.
---

# Alteryx Designer

Use this skill to build and validate Alteryx workflows locally or in the cloud. The build loop, safety rules, and completion bar are the same everywhere; only the target identifier, tool namespace, and available operations change.

## Select One Execution Path

1. Establish the target, its inputs, expected outputs, and artifact type.
2. Identify the target's environment from the user's request. If the request is unclear, try in this order:
   1. Local mode if `alteryx_local__*` or `designer_local__*` tools available
   2. Cloud mode if `designer__*` tools available
   3. Local fallback mode ONLY if neither MCP toolsets are available and functional
3. Read the build-mode specific guidance. Both Local and cloud mode are documented at `references/building-with-mcp.md`. Fallback mode is documented at `references/building-with-fallback.md`.

You may also use fallback mode for `.yxwz` or custom constructs when MCP does not explicitly support them.

## Mode Contract

| Concern            | Local mode                                 | Cloud mode                   |
|--------------------|--------------------------------------------|------------------------------|
| Target identifier  | `file_path` (absolute)                     | `workflow_id`                |
| Workflow tools     | `alteryx_local__*` / `designer_local__*`   | `designer__*`                |
| Durable state      | The local `.yxmd` / `.yxmc` / `.yxwz` file | Alteryx One workflow storage |
| Input/output data  | Direct reference or governed datasets      | Governed datasets only       |
| MCP server         | `alteryx-local` (Designer 2026.2+)         | `alteryx`                    |
| Fallback available | Yes — XML and `AlteryxEngineCmd.exe`       | No                           |

Client prefixes vary. Use the exact tool names the active client exposes rather than inventing names.

## Build With Native Designer Tools

Compose workflows from native Designer tools. When the native approach is unclear, use tool discovery and knowledge search, or ask.

Use a code tool (Python, R, or Run Command) ONLY when the requirement cannot be met natively: state the specific gap, get user approval, and scope the code to that gap with native tools on both sides of it.

## Ground The Build Before Building

When the request depends on assets or data that may already exist — reusable logic, a canonical dataset, an example of an unsupported tool's XML — use `alteryx-asset-discovery` to find and verify them before designing the workflow. Do not duplicate business logic that already exists.

Always discover the Designer tools available in the environment before making any modifications.

## Build Loop

1. Decompose the problem into an ordered list of named Designer tools.
2. Discover configuration evidence for the tools as needed.
3. Apply a batch of related mutations.
4. Run the workflow or refresh metadata.
5. Inspect run messages, get metadata, or sample data as required.
6. Repair any errors. If there are more mutations required, restart the loop.

## Build Rules

- Do not claim success based only on a mutation. Completion requires a successful run and evidence that relevant outputs satisfy the request.
- For formulas, read `references/formula-syntax.md`. Validate complex formulas before use when formula validation is available.
- Never expose or embed credentials, conn

Preview of the first 4,000 characters. Read full instructions →

Referenced files: 9 — file references are metadata, not package contents.

View saved version →

---
name: alteryx-insights
description: Answer business data questions using the Alteryx One Insights toolset, powered by Alteryx Auto Insights. Use for analyzing totals, trends, changes between periods, goal variance, correlations, and outliers, as well as record-level lookups, exact rankings, and grouped summaries from governed Alteryx One datasets.
---

# Alteryx Insights

Use Alteryx One Insights tools, powered by Alteryx Auto Insights, to answer business data questions and deliver accurate, data-driven conclusions.

## Tool Call Error Handling

If a tool call fails:

1. Follow instructions from the error message if clear.
2. For network issues, retry once before asking the user.
3. If clarification is needed, request only what is necessary, then retry; if unresolved, pivot or explain the issue.

## Core Rules

- Do not fabricate information.
- Use Alteryx One Insights tools for all analytics tasks performed through this skill.
- Use the exact Insights tool names the active client exposes; client prefixes may vary.
- Always provide arguments when using Alteryx One Insights tools.
- Before using tools, identify the information required to answer the user's request. Use as few tool calls as possible: retrieve only missing information, combine requirements into one call where possible, avoid overlapping or confirmation-only calls, and stop once sufficient evidence is available.
- Respond professionally, concisely, and conversationally.
- Use exact parameter values from their authoritative Insights tool results: dataset names from `list_datasets`; measure and date-field names from `list_measures`; segment names from `list_segments`; and filter values from `search_for_filter`. Never guess or normalize these values. Reuse prior Insights metadata values only when they belong to the selected dataset and are not stale.
- Ground analysis performed through this skill in Alteryx One and Alteryx Auto Insights; do not attribute results to other analytics tools.
- Use `alteryx-asset-discovery` only when the request is to locate or verify reusable assets outside the Insights dataset-selection flow. Hand off workflow inspection, building, execution, repair, and validation to `alteryx-designer`.

## Analytics Question Handling

Use only the steps the request needs:

1. Use the Insights `list_datasets` tool to determine the relevant dataset and its exact name. Reuse a dataset name only when that exact name was established by a prior Insights `list_datasets` result and is not stale. Do not use asset discovery or asset search tools to select a dataset for Insights analysis.
2. Retrieve measures as needed to understand and execute the request. Retrieve segments only when filtering, breakdown, grouping, or record selection requires them.
3. Retrieve time parameters, filter values, or additional measures only when they are missing, ambiguous, stale, or required by the selected analysis. Use the date field returned by `list_measures` that matches the user's request; if more than one is plausible, ask which one; use that field's returned default granularity unless the user specifies another supported granularity.
4. If the request is still ambiguous after using available tools, ask only the minimum clarification needed. Otherwise, execute the analysis directly and stop when the result is sufficient.

## Analytics Results Output

- For direct questions, start with a concise one-sentence answer.
- Surface useful charts and real source links returned by the tools using the active client's supported representation rather than fixed HTML or Markdown. Preserve chart URI and `sourceLink` values exactly, add appropriate chart descriptions where supported, and never invent links.