forcedotcom/sf-skills / skills/tableau-next-asset-create
tableau-next-asset-create
VerifiedBuild and edit Tableau Next semantic models (SDMs), vizzes, and dashboards via MCP. TRIGGER when: building a semantic model or dashboard from CSV/Excel files; ingesting a flat file/database into DLO/DMO; profiling a dataset (grain, measures, dimensions; large/wide files via `infer_object_schema`); adding a dimension, measure, AI-ready metric, join, or logical view; running a semantic query, interpreting a breakdown, analyzing account/customer engagement, or pulling counts/totals from existing Tableau Next data (even unnamed/read-only); creating/editing a viz (filter, forecast, sort, shelf, mark encoding, reference line), widget, or dashboard layout. Also: Data Cloud SQL transforms; show a dashboard; share/revoke access; reuse prod or promote Personal Org assets; provision users/licenses; data alerts ('alert me when'); list/classify verified questions or score agent SQL. DO NOT TRIGGER for: rewriting prose descriptions, layout-only dashboard review, debugging MCP, or writing app code.
references/insight-bundle.md
View on GitHub# Insight bundle and metric render — app-only payloads
Cited from `tasks/build-dashboard.md` and `dashboard-authoring.md`. **Not a
first hop. Not a user dispatch.** Do not call these because a chat user said
"generate insights."
The MCP tools are namespaced per server — names here are bare; use whichever
server prefix is connected.
---
## `generate_insight_bundle`
Produces a Tableau Next insight bundle (live value, trend, and status) for a
**dashboard metric widget**.
**Internal / app-only.** `visibility=app` hides it from the model's tool
list. Intended for the MCP app renderer via `app.callServerTool()`, **not**
for the model to invoke on a user chat turn.
The renderer forwards the metric definition it already holds. The server
delegates to the internal insights service via a named-credential callout;
the org JWT is **minted server-side**. Do **not** mint or pass a browser JWT.
Access also requires permission to view Tableau dashboards (plus the Analytics
family's org-level Tableau / semantic-layer check).
### Body (opaque JSON, forwarded verbatim)
Connect does not reshape the body. Field set tracks
`GenerateInsightBundleRequest`:
- `input` — metric bundle input (metric reference + evaluation context:
measurement/metric, grain, filters, time range the widget is showing)
- `options` — which artifacts to compute (value, trend/comparison,
status/threshold)
- `models` — inline semantic model(s) keyed by API name when the caller
supplies the definition instead of a stored SDM
### Returns (forwarded verbatim)
Unknown nested fields are preserved for the renderer:
- `bundle` — live value, trend/comparison series, status/threshold
- `submetric` — resolved sub-metric when the metric is decomposed
- `sdm` — resolved semantic-model context
- `timeRange` / `unifiedTimeRange` — effective range(s) the bundle used
### Live 404 is backend, not a payload bug
Orgs have returned `UNEXPECTED_ERROR` / `RuntimeException: Post to
/v2/internal/bundle status failed. status code: 404` even with a real
metric + model. The same 404 appears via `render_metric` (same backend
endpoint). **Do not retry as if the body were wrong.** Document the
failure; do not invent a "correct" JWT or SDM pin to work around it.
---
## `render_metric`
Render a semantic metric **card**: current value, trend, forecast, and
insights. Pass the metric `apiName` and the semantic model's `apiName`.
Returns a fully-primed insight-bundle envelope (`sdm` + `bundle` +
`submetric` + resolved `timeRange` + filters + layout) for the
metric-standalone MCP renderer. First paint needs no extra client
round-trips.
Same `/v2/internal/bundle` backend family as `generate_insight_bundle` —
a 404 there is the service, not a missing `apiName`.
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| deprecation-and-migrationaddyosmani/agent-skillsManages deprecation and migration. Use when removing old systems, APIs, or features. Use when migrating users from one implementation to another. Use when migrating a database schema in production, such as renaming or dropping a column without downtime (expand/contract). Use when deciding whether to maintain or sunset existing code. | Stars: 119k | Updated | Claude CodeCodex | Verified | Install |
| performance-optimizationaddyosmani/agent-skillsOptimizes application performance across frontend, backend, queries, and databases. Use when performance requirements exist, when you suspect performance regressions, when Core Web Vitals or load times need improvement, when N+1 query patterns need fixing, or when profiling reveals bottlenecks. | Stars: 119k | Updated | Claude CodeCodex | Verified | Install |
| agent-cost-reportthedotmack/claude-memBelievable agent cost report for any period, default the last 7 full days PT, not counting today. Measured tokens from Claude Code transcripts priced at OpenRouter list prices (ESTIMATED), measured provider spend when a sanctioned source exists, note-taker cost separate, Timing-style HTML/PDF plus report.json, line-items.csv, evidence.json. | Stars: 118k | Updated | Claude CodeCodex | Verified | Install |
| agent-cost-reportthedotmack/claude-memBelievable agent cost report for any period, default the last 7 full days PT, not counting today. Measured tokens from Claude Code transcripts priced at OpenRouter list prices (ESTIMATED), measured provider spend when a sanctioned source exists, note-taker cost separate, Timing-style HTML/PDF plus report.json, line-items.csv, evidence.json. | Stars: 118k | Updated | Claude CodeCodex | Verified | Install |