메뉴
Inventory a Hex instance and produce a migration-readiness readout — environment counts, content mix, complexity, and a value/cost-ranked shortlist. Read-only.
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
SOC 직업 분류 기준
Convert a Domo dashboard (pages + cards + DataSets + Beast Modes) into a Sigma data model and matching workbook. Use when the user has a Domo instance and wants to recreate a dashboard in Sigma. Discovery via Domo's public + private APIs, Beast Mode (MySQL-dialect SQL) → Sigma formula translation, a reuse check before building a new data model, data model + workbook creation via the Sigma REST API, layout generation, Domo PDP → Sigma row-level-security detection, and parity verification against the same warehouse — driven by `scripts/*.rb`.
Convert a Hex project (SQL cells, single-value/METRIC cells, EXPLORE charts, app layout) into a Sigma data model and matching workbook. Discovery via a Hex project export file (Hex's REST API does not expose cell content), calc translation, DM + workbook creation via REST, layout, and warehouse parity verification.
Convert a Looker instance (LookML semantic model + dashboards) into a Sigma data model and matching workbook(s). Use when the user has Looker content — LookML projects, explores, or dashboards (user-defined OR LookML-defined) — and wants to recreate it in Sigma. Discovery via the Looker REST API 4.0 / Looker MCP server (or LookML files offline), model conversion via the local vendored LookML converter (convert_lookml_to_sigma MCP tool as a manual fallback), dashboard → workbook conversion from the Looker Dashboard API JSON, build via the Sigma REST API, and 3-way parity verification against the source warehouse — driven by `scripts/*`.
Convert a Power BI report + semantic model into a Sigma data model and matching dashboard. Use when the user has a Power BI report (in Power BI Service / Fabric, or a .pbix/.pbit file) and wants to recreate it in Sigma. Covers connecting to Power BI with no Entra app, extracting the model (TMSL) + report layout (PBIR/Report-Layout), converting via the sigma-data-model MCP, posting the data model + workbook via REST, and parity verification. Can also author dashboards back INTO Power BI via the Fabric write API.
Convert a Qlik Sense / Qlik Cloud app into a Sigma data model and matching workbook. Use when the user has a Qlik Cloud tenant/app and wants to recreate it in Sigma. Discovery via qlik-cli (Engine + REST), Qlik-expression → Sigma-formula translation via the local vendored convert_qlik_to_sigma converter (MCP tool only as a manual fallback), data model + workbook creation via the Sigma REST API, and parity verification against the source warehouse. Requires qlik-cli + a Sigma SIGMA_API_TOKEN.
Convert an Amazon QuickSight analysis or dashboard into a Sigma data model and matching dashboard. Use when the user has a QuickSight analysis/dashboard and wants to recreate it in Sigma. Covers AWS-CLI extraction of the analysis definition + datasets + data sources, calc-field / data-prep translation via the local vendored converter (the convert_quicksight_to_sigma MCP tool is a manual fallback only), posting the data model + workbook via the Sigma REST API, layout, and parity verification against the same warehouse.
| name | hex-assessment |
| description | Inventory a Hex instance and produce a migration-readiness readout — environment counts, content mix, complexity, and a value/cost-ranked shortlist. Read-only. |
SCAFFOLD — deferred.
hex-to-sigma's first pass (a single-project conversion) was the priority; this assessment skill is not yet built out. Assessments never write to the source or post to Sigma. Produce the standard readout (see other*-assessmentskills) and hand off tohex-to-sigma.
TODO: auth to Hex. Note for whoever builds this: Hex's public REST API
(learn.hex.tech/docs/api/api-overview) DOES cover project listing/metadata
and GetQueriedTables (Enterprise-only, useful for estate-wide table-usage
counts) even though it can't return cell content — that's enough for an
inventory pass without needing per-project .hex.yaml exports.
TODO: enumerate projects via ListProjects/GetProject; dedup with
scripts/dup-dashboards.py. Per-project complexity scoring (cell-type mix,
Python-cell prevalence, chart-type mix) needs the .hex.yaml export per
project — no way around that for content-level detail, only counts/metadata
are API-reachable.
TODO: complexity score + value/cost-ranked migration shortlist + readout.
Flag Python-heavy projects as higher-effort up front (see hex-to-sigma
SKILL.md's Gaps section — Python/CODE cells have no automatic translation).
