From ThoughtSpot → Sigma
Take inventory of a ThoughtSpot instance and produce a migration-readiness readout — models/worksheets, Liveboards, Answers, connections, per-Liveboard chart-type mix and complexity, chart-type coverage, and a value/cost-ranked migration shortlist. Use to scope a ThoughtSpot→Sigma migration or audit BI sprawl. Read-only.
How this skill is triggered — by the user, by Claude, or both
Slash command
/thoughtspot-to-sigma:thoughtspot-assessmentThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Read-only pre-scoping for a ThoughtSpot → Sigma migration. Complements
Read-only pre-scoping for a ThoughtSpot → Sigma migration. Complements
thoughtspot-to-sigma (which does the actual conversion).
Same as thoughtspot-to-sigma: TS_HOST + TS_TOKEN (SSO session token or
Trusted-Auth service token). No Sigma credentials needed — this only reads
ThoughtSpot.
scripts/scan.py — inventories the instance via metadata/search
(LOGICAL_TABLE / LIVEBOARD / ANSWER / CONNECTION), exports each Liveboard's TML,
and per Liveboard scores migration complexity from its visualizations:
viz count + distinct chart kinds + models touched. Output:
Writes the full report to ~/thoughtspot-migration/assessment.json.
The thoughtspot-to-sigma pipeline maps KPI / COLUMN / BAR / LINE / PIE / TABLE
/ ADVANCED_COLUMN / stacked / area / LINE_COLUMN to Sigma equivalents. Flagged
for review (no direct 1:1 in the current pipeline): SCATTER, BUBBLE, GEO_AREA,
PIVOT_TABLE, WATERFALL, FUNNEL, TREEMAP, LINE_STACKED_COLUMN.
json.loads(..., strict=False).= (oper: =) which trips PyYAML's value tag — the
scan registers a constructor that reads it as a string.npx claudepluginhub twells89/sigma-migration-skills --plugin thoughtspot-to-sigmaSearches MemPalace before answering questions about past work, people, projects, or prior decisions. Returns verbatim stored content instead of guessing from model memory.
Guides Payload CMS config (payload.config.ts), collections, fields, hooks, access control, APIs. Debugs validation errors, security, relationships, queries, transactions, hook behavior.
Implements vector databases with Pinecone, Weaviate, Qdrant, Milvus, pgvector for semantic search, RAG, recommendations, and similarity systems. Optimizes embeddings, indexing, and hybrid search.