Overview

Teach Claude to query and interpret HG's momentum, trending, and time-series tables so it can detect companies where product usage is growing or declining — the signal behind 'companies using Workday but less and less.'

Use cases

Target accounts in a platform transition window
When intensity_momentum goes negative, the company is pulling back from a product. That's a displacement window — and the workflow catches it automatically by querying install_intensity_momentum_global and ranking by the steepest decline.
Find companies doubling down on a technology bet
Positive momentum + rising trending = a company investing more in a platform. Perfect for cross-sell or expansion plays — and the skill teaches Claude exactly how to query and interpret the signal.

View full skill

HG Momentum Signals

When to use

Detecting companies where product usage is growing or declining
Queries that need "companies using X but less and less" or "companies ramping up on Y"
Time-series analysis for trend validation

Three tables, three granularities

Table	Field	Granularity	Use
`install_intensity_momentum_global`	`intensity_momentum`	Single score per product×company	Quick filter: declining vs. growing
`install_intensity_trending_global`	`intensity_trending`	Trending direction	Confirm direction when momentum is ambiguous
`install_time_series_global`	`weighted_score` × `date_verified`	Monthly snapshots	Granular trend analysis and charting

Momentum interpretation bands

`intensity_momentum` value	Interpretation
< −20	Significant decline — active pullback, displacement window
−20 to 0	Slight decline — worth monitoring
0 to 20	Stable — no clear directional signal
> 20	Growing — company investing more in this product

Query pattern: declining usage

SELECT cl.name, cl.country_name, cl.revenue_min,
       m.intensity_momentum, ig.intensity
FROM install_intensity_momentum_global m
JOIN install_global ig ON m.url_id = ig.url_id AND m.product_id = ig.product_id
JOIN company_locations cl ON m.url_id = cl.url_id
WHERE ig.vendor_name = 'Workday, Inc.'
  AND cl.is_ghq = true
  AND m.intensity_momentum < -20
ORDER BY m.intensity_momentum ASC
LIMIT 100

Query pattern: growing usage

SELECT cl.name, cl.country_name, cl.revenue_min,
       m.intensity_momentum, ig.intensity
FROM install_intensity_momentum_global m
JOIN install_global ig ON m.url_id = ig.url_id AND m.product_id = ig.product_id
JOIN company_locations cl ON m.url_id = cl.url_id
WHERE ig.category_leaf_name = 'Cloud Security'
  AND cl.is_ghq = true
  AND m.intensity_momentum > 20
ORDER BY m.intensity_momentum DESC
LIMIT 100

When to use each table

Need	Table	Why
Filter a list by "declining" or "growing"	`install_intensity_momentum_global`	Single score, fast filter
Confirm an ambiguous momentum score	`install_intensity_trending_global`	Trending direction adds a second signal
Deep dive on one account's product trajectory	`install_time_series_global` via `company_install_time_series` tool	Monthly datapoints for trend analysis

Credit implications

Momentum and trending table queries via hg_data_query: dynamic credits (varies by query complexity)
company_install_time_series (per-account): 3 credits per product returned (default up to 10 products; can exceed 30 credits at max)
Time-series table has 5.5B rows — always filter by product_id first to avoid expensive full-table scans

Reference

hg-insights-api.md#company_install_time_series — per-account time-series tool
hg-data-query-discipline — safe ClickHouse query patterns
hg-recent-signals — recency (fresh vs. stale), distinct from momentum (growing vs. declining)

Skill: HG Momentum Signals