Platform · Live · new here
Selection-method validity advisor — RUBRIC-8 prove-one (HO-440)
Stateless REST+MCP advisor returning ranked selection-method PORTFOLIOS (never one option) grounded VERBATIM in the cross-book selection-assessment corpus (canonicai cluster model + validity overlay, 3 fingerprinted inputs): the Sackett-corrected validity ordering, the validity-diversity tradeoff, and the five HO-440 evidence guardrails enforced as refusals — no-legacy-validity-figures (build-time leak check fails if a .51-era coefficient enters the registry OR the output), structured-is-the-default (unstructured only behind an explicit override + warning), past-behavior-anchored-first, panel-over-single-rater, BARS-as-defensibility-not-superiority. Basis-honesty per method: numeric ONLY where the overlay adjudicates a current figure (structured-interview design/reliability); ordinal where the corpus supports ranking; qualitative verbatims otherwise; nothing fabricated. 12-method registry generated by scripts/build-selection-methods.mjs; freshness test FAILS (never green-skips) when the canonicai artifacts are absent or drift.
- Cluster
- Platform
- Type
- algo
- Status
- Live
- Used by
- people-analytics-toolbox
Maturity evidence
- Functioning
- 17 node:test tests green (guardrail suite a-e, basis-honesty, ranking vs the adjudicated ordering, diversity-priority presentation flip, refusals) + 13 existing spoke tests green; check:spokes assessment-library OK; contract 0.3.0.
- Valuable
- First consumer pending — the tool exists for the Triple-A W3 Attraction workstream; value lands when a hiring-assessment buyer or the jobframe assessment rail calls it.
- Understood
- Every recommendation carries citations + basis kind; guardrails documented in the data module + this entry; the excluded legacy figures are listed with WHY.
- Integrated
- Extends the live assessment-library spoke (both doors registered through its existing mcp files); registry data regenerable from the canonicai artifacts with per-file sha256 fingerprints.
How to use it
- REST
- /api/spokes/assessment-library/selection-advisor
- MCP
- assessment-library.selection-advisor
- CLI
- scripts/build-selection-methods.mjs
- Data
- src/spokes/assessment-library/data/selection-methods.json
Other Platform capabilities
- Comp audit self-serve — CSV intake, free validate, commerce-gated watermarked run (HO-155)
- Gift pass — gifted ownership on the entitlement store (magic-link claim)
- JobFrame canonical Job Family × Focus × Level taxonomy + classifier
- SMB pay-system wizard — chocolate/vanilla over the pay-system catalog
- Support channel — portfolio-wide /support form → ticket store → operator email
- Ask-your-data — generalizable NL→rank→tier→cite spoke (HO-378)
- Diagnostic acquisition — next-best-ask over a live hypothesis set
- Executive-Priorities Elicitation Instruments (static catalog)
Capability detail sourced from the People Analytics Toolbox capability feed (source of truth), snapshot retrieved 2026-07-23.