Platform · Live · new here
Structured-interview kit auditor — RUBRIC-8-B diagnostic (second proof)
Corpus-grounded DIAGNOSTIC (vs the advisor's advisory): scores any existing interview kit — native RubricKit or foreign-shape — against the 8 selection-evidence done-well bars with HONESTY-TYPED verdicts: 4 bars MEASURED pass/fail (structure components, past-behavior share via a deterministic disputable regex classifier (10 past-behavior + 8 situational marker sets; ambiguity -> other, never guessed), anchor coverage, panel scoring — where a kit SILENT on scoring gets not_auditable_from_kit, because silence != single-rater, and the top posture is blocked), 1 bar measured WITHOUT verdict (competency-linkage share — the corpus states no numeric cutoff, so no invented threshold), 3 bars not_auditable_from_kit with the evidence that WOULD make them auditable. Fix-forward guidance quotes the kit's own weakest question indices and is guardrail-safe (never suggests situational-only remedies; legacy-figure redaction on kit excerpts). Guardrail posture cap: a kit whose only remedy violates a guardrail cannot receive the top posture.
- Cluster
- Platform
- Type
- algo
- Status
- Live
- Used by
- people-analytics-toolbox
Maturity evidence
- Functioning
- 31/31 kit-auditor tests + full spoke suite 61/61; audits the spoke's OWN generated RubricKit (strong) and a deliberately weak foreign kit (every bar catches its weakness, fixes quote the right indices); hand-labeled classifier vectors incl. ambiguous->other; contract 0.4.0; check:spokes OK.
- Valuable
- Same consumer path as the advisor — value lands with the first hiring-assessment buyer or the jobframe assessment rail.
- Understood
- Bar-by-bar measurability table + classifier marker sets + threshold-vs-no-threshold reasoning in the module + this entry. Registry gap recorded: done_well_bar is a bare string array — a structured shape needs a build-script output-contract extension (carded, deferred per wave rules).
- Integrated
- Extends the live spoke through its existing mcp files; consumes the committed selection-methods registry (drift = loud named error, never a skipped bar).
How to use it
- REST
- /api/spokes/assessment-library/kit-audit
- MCP
- assessment-library.kit-audit
- Data
- src/spokes/assessment-library/core/kit-auditor.ts
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.