CUJ-20 — rule-based skill suggestions for this agent
Run the CUJ-20 detectors and return a ranked list.
Signals (each with structured evidence for the UI to render “why”):
install— uncovered tool calls (rule-based)remove— menu-bloat skills (rule-based)install_category— category gap relative to registry leaders (rule-based)install_rater— skill the agent struggled without, per Skill Rater output (Phase 2 — evidence-based)
Org-scoped and agent-scoped. Empty list when nothing trips the thresholds — the UI renders a “no suggestions right now” placeholder rather than a fake recommendation.
Phase 2 (2026-05-25): the rule-based detectors are joined by Rater-driven recommendations, surfaced with the same response shape so the UI doesn’t have to know they came from a different signal source. Eventually the rule-based detectors deprecate; for now both coexist and the Rater-driven ones rank higher when present.
Authorizations
Enter your API key (e.g. dai_sk_test_key_001)
Headers
Path Parameters
Query Parameters
1 <= x <= 901 <= x <= 20Cookies
Response
Successful Response