Reusable AI capabilities
Skills are reusable instructions for a focused capability. Each Skill is based on a published Amo.ng Prompt or Workflow and explains what information you need, how to apply the method, and what completion looks like. Skills do not run automatically.
Analyze a slow PostgreSQL query using execution plans, runtime statistics, table shape, indexes, locks, and controlled experiment design to produce a safe optimization recommendation with verification criteria.
Apply a recurring method to detect corrected, retracted, obsolete, or superseded citations and govern claim updates without confusing age with invalidity.
Apply a repeatable incident method to locate the first data-lineage divergence, bound affected outputs and decisions, and gate repair and reprocessing.
Maintain risk-based freshness objectives, change triggers, breach responses, and revalidation evidence for enterprise knowledge used by retrieval systems.
Set and maintain risk-based AI regression gates using measurement uncertainty, baseline variance, critical slices, practical significance, and explicit release trade-offs.
Apply a repeatable control test to determine whether pause, override, containment, and recovery mechanisms limit harm quickly and completely enough under realistic failure conditions.
Compare approved and effective agent tool access across identities, environments, and time to detect drift, bound affected actions, and govern recertification.
Reconcile checkpoints, durable state, side effects, approvals, and idempotency after interruption to select and gate a safe resume, replay, compensate, or abort path.
Apply a reusable launch-control method to SEO-sensitive migrations, reconciling URLs and directives, gating release, and monitoring discoverability and recovery evidence.
Apply a recurring source-to-ledger reconciliation method across currencies, settlements, recognition, fees, taxes, and journals, with evidence-linked exception ownership.
Apply a repeatable evidence and decision method to isolate a failed Kubernetes rollout, choose the smallest safe recovery path, and verify restored service before closing the incident.
Assess whether a proposed vendor procurement package contains sufficient requirements, evidence, controls, ownership, and commercial information to proceed into formal due diligence.
