Skills

Guides containment, evidence collection, root-cause analysis, customer communication, and remediation when an AI agent takes an unsafe, incorrect, or unauthorized action.

Defines versioned data contracts between producers and consumers, with ownership, schemas, quality expectations, compatibility rules, and operational change management.

Defines repeatable quality evaluation for LLM outputs using representative datasets, scoring rubrics, model-graded checks, human review sampling, and regression thresholds.

Produces clear, reviewable architecture decision records that capture context, alternatives, trade-offs, consequences, rollout steps, and reversal criteria.

Reviews cloud and AI infrastructure spend to identify measurable savings while preserving reliability, performance, security, ownership, and product requirements.

为 AI 智能体构建可重复的评估，在真实端到端场景中衡量任务成功率、工具使用正确性、事实依据、延迟、成本和安全恢复能力。

Designs durable memory for AI agents, including what to retain, how to retrieve it, privacy boundaries, expiration policies, and evaluation criteria for useful recall.

Optimizes prompts and agent workflows for finite context windows by prioritizing evidence, compressing history, managing retrieval budgets, and measuring token-cost trade-offs.

Tests AI agent tool use with realistic fixtures, malformed inputs, permission boundaries, deterministic assertions, and recovery checks for failed or partially completed actions.

Produces blameless, actionable incident postmortems with a precise timeline, contributing factors, impact, decisions, corrective actions, owners, and measurable follow-through.

Designs reliable JSON and typed outputs for LLM features, including schemas, validation, recovery paths, versioning, examples, and contracts for downstream consumers.

Reviews Model Context Protocol servers for excessive permissions, unsafe tool design, prompt injection exposure, secret handling, authorization gaps, and auditability.

Designs trustworthy product analytics events, properties, identity rules, validation, privacy boundaries, dashboards, and governance for product and growth decisions.

Designs traces, metrics, structured events, privacy controls, dashboards, and alerts for LLM applications so teams can diagnose quality, cost, latency, and tool-use behavior.

Simulates realistic adversarial behavior against AI features to uncover prompt injection, data exfiltration, unsafe tool use, jailbreak, and authorization failures before launch.

Builds regression suites for prompts and agent instructions so teams can detect quality, safety, format, and tool-selection regressions before deploying changes.

Converts a design specification or screenshot into accessible, responsive production UI while preserving component boundaries, design tokens, semantic structure, and states.

Synthesizes interviews, support tickets, reviews, and survey responses into evidence-based themes, opportunities, representative quotes, confidence levels, and product actions.

Designs reliable AI-assisted business and engineering automations with triggers, approvals, idempotency, observability, exception handling, and human handoff points.

Plans safe database schema and data migrations with backwards compatibility, staged rollout, validation, rollback, performance safeguards, and application coordination.

Designs durable API evolution plans with compatibility guarantees, deprecation policy, version negotiation, consumer communication, migration tooling, and operational telemetry.