Agent skills for DeepSeek Harness

Manages Arize users, organizations, spaces, projects, roles, role bindings, resource restrictions, and API keys via the ax CLI.

Creates, reads, updates, and deletes Arize AI integrations that store LLM provider credentials used by evaluators and other Arize features.

INVOKE THIS SKILL when auditing an AI agent or LLM app for regulatory compliance.

Generates deep links to the Arize UI for traces, spans, sessions, datasets, labeling queues, evaluators, and annotation configs.

Guide non-technical ART+COM users from an idea to a shareable internal web prototype.

Resolve and download public biological database files through IBM Aspera ascp, especially GEO, NCBI, SRA, and ENA accessions or links.

Configure Aspire AppHost to emit explicit app config via environment variables; keep app code free of Aspire clients and service discovery.

Audit a proposed assessment for construct validity, reliability, and alignment to learning objectives.

Detect and triage OWASP AST03 Over-Privileged Skills — permission manifests broader than a skill's stated function, logic-layer prompt…

Detect and triage OWASP AST05 Untrusted External Instructions — skills that fetch external documentation (URLs, runbooks, schemas) and…

Detect and triage OWASP AST07 Update Drift — skills installed without immutable pinning that fall behind known-good versions, or that…

Deep-dive data profiling for a specific table.

ALWAYS read this skill before generating spoken audio or calling audio_generate — a voiceover, narration, an ad read, a character line, or…

Audit and correct meta tags for SEO and social media.

Audit the choices an implementing agent made, not its diff — a pure decision audit that traces the session's history into a choices…

Use when reviewing or changing a React, Next.js, Tailwind, or shadcn interface and you need evidence-backed findings for accessibility…

Audit work, verify claims with concrete evidence, and explain the result in simple grade-5 language.

Debug Auditaur-enabled Tauri apps. Use when asked to inspect app startup, telemetry readiness, frontend errors, IPC, events, traces…

Automates publishing images, videos, and interactions on Xiaohongshu (RED) using browser automation.

Author or repair an instruction layer to the Jidoka standard.

Run an iterative code-improvement hill-climb against real Datadog LLM-Obs data, locally, with Claude Code as the agent.