Optimizes, improves, and debugs LLM prompts using production trace data, evaluations, and annotations. Extracts prompts from spans, gathers performance signal, and runs a data-driven optimization loop using the ax CLI. Use when the user mentions optimize prompt, improve prompt, make AI respond better, improve output quality, prompt engineering, prompt tuning, or system prompt improvement.
npx skills add https://github.com/arize-ai/arize-skills/tree/main/skills/arize-prompt-optimizationOptimizes, improves, and debugs LLM prompts using production trace data, evaluations, and annotations. Extracts prompts from spans, gathers performance signal, and runs a data-driven optimization loop using the ax CLI. Use when the user mentions optimize prompt, improve prompt, make AI respond better, improve output quality, prompt engineering, prompt tuning, or system prompt improvement.
This repo contains 2 individual skills — each has its own dedicated page.
Adds Arize AX tracing to an LLM application for the first time. Follows a two-phase agent-assisted flow to analyze the codebase then implement instrumentation after user confirmation. Use when the user wants to instrument their app, add tracing from scratch, set up LLM observability, integrate OpenTelemetry or openinference, or get started with Arize tracing.
Downloads, exports, and inspects existing Arize traces and spans to understand what an LLM app is doing or debug runtime issues. Covers exporting traces by ID, spans by ID, sessions by ID, and root-cause investigation using the ax CLI. Use when the user wants to look at existing trace data, see what their LLM app is doing, export traces, download spans, investigate errors, or analyze behavior regressions.
Unofficial local-first Withings MCP server for AI health, sleep and activity agents.
Facilitate a structured sprint retrospective — what went well, what didn't, and prioritized action items with owners and deadlines. Use when running a retrospective, reflecting on a sprint, creating action items from team feedback, or learning how to run effective retros.
An Agent Skill for creating Spring Boot applications
Self-optimizing multi-subagent web/app audit system (Claude skill): 7-phase pipeline, memory-driven routing, Knowledge Gate, 2026 benchmarking, ICE roadmap.
Installable AI-agent skill bundle for OWASP-driven code scanning, fixing, and secure-build supervision. Multi-host (Claude Code, Cursor, Codex, etc). Distilled from the SCCAP platform. Distributed via skills.sh.
Get your agents talking. A hosted messaging store + router with fast retrieval. Useful for orchestrating agents.