Impl Agent UX — Data & AI agent for Claude Code
Reviews implementation plans from the perspective of AI agent system design.
How to install Impl Agent UX
Installs to ~/.claude/agents/pinecone-io-rings-impl-agent-ux.md
mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/pinecone-io/rings/HEAD/.claude/agents/impl-agent-ux.md -o ~/.claude/agents/pinecone-io-rings-impl-agent-ux.md Restart Claude Code, or start a new session, for it to be picked up.
What Impl Agent UX does
name: impl-agent-ux model: opus description: Reviews implementation plans from the perspective of AI agent system design. Use when evaluating whether the implementation correctly handles long-running agentic invocations, context window management, session continuity, partial output handling, and the mechanics of building reliable multi-step agent loops.
You build AI agent systems and have deep experience with what makes multi-step LLM workflows reliable in practice vs. fragile in theory
Alternatives in Data & AI
- Multi Agent Review — A sophisticated AI-powered code review system designed to provide comprehensive, multi-perspective a... - wsho 31.9k ★
- Vision — GSD-2 is the orchestration layer between you and AI coding agents 5.7k ★
- Council Sutskever — Council member 4.2k ★
Full documentation available on GitHub
View Source RepositoryRelated Agents
Impl Serialization
Reviews implementation plans from a serialization and data format perspective. Use when evaluating serde usage
Review Agent UX
Reviews plans and specs from the perspective of someone building AI agent systems and agentic workflows. Use w
Context Isolator
Runs data-heavy read-and-summarize operations in an isolated context window to prevent bloating the main conve
Askit Quality Grader
Judges whether a skill triggers and behaves correctly by running it against its eval-set and grading the outpu
Pace Analyst
Analyst perspective agent for devpace. Handles metrics collection, retrospectives, and trend analysis. Data an
Agentic Search Optimizer
Expert in WebMCP readiness and agentic task completion — audits whether AI agents can actually accomplish task
Related Skills
Chair
Show or change the chair setup — who drafts plans / summarises reviews for Claude, and whether Claude (Fable)
Validate Replica
Validate a ReplicaClient implementation in Litestream. This command helps ensure a replica client correctly im
AgentInjectionBench
A benchmark for evaluating prompt injection attacks in agentic tool-use pipelines