<?xml version='1.0' encoding='utf-8'?>
<feed xmlns="http://www.w3.org/2005/Atom"><title>REI Skills Wiki</title><id>https://skills.rootcastle.com/wiki/</id><updated>2026-11-18T00:00:00Z</updated><link href="https://skills.rootcastle.com/wiki/" /><link href="https://skills.rootcastle.com/wiki/feed.xml" rel="self" /><author><name>Rootcastle Engineering &amp; Innovation</name></author><entry><title>Install and verify AI agent skills</title><id>https://skills.rootcastle.com/wiki/agent-skills-getting-started/</id><updated>2026-11-18T00:00:00Z</updated><link href="https://skills.rootcastle.com/wiki/agent-skills-getting-started/" /><summary>Install a single REI skill in Codex CLI, Claude Code or Cursor. Check the target directory, run a scoped trial and remove the skill with the same installation flags.</summary></entry><entry><title>Write an agent skill with testable instructions</title><id>https://skills.rootcastle.com/wiki/write-an-agent-skill/</id><updated>2026-11-18T00:00:00Z</updated><link href="https://skills.rootcastle.com/wiki/write-an-agent-skill/" /><summary>Design a SKILL.md with clear triggers, prerequisites, inputs, expected artifacts and verification cases. Test the skill against both matching and adjacent tasks.</summary></entry><entry><title>How REI Skills routes tasks and reports benchmarks</title><id>https://skills.rootcastle.com/wiki/skill-router-and-benchmarks/</id><updated>2026-11-18T00:00:00Z</updated><link href="https://skills.rootcastle.com/wiki/skill-router-and-benchmarks/" /><summary>Understand REI’s hybrid task router, interpret the held-out Recall@3 and Precision@3 results, and build an evaluation set for your own tasks.</summary></entry><entry><title>Plan AI agent workflows with acceptance evidence</title><id>https://skills.rootcastle.com/wiki/workflow-plans-and-evidence/</id><updated>2026-11-18T00:00:00Z</updated><link href="https://skills.rootcastle.com/wiki/workflow-plans-and-evidence/" /><summary>Use a dependency-aware REI Skills plan, define what each step must produce and keep planned work separate from completed verification.</summary></entry><entry><title>Configure a local REI Skills MCP server</title><id>https://skills.rootcastle.com/wiki/mcp-local-integration/</id><updated>2026-11-18T00:00:00Z</updated><link href="https://skills.rootcastle.com/wiki/mcp-local-integration/" /><summary>Understand REI’s stdio MCP process, check client configuration and tool visibility, and review the permissions that apply to the local integration.</summary></entry><entry><title>Review prompts from the Rootcastle Prompt Archive</title><id>https://skills.rootcastle.com/wiki/prompt-archive-provenance/</id><updated>2026-11-18T00:00:00Z</updated><link href="https://skills.rootcastle.com/wiki/prompt-archive-provenance/" /><summary>Trace a downloaded prompt to a pinned source, distinguish integrity from publisher authentication and preserve the inputs needed to reproduce a composed prompt.</summary></entry><entry><title>KiCad to Fusion 360 PCB enclosure verification</title><id>https://skills.rootcastle.com/wiki/kicad-fusion-pcb-handoff/</id><updated>2026-11-18T00:00:00Z</updated><link href="https://skills.rootcastle.com/wiki/kicad-fusion-pcb-handoff/" /><summary>Prepare a traceable KiCad to Autodesk Fusion handoff. Verify the PCB revision, coordinate origin, connector clearances and CAD evidence before prototype release.</summary></entry><entry><title>Event time, late arrivals and replay in IoT telemetry</title><id>https://skills.rootcastle.com/wiki/telemetry-event-time/</id><updated>2026-11-18T00:00:00Z</updated><link href="https://skills.rootcastle.com/wiki/telemetry-event-time/" /><summary>Design a test matrix for delayed and duplicate IoT telemetry. Define event time and receive time, replay a small fixture and preserve evidence for ingestion changes.</summary></entry><entry><title>Reproducible research workflows with AI agents</title><id>https://skills.rootcastle.com/wiki/reproducible-research-agents/</id><updated>2026-11-18T00:00:00Z</updated><link href="https://skills.rootcastle.com/wiki/reproducible-research-agents/" /><summary>Create an evidence ledger for an agent-assisted engineering study. Separate observations, simulations and claims before using the optional PaperOrchestra integration.</summary></entry><entry><title>Evaluate AI agent skills with baseline and regression tests</title><id>https://skills.rootcastle.com/wiki/evaluate-agent-skills/</id><updated>2026-11-18T00:00:00Z</updated><link href="https://skills.rootcastle.com/wiki/evaluate-agent-skills/" /><summary>Design a repeatable skill evaluation. Compare the registry quality tier, targeted functional checks and NVIDIA SkillEvaluator evidence against a real baseline.</summary></entry></feed>