REI Skills wiki
Start with the installation guide, then follow the source code behind skill selection, planning and verification. Field notes show what to capture before applying a skill to a real engineering task.
No matching articles.
Getting started

Getting started
Install and verify AI agent skills
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.

Getting started
Write an agent skill with testable instructions
Design a SKILL.md with clear triggers, prerequisites, inputs, expected artifacts and verification cases. Test the skill against both matching and adjacent tasks.
Platform

Platform
How REI Skills routes tasks and reports benchmarks
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.

Platform
Plan AI agent workflows with acceptance evidence
Use a dependency-aware REI Skills plan, define what each step must produce and keep planned work separate from completed verification.

Platform
Configure a local REI Skills MCP server
Understand REI’s stdio MCP process, check client configuration and tool visibility, and review the permissions that apply to the local integration.

Platform
Review prompts from the Rootcastle Prompt Archive
Trace a downloaded prompt to a pinned source, distinguish integrity from publisher authentication and preserve the inputs needed to reproduce a composed prompt.
Engineering field notes

Engineering field notes
KiCad to Fusion 360 PCB enclosure verification
Prepare a traceable KiCad to Autodesk Fusion handoff. Verify the PCB revision, coordinate origin, connector clearances and CAD evidence before prototype release.

Engineering field notes
Event time, late arrivals and replay in IoT telemetry
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.

Engineering field notes
Reproducible research workflows with AI agents
Create an evidence ledger for an agent-assisted engineering study. Separate observations, simulations and claims before using the optional PaperOrchestra integration.

Engineering field notes
Evaluate AI agent skills with baseline and regression tests
Design a repeatable skill evaluation. Compare the registry quality tier, targeted functional checks and NVIDIA SkillEvaluator evidence against a real baseline.