rpi-walkthrough Skill
Guided, conversational walkthrough that explains code, UI, UX, features, or .copilot-tracking artifacts one line or block at a time with navigable evidence links, deep subagent review, and captured change requests for RPI handoff. Use when the user wants to understand how something works or why it was changed. Published by microsoft in hve-core.
What is rpi-walkthrough Skill?
Guided, conversational walkthrough that explains code, UI, UX, features, or .copilot-tracking artifacts one line or block at a time with navigable evidence links, deep subagent review, and captured change requests for RPI handoff. Use when the user wants to understand how something works or why it was changed. Published by microsoft in hve-core. This profile combines repository metadata with install, compatibility, and usage signals so developers can quickly decide whether it fits their agent workflow before opening the source repository.
Automated repository signals based on public metadata such as recency, license, installation evidence, and adoption. These are not a security audit or endorsement.
Key capabilities
- Includes SKILL.md support
- Reusable instructions support
- Design and media
- Research
- Design and media use cases
- Research use cases
Technical details
- Install or run with Copy skill directory
When to use rpi-walkthrough Skill
- Use it for design and media.
- Use it for research.
Built with
Editorial notes
Source
- Creator: microsoft
- Repository: microsoft/hve-core
- Skill file: .github/skills/rpi/rpi-walkthrough/SKILL.md
What it does
Guided, conversational walkthrough that explains code, UI, UX, features, or .copilot-tracking artifacts one line or block at a time with navigable evidence links, deep subagent review, and captured change requests for RPI handoff. Use when the user wants to understand how something works or why it was changed.
Skill instructions
RPI Walkthrough Use references/walkthrough.md for the full walkthrough protocol, segment loop, reference-table format, change-capture format, and subagent dispatch. Follow the shared conventions in copilot-tracking.instructions.md. Goal Walk the user through a target one segment at a time, explaining what each line or block does and why, with navigable evidence links, then capture any requested changes for an RPI handoff without editing the codebase. A target is source code, UI or UX wiring, a library or feature, a prompt-engineering artifact such as a prompt, instructions, agent, or skill, or a .copilot-tracking artifact such as a research, plan, changes, review, or log document. Derive {{taskslug}} in lower-kebab-case from the primary target's main subject, such as the primary file's base name without its extension or the feature or area name, use the current date in YYYY-MM-DD, and record session notes in .copilot-tracking/walkthroughs/{{YYYY-MM-DD}}/{{taskslug}}-walkthrough.md with
Explore related resources
Frequently asked questions
What is rpi-walkthrough?
rpi-walkthrough is a open-source AI agent skill with Copy skill directory. Guided, conversational walkthrough that explains code, UI, UX, features, or .copilot-tracking artifacts one line or block at a time with navigable evidence links, deep subagent review, and captured.
Who is rpi-walkthrough best for?
rpi-walkthrough is best for reusing agent instructions, scripts, and references, design and media workflows, research workflows.
How do I install rpi-walkthrough?
Install or run rpi-walkthrough using Copy skill directory. Check rpi-walkthrough for the latest setup command.
Is rpi-walkthrough actively maintained?
rpi-walkthrough may need a closer maintenance check before production use.
Auto-fetched from GitHub.
