# Radial

> The fast, keyboard-first issue tracker with no AI bolted on. Scriptable from a CLI, an MCP server and a REST API, with an open-source pack of agent skills for Claude Code and Codex.

Every page below is available as markdown at the same URL.

## Getting started

- [Documentation](https://www.radial.build/docs.md): How to drive Radial from the terminal, from your agent, and from your own code.

## Agent skills

- [Agent skills](https://www.radial.build/docs/skills.md): Eleven rd-* skills that teach Claude Code and Codex how to plan, file, build and ship work in Radial.
- [Install and update](https://www.radial.build/docs/skills/install.md): Where the rd-* skills go for Claude Code and Codex, global versus per-repo, and what to do when one does not show up.
- [From an idea to a pull request](https://www.radial.build/docs/skills/workflow.md): The seven workflow skills walked end to end on one real feature, with the commands and the tree they produced.
- [rd-setup](https://www.radial.build/docs/skills/rd-setup.md): Get a repo and a machine ready for Radial. CLI, sign-in, team, config, agent instructions, and the skill pack.
- [rd-plan](https://www.radial.build/docs/skills/rd-plan.md): Turn an idea into one parent and two to four children with acceptance criteria, written to a file so you can argue with it before it becomes a tree.
- [rd-prototype](https://www.radial.build/docs/skills/rd-prototype.md): Build one self-contained clickable HTML file from a plan or an issue, and attach it so reviewers click a Preview URL instead of reading a description.
- [rd-issues](https://www.radial.build/docs/skills/rd-issues.md): File a plan as a real tree (parent, children, blocked-by edges) and read every issue back to prove the fields landed.
- [rd-build](https://www.radial.build/docs/skills/rd-build.md): Work a filed tree child by child (in progress, build, gate, browse checks, notes, in review), resuming from live statuses.
- [rd-verify](https://www.radial.build/docs/skills/rd-verify.md): Resolve this repo's real gate, run each command once to a log, and read the summary line instead of trusting the exit code.
- [rd-pr](https://www.radial.build/docs/skills/rd-pr.md): Open one pull request for the tree, with every sibling issue id rewritten so merging cannot close work nobody reviewed.
- [Keeping a backlog honest](https://www.radial.build/docs/skills/hygiene.md): The four standalone skills (triage, cleanup, changelog, retro), when to run each and what each one writes.
- [rd-triage](https://www.radial.build/docs/skills/rd-triage.md): Rank open parents Now, Next, Later and Icebox from real signal, show the table, and write priorities only after you say yes.
- [rd-cleanup](https://www.radial.build/docs/skills/rd-cleanup.md): Find the work the workflow left behind (open children under done parents, stale in-progress issues) and decide each on evidence.
- [rd-changelog](https://www.radial.build/docs/skills/rd-changelog.md): Turn the issues completed since a date or a tag into Feature, Improvement and Fix entries in customer language.
- [rd-retro](https://www.radial.build/docs/skills/rd-retro.md): Score one finished build against the workflow using only what Radial and git already hold, and turn each finding into a wrapper you can paste.
- [Extending a skill](https://www.radial.build/docs/skills/extending.md): Add your team's rules to an rd-* skill at named extension points, without forking it.
- [The issue body](https://www.radial.build/docs/skills/issue-body.md): The schema rd-plan writes, rd-issues files, rd-build treats as done-or-not, and rd-retro scores against.
- [Conventions](https://www.radial.build/docs/skills/conventions.md): The .radial directory, how the team key resolves, and the four rules every skill carries.

## Optional

- [Full documentation, one document](https://www.radial.build/llms-full.txt)
- [Brand and design system](https://www.radial.build/brand.md)
- [Developer surface: CLI, MCP, REST](https://www.radial.build/developers)