Setup Readme

This documentation was generated with the assistance of AI. Please report any inaccuracies.

Create or refresh a repository’s root README.md by exploring what actually exists — build files, CI workflows, quality-tool config, documentation, license, and source code — and composing only the sections that real material supports.

Purpose

iru-setup-readme never invents version numbers, badge URLs, dashboard links, or example code that don’t correspond to something actually present in the repository. It gathers project identity (repository/host, description, license, build tool, current and latest-released versions), badge sources (CI status, SonarCloud/SonarQube, package registry), a project status table, documentation links (Antora site, Maven site report, Sonar dashboard, CHANGELOG.md), installation instructions matched to the actual build tool, and a "how it works" section with a runnable example grounded in the current public API — reusing an existing Antora overview/example rather than writing a divergent one if the docs site already covers it. A section whose source material doesn’t exist yet (e.g. a brand-new, mostly empty repository) is omitted rather than filled with placeholders. If README.md already exists, the skill warns the user, preserves any hand-written section it doesn’t know how to regenerate (e.g. "Contributing"), and shows the proposed new content as a diff before writing anything, requiring explicit approval.

Purpose group

Invocation

/iru-setup-readme

Inputs

Argument Required Description Default

(none)

No

This skill takes no arguments — it derives everything it needs by exploring the repository directly (pom.xml/build.gradle/package.json, git remote, .github/workflows/*.yml, Sonar config, Antora docs, CHANGELOG.md, LICENSE, and source code).

Not applicable.

Outputs

  • README.md at the repository root — newly created, or updated after explicit user approval.

  • If README.md didn’t previously exist: it is written directly, no approval step needed.

  • If README.md already existed: the full proposed content (or diff) is shown first, and the file is only overwritten if the user explicitly accepts; any partial-apply request is handled by revising the draft in free text before writing.

  • A closing report naming which sections were included versus omitted and why (e.g. no Installation section because no build/package config was found), any fact that had to be inferred rather than confirmed, and a reminder to double-check the "How It Works"/example section specifically since it depends on this skill’s reading of the current API.

Execution flow

flowchart TD A[Start /iru-setup-readme] --> B{"README.md already\nexists at root?"} B -- yes --> C["Read existing content;\nwarn user changes will be proposed"] B -- no --> D C --> D["Step 2: Gather project identity\n(repo/host, description, license,\nbuild tool, versions)"] D --> E["Step 3: Gather badge sources\n(CI, SonarCloud, package registry)"] E --> F["Step 4: Build project status table"] F --> G["Step 5: Gather documentation links"] G --> H["Step 6: Compose installation\ninstructions for detected build tool"] H --> I["Step 7: Write how-it-works\nsection with a real example\n(via Explore agent)"] I --> J["Step 8: Compose remaining structural\nsections; preserve hand-written extras"] J --> K{"Did README.md\nalready exist?"} K -- no --> L["Write README.md directly"] K -- yes --> M["Show diff, ask user:\naccept or skip"] M -- accept --> L M -- skip --> N["Leave existing README.md untouched"] L --> O["Step 11: Report"] N --> O

Dependencies

Invokes

None — iru-setup-readme is a leaf skill; it does not call any other skill in this catalog.

Invoked by

  • Setup Java Library Repository — Step 8, the last of its six delegated skills, runs iru-setup-readme with no args.

  • Release — Step 7 runs iru-setup-readme to refresh `README.md’s version references as part of cutting a release.

  • Explore (see Agents) — used in Step 7 to locate the main source entry points before reading them directly, rather than reading the whole source tree — the same agent the iru-explore skill itself uses for this kind of broad structural search.

Source

SKILL.md on GitHub — the file this page was generated from.