← ClaudeAtlas

onboard-repolisted

Index an unfamiliar codebase into the knowledge graph, then produce a first orientation map -- entry points, most-depended-upon modules, hotspots, test topology.
n24q02m/claude-plugins · ★ 4 · AI & Automation · score 73
Install: claude install-skill n24q02m/claude-plugins
# Onboard Repo Take a codebase you have never seen and turn it into a queryable graph, then read the graph to produce an orientation map. Use this on first contact with a repository, before answering questions about it or changing anything in it. **Scope:** this skill builds and reads a knowledge graph. It does not modify source files, CI configuration, or project conventions. The only files it creates are the graph database under `.code-review-graph/` (already self-ignored) and, when you choose to add one, a `.code-review-graphignore`. **Command surface:** run the local CLI through the coding harness shell. Examples use the installed `better-code-review-graph` command; from a source checkout, prefix it with `uv run`. No MCP mapping is required. ## Steps 1. **Check what already exists** with `better-code-review-graph graph stats --repo-root "<path>"`. A non-empty graph can go directly to step 5; a missing-graph error means continue with a build. 2. **Decide the indexing scope before building**: - Single repository: pass only `--repo-root "<path>"`. - A repository that vendors or embeds others: add a `.code-review-graphignore` at the repo root (one `fnmatch` pattern per line, `#` for comments) so vendored trees, build output, and fixtures do not inflate the graph. Common additions: `vendor/*`, `third_party/*`, `**/generated/*`, `**/*.min.js`. - Several sibling repositories that call each other: federate them in one graph with `--roots` in step 3, then use `impac