← ClaudeAtlas

migrate-docslisted

Discover all existing documentation in the repo — public and private, wherever it lives — classify each file, transform the content to match harness templates, and migrate everything to the correct location (.harness/ for internal docs, repo root for public docs). Use on any existing project to adopt the harness workflow without starting from scratch. Safe: never deletes originals without explicit confirmation.
RubenGlez/harness · ★ 0 · Data & Documents · score 72
Install: claude install-skill RubenGlez/harness
# Migrate Docs ## What this skill does Scans the repo for every documentation file, classifies each one as public or internal, transforms the content to match harness file templates (preserving all information), writes to the correct harness location, and removes the originals only after explicit confirmation. The result is a clean harness-structured project ready to continue with `/product-plan`, `/dev-plan`, or whichever step in the workflow comes next. ## Step 1: Discover Scan the entire repo for documentation. Do not limit yourself to obvious locations — check everywhere. **Root-level files** — check for all of these by name: `README.md`, `CHANGELOG.md`, `HISTORY.md`, `CONTRIBUTING.md`, `CONTRIBUTION.md`, `DESIGN.md`, `SPEC.md`, `PRD.md`, `ROADMAP.md`, `ARCHITECTURE.md`, `SECURITY.md`, `CODE_OF_CONDUCT.md`, and any other `.md` files at the root. **Common doc directories** — scan recursively: `docs/`, `documentation/`, `wiki/`, `spec/`, `specs/`, `notes/`, `planning/`, `design/`, `.github/` **Package manifests** — check for usable product context: `package.json` → description, keywords, homepage `pyproject.toml`, `go.mod`, `Cargo.toml` → name, description **Existing harness structure** — read `.harness/` if it already exists, to avoid overwriting content that has already been migrated. Build a complete inventory: `path`, a one-line description of what the content is about, and approximate size. Include everything — classify later. ## Step 2: Classify For each f