← ClaudeAtlas

ce-initlisted

Bootstrap core-engineering in a repository: profile languages, package managers, build/test commands, CI, API/data/security surfaces, then write starter repo SDLC artifacts under docs/plans without overwriting human policy silently. Triggers: first-run setup, initialize this framework in a repo, generate vc-policy/review-policy/patterns/repo profile before planning.
relusion/vg-sdlc-claude-plugins · ★ 0 · AI & Automation · score 70
Install: claude install-skill relusion/vg-sdlc-claude-plugins
# Init **Invocation input:** Bootstrap request and optional flags: $ARGUMENTS Bootstrap the `core-engineering` framework in the current repository. This skill turns a cold repo into a usable SDLC workspace by producing the starter artifacts that later skills expect: repository profile, version-control policy, review policy, and known-patterns seed. This is a **setup skill**, not a planner. It detects facts, proposes defaults, and writes starter policy only after surfacing what is inferred vs missing. It does not decompose features, implement code, review code, modify production files, install packages, or connect to trackers. ## Runtime Inputs - **Repository root:** current working directory. - **Optional `--write`:** write missing starter artifacts under `docs/plans/`. Without it, run as a dry profile and show the proposed outputs. - **Optional `--force`:** overwrite existing starter artifacts only after an explicit human confirmation in this invocation. Existing human-authored policy is never replaced silently. - **Optional `--readiness`:** add a deterministic adoption view that separates locally detectable workflow prerequisites from repository-host controls that require administrator verification. It executes no build, test, or CI job and is not a compliance attestation. - **Optional context from the human:** team branching policy, protected branch, review bar, known flaky tests, forbidden paths, deployment constraints, and security-sensitive surface