← ClaudeAtlas

code-upliftlisted

Review + refactor code that's already written — same gsd machinery as feature-spec/feature-implement but findings-driven instead of spec-driven. Adversarial cross-model review, refactor phases, test uplift to the coverage floor, smoke/e2e via canary-gate, review-gate finish tail.
austinmao/feature-fix-swarm · ★ 3 · AI & Automation · score 72
Install: claude install-skill austinmao/feature-fix-swarm
# code-uplift — review, refactor, and test-uplift existing code ## Host dispatch contract - Codex: `$skill`, Codex collaboration roles, and GPT-5.6 tiers. - Claude: `/skill`, Agent/Skill tools, and Claude aliases. - A bare `/skill` in this shared source denotes the Claude form; Codex dispatches the same named skill as `$skill`. ## Init gate Before any other step, run the advisory init guard and relay its output verbatim: ```bash bash "$(git rev-parse --show-toplevel)/scripts/gsd/init-guard.sh" || true ``` If it printed `INIT-GUARD:` warnings, offer `/ffs-init` before proceeding in interactive sessions (declining proceeds anyway); headless, spawned, and autonomous runs relay the warnings once and continue. Advisory only — never a block, never an exit-code change. At entry, make one opportunistic, fail-soft `bash scripts/gsd/reconcile.sh` pass; never block on its result. ## When to invoke - "review and refactor <path/module>", "uplift tests for X", "harden this code", "bring <dir> to coverage floor", "clean up module Y and its tests" - After inheriting/adopting code that never went through `/feature-spec` → `/feature-implement` - NOT for new features (use `/feature-spec`) and NOT for a single named bug (use `/fix`) ## Relationship to other skills ``` /feature-spec — spec-driven: requirements come from an interview /code-uplift — findings-driven: requirements come from reviewing existing code /feature-implement — both hand off to the same gsd exec