pr-desloplisted

Use when the user wants to clean AI slop, verbosity, fragile hard-coded references (line numbers, test counts, file counts), or low-value contributions out of a branch's commits before review. Triggers on phrases like "deslop", "remove AI slop", "clean up commits", "tighten the commits", "fix verbose commit messages", "drop the fluff", "remove brittle counts", "kill the line-number references", "audit the branch for slop", "scrub Claude signatures", or "fixup the slop on this branch". Operates per-commit since trunk: detects issues, proposes targeted patches and fixup commits (and `--fixup=reword:` for commit-message slop), then optionally runs `git rebase -i --autosquash`, running the project's formatter, linter, and type-checker on every conflict pause.
tony/ai-workflow-plugins · ★ 2 · Code & Development · score 69

Install: claude install-skill tony/ai-workflow-plugins

# this skill Audit-first, autosquash-on-explicit-opt-in slop cleaner. Reviews every commit on the current branch since trunk for AI slop, verbose code/comments, fragile hard-coded references, and low-value contributions. Produces a numbered patch series under `.git/deslop/<ts>-<pid>/` plus a checkpointed `apply.sh`. With `--apply-rebase`, applies aggregated fixups (one per target SHA) and runs `git rebase -i --autosquash`, delegating conflict resolution to the project's discovered quality gates. The skill **refuses to operate on already-pushed branches** unless `--force-rewrite-pushed` is passed, and **refuses `--apply-rebase` entirely** if the branch contains merge commits since trunk (`git rebase -i --autosquash` without `--rebase-merges` silently flattens topology). Subjective findings are calibrated against the project's accepted voice on `origin/<trunk>` (not `HEAD`) before being flagged. The skill auto-applies only Tier A signals; Tier B is user-confirmed per finding; Tier C is advisory only. This is a slash command, not a model-invocable skill — history rewrites must be user-explicit, not router-inferred. ## Core thesis Slop is a workflow label, not proof the text is wrong. The skill's job is to reduce review-hostile noise, not to scrub the user's voice. Three disciplines: 1. **Audit-first, autosquash-on-explicit-opt-in.** Default produces a patch series plus a checkpointed `apply.sh`. `--apply-rebase` is the explicit opt-in. 2. **Three severity tiers gove