菜单
AI-generated code cleanup — deletion-first approach, regression-safe. Removes unnecessary abstractions, verbose comments, and over-engineering.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
| name | ai-slop-cleaner |
| description | AI-generated code cleanup — deletion-first approach, regression-safe. Removes unnecessary abstractions, verbose comments, and over-engineering. |
| version | 1.0.0 |
| triggers | [{"pattern":"user asks to clean up AI-generated code, remove slop, simplify over-engineered code, or audit for unnecessary abstractions"}] |
| category | review |
Adapted from oh-my-claudecode.
AI-generated code accumulates "slop" — unnecessary abstractions, verbose comments, defensive code for impossible scenarios, and premature generalizations. This skill systematically identifies and removes it.
# increment counter above counter += 1)Scan the codebase for slop patterns. Report findings:
## Slop Audit Results
- 12 single-use helper functions
- 8 obvious comments
- 3 unnecessary try/except blocks
- 2 abstract classes with 1 implementation
Estimated lines removable: ~200 (15% of codebase)
Rank by impact:
For each deletion:
Rule: Delete first, add only if tests fail.
# Run full test suite after each batch
uv run pytest tests/ --cov=<src> --cov-fail-under=80
# Check nothing was accidentally removed
git diff --stat
NOT slop — keep these:
/review identifies code quality issues/simplify (which focuses on recently changed code)/ship to reduce PR diff noiseurllib.parse.urlparse로 URL 파싱 후 netloc 재조합 시 발생하는 두 침묵 버그 — userinfo 대소문자 소실과 cross-scheme 기본 포트 오삭제.
BSVibe verification runs in a fresh /work clone of main for EVERY turn — files from failed prior turns are gone. Commit within the CURRENT turn or they vanish.
When you depend on a 3rd-party GitHub-hosted data artifact (CSV/JSON/schema/config) via `try: fetch new; except: use HARDCODED_DEFAULT_URL`, the "safety fallback" masks upstream file renames. Symptom — after upstream restructures naming, the auto-discovery quietly returns nothing (regex mismatch = empty result), the code falls through to the frozen default URL, that URL 404s, and the caller catches the exception and degrades to `whitelist=set()` / empty result / None — silently. No hard error, but every downstream measurement built on that data reshapes. bloasis PR59 caught this after 4 weeks of `whitelist=0` had already re-run the mention extractor with distorted sample sizes across per-bucket tables.
A CLI tool (claude/gh/aws/codex…) invoked by a launchd/systemd daemon fails auth with 401 while the identical command works in your interactive shell — because the daemon's security session can't read the OS keychain and silently falls back to a stale on-disk credential. Diagnose from the daemon context, not your shell.
After `pnpm install` in a git worktree, vitest/jest can discover a test file from a SECOND path — pnpm hardlinks the whole project (test/ included) into `~/Library/pnpm/store/v<n>/projects/<hash>/`, and the glob picks up that out-of-root mirror where the `@/` alias / vite root doesn't apply → bogus "Cannot find package '@/...'" resolution errors. Clearing the stale store-project mirror fixes it.
React/JS diff-render libraries (@git-diff-view/react, react-diff-view, diff2html) that take a `hunks`/diff-string input silently render NOTHING when fed a bare `@@ … @@` hunk — they need the full `diff --git` / `