菜单
Detect unused functions, classes, and variables. Uses Vulture (Python) and ts-prune (JS/TS) to find candidates, then relies on Agent verification to avoid false positives.
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 | dead-code-reaper |
| description | Detect unused functions, classes, and variables. Uses Vulture (Python) and ts-prune (JS/TS) to find candidates, then relies on Agent verification to avoid false positives. |
Find code that does nothing. Less code = Less complexity.
vulture to find unused code.ts-prune to find unused exports.Finds unused code candidates in Python files.
# Install if missing
pip install vulture > /dev/null 2>&1
# Run scan (exclude tests and migrations by default)
vulture . --min-confidence 80 --exclude "tests/,migrations/,venv/,.venv/"
Output Interpretation:
unused function 'foo'unused class 'Bar'Finds unused exports in TS/JS projects.
# Run with bunx (instant, no install needed)
bunx ts-prune | head -n 50
1. Detect Suspects Run the scan tool for the language.
2. Verify (The "Double Check") Static analysis is often wrong (false positives). Before declaring code "dead," check for dynamic usage:
getattr(x, "my_func")).main.py or cli.py?3. Report Present the list of verified dead code.
## Dead Code Candidates
| File | Symbol | Confidence | Recommendation |
|------|--------|------------|----------------|
| `utils.py` | `old_helper` | High | 🗑️ Delete |
| `api.py` | `unused_handler` | Medium | ⚠️ Check URL conf |
❌ Deleting without checking: Vulture is heuristic. It will be wrong. ❌ Ignoring API surfaces: Public libraries have "unused" functions that are meant for users. ❌ Removing "TODO" stubs: Empty functions might be placeholders.
vulturets-prune (via npx)Behavioral testing methodology — test what users experience, not how code is structured. Use when writing tests, reviewing test quality, planning test strategy for new features, or when existing tests are brittle/verbose/coupled to implementation details. Triggers: writing tests, TDD, test review, "tests keep breaking", "too many mocks", "tests are verbose", test coverage planning, behavior-driven development.
Summon 8–12 fictional but statistically plausible people from Kyrgyzstan to judge your web app. They take screenshots, click around, get confused, get delighted, and write honest reviews in Russian. Output: a single .md report with embedded screenshots. Use when you need brutal UX feedback from people who ride marshrutkas.
Artemy Lebedev-style бизнес-линч design review. Opens the site in a real browser, screenshots everything, then tears it apart (or praises it) in his signature voice — brutal, specific, visual. Use when you want a no-bullshit design review, 'линч', 'lebedev review', 'artemy review', or 'roast my site'.
Autonomous experiment loop — modify code, measure, keep/discard, repeat forever. Based on Karpathy's autoresearch pattern. Use when there's working code + a measurable metric to optimize. Agent works while you sleep.
Iterative deep research agent — recursive breadth×depth tree search that accumulates learnings, generates follow-ups, and produces cited reports. Uses exa + serper + subagents. Use when user says 'deep research', 'investigate', 'deep dive', 'thorough analysis', or needs multi-source synthesis with depth.
Detect and fix design system leaks — default shadcn/bootstrap/MUI styling breaking through your brand. Use when: UI feels 'template-y', 'looks like shadcn', 'too generic', buttons are inconsistent colors, cards look default, or after shipping many features fast. Also: 'audit my design', 'check consistency', 'brand leak', 'fix the defaults'.