菜单
Use when you need to detect or remove AI slop from text — filler openers, hedge stacks, redundant qualifiers, and emoji clusters. Scans stdin or a file and optionally rewrites clean output.
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
Use when you have a large-scale, multi-phase project requiring orchestrated execution.
Use when you need persistent looping until a task is fully complete.
Deterministic adversarial code review for high-stakes scope — independent per-dimension review, a non-skippable per-finding refutation, completeness + interaction critics, and a deterministic 3-lens rubric judge panel. Opt-in main-loop Workflow tier.
Use when the user wants to review accumulated skill feedback, verdict trends, or improvement candidates collected during Stage 4 retrospectives. Trigger on "show skill feedback", "스킬 피드백 보여줘", or finding which skills need /writing-skills work.
Deterministic competitive code tournament — N builders independently solve one task and return patches, an Action-Kamen judge scores them head-to-head, the winner is picked by score and applied. Opt-in main-loop Workflow tier.
Deterministic adversarial debate for high-stakes or irreversible decisions — mandatory refutation plus a scored judge panel. Opt-in main-loop Workflow tier.
| name | team-shinchan:simplify |
| description | Use when you need to detect or remove AI slop from text — filler openers, hedge stacks, redundant qualifiers, and emoji clusters. Scans stdin or a file and optionally rewrites clean output. |
| user-invocable | true |
Removes AI-generated filler language from text files or stdin.
# Scan mode (default) — print matched slop phrases with line numbers
echo "Certainly, here is your answer." | node ${CLAUDE_PLUGIN_ROOT}/src/slop-cleaner.js
# Fix mode — rewrite cleaned text to stdout
echo "Certainly, here is your answer." | node ${CLAUDE_PLUGIN_ROOT}/src/slop-cleaner.js --fix
# File input — scan a file
node ${CLAUDE_PLUGIN_ROOT}/src/slop-cleaner.js --file path/to/doc.md
# File input + fix — rewrite cleaned text back to the file
node ${CLAUDE_PLUGIN_ROOT}/src/slop-cleaner.js --fix --file path/to/doc.md
| Category | Examples |
|---|---|
| Filler openers | "Certainly,", "Absolutely,", "Of course,", "Sure,", "Great,", "I'll help you" |
| Hedge stacks | "It's worth noting that ", "It is important to mention ", "Please note that " |
| Redundant qualifiers | "very unique" → "unique", "completely eliminate" → "eliminate", "totally unnecessary" → "unnecessary" |
| Emoji clusters | 3 or more consecutive emoji in a row |
When this skill is invoked, run the slop-cleaner script directly using the Bash tool:
# Scan mode
node ${CLAUDE_PLUGIN_ROOT}/src/slop-cleaner.js --file <path>
# Fix mode
node ${CLAUDE_PLUGIN_ROOT}/src/slop-cleaner.js --fix --file <path>
Report the output to the user. If slop is found in scan mode, summarize the matches and suggest running with --fix to clean them.