stop-slop

hardikpandya/stop-slop · Agent Skill

移除文字中可預測的人工智慧寫作模式，使其更自然、更人性化。

總覽

發布者	hardikpandya社群
儲存庫	hardikpandya/stop-slop ↗
技能資料夾	`stop-slop`
星	16,902
附帶檔案	4
授權	MIT
最近更新	2026年3月16日
連結	技能原始碼 ↗

Mozgi 檢查

我們在技能檔案中發現的內容。詳細資訊需訂閱。

安全性

低風險 · 未發現明顯風險 — 完整報告會顯示細節

相容性

僅含說明 — 適用於多數代理

相似技能

找到 133 個相似技能

訂閱另含

安裝

技能就是一個含 SKILL.md 的資料夾。選擇你的代理，在專案根目錄的終端機（macOS、Linux 或 Windows 的 Git Bash）執行指令。

把提示貼到 Claude、Codex 或其他助理：它會自行檢查並安裝技能。

Install the “stop-slop” skill from mozgi.io (https://mozgi.io/skills/stop-slop/) for me.

1. Download the archive: https://mozgi.io/skills/stop-slop/download
   If it fails, take the skill folder from the source: https://github.com/hardikpandya/stop-slop
2. Read SKILL.md and the other files. Check the skill is safe: no hidden commands, no sending data elsewhere, no scripts doing something other than described. If anything looks suspicious, stop and tell me.
3. Put the “stop-slop” folder into your agent's skills folder: .claude/skills/ for Claude Code, .agents/skills/ for Codex, .cursor/skills/ for Cursor, .gemini/skills/ for Gemini CLI. Inside the project if we are in one, otherwise in the home folder (~/.claude/skills/ etc.).
4. Make sure <skills folder>/stop-slop/SKILL.md exists.
5. Briefly tell me what this skill does and offer to try it on my task.

If you cannot do a step yourself, tell me what to click or type.

git clone --depth 1 --branch main https://github.com/hardikpandya/stop-slop.git /tmp/stop-slop
mkdir -p .claude/skills
cp -r /tmp/stop-slop .claude/skills/stop-slop && rm -rf .claude/skills/stop-slop/.git

重新啟動 Claude Code — 技能就會出現在清單中，手動呼叫：/stop-slop。要套用到所有專案，請放在 ~/.claude/skills。

git clone --depth 1 --branch main https://github.com/hardikpandya/stop-slop.git /tmp/stop-slop
mkdir -p .agents/skills
cp -r /tmp/stop-slop .agents/skills/stop-slop && rm -rf .agents/skills/stop-slop/.git

Codex 會從目前資料夾往上到儲存庫根目錄，在 .agents/skills 中尋找技能；用 /skills 或 $stop-slop 呼叫。所有專案：~/.agents/skills。

git clone --depth 1 --branch main https://github.com/hardikpandya/stop-slop.git /tmp/stop-slop
mkdir -p .cursor/skills
cp -r /tmp/stop-slop .cursor/skills/stop-slop && rm -rf .cursor/skills/stop-slop/.git

Cursor 啟動時會載入技能；在 Agent 聊天輸入「/」呼叫。Cursor 也會讀取 .claude/skills 與 .agents/skills。所有專案：~/.cursor/skills。

git clone --depth 1 --branch main https://github.com/hardikpandya/stop-slop.git /tmp/stop-slop
mkdir -p .gemini/skills
cp -r /tmp/stop-slop .gemini/skills/stop-slop && rm -rf .gemini/skills/stop-slop/.git

任務符合時，Gemini CLI 會提議啟用技能，由你確認。所有專案：~/.gemini/skills。

技能檔案

4 個檔案下載 ZIP

安裝前請先檢視 SKILL.md 與相關檔案。點擊檔案即可預覽。

SKILL.md 內容

作者原文 · 唯讀

Stop Slop

Eliminate predictable AI writing patterns from prose.

Core Rules

1. Cut filler phrases. Remove throat-clearing openers, emphasis crutches, and all adverbs. See references/phrases.md.

2. Break formulaic structures. Avoid binary contrasts, negative listings, dramatic fragmentation, rhetorical setups, false agency. See references/structures.md.

3. Use active voice. Every sentence needs a human subject doing something. No passive constructions. No inanimate objects performing human actions ("the complaint becomes a fix").

4. Be specific. No vague declaratives ("The reasons are structural"). Name the specific thing. No lazy extremes ("every," "always," "never") doing vague work.

5. Put the reader in the room. No narrator-from-a-distance voice. "You" beats "People." Specifics beat abstractions.

6. Vary rhythm. Mix sentence lengths. Two items beat three. End paragraphs differently. No em dashes.

7. Trust readers. State facts directly. Skip softening, justification, hand-holding.

8. Cut quotables. If it sounds like a pull-quote, rewrite it.

Quick Checks

Before delivering prose:

Any adverbs? Kill them.
Any passive voice? Find the actor, make them the subject.
Inanimate thing doing a human verb ("the decision emerges")? Name the person.
Sentence starts with a Wh- word? Restructure it.
Any "here's what/this/that" throat-clearing? Cut to the point.
Any "not X, it's Y" contrasts? State Y directly.
Three consecutive sentences match length? Break one.
Paragraph ends with punchy one-liner? Vary it.
Em-dash anywhere? Remove it.
Vague declarative ("The implications are significant")? Name the specific implication.
Narrator-from-a-distance ("Nobody designed this")? Put the reader in the scene.
Meta-joiners ("The rest of this essay...")? Delete. Let the essay move.

Scoring

Rate 1-10 on each dimension:

| Dimension | Question |

|-----------|----------|

| Directness | Statements or announcements? |

| Rhythm | Varied or metronomic? |

| Trust | Respects reader intelligence? |

| Authenticity | Sounds human? |

| Density | Anything cuttable? |

Below 35/50: revise.

Examples

See references/examples.md for before/after transformations.

License

MIT

常見問題

stop-slop 技能有什麼用途？

移除文字中可預測的人工智慧寫作模式，使其更自然、更人性化。

如何安裝 stop-slop？

打開本頁的「安裝」區塊並選擇你的代理 — Claude Code、Codex、Cursor 或 Gemini CLI：那裡有把技能資料夾複製到正確位置的現成指令。也可以複製「透過助理」分頁中的提示，讓助理自行檢查並安裝技能。

stop-slop 適用哪些 AI 模型？

技能是純 Markdown 指示（Agent Skills 格式），因此 stop-slop 適用任何讀取 SKILL.md 的代理：Claude Code、Codex、Cursor、Gemini CLI、GitHub Copilot、OpenCode 等。只有在任務符合技能描述時，模型才會載入指示。

stop-slop 是免費的嗎？

此技能由 hardikpandya 公開發布，採用 MIT 授權。技能本身免費 — 你只需向 AI 供應商支付實際使用的 token 費用。

安裝技能安全嗎？

技能是代理會遵循的指示，安裝前請閱讀 SKILL.md 及相關檔案。技能資料夾中的腳本只有在代理執行時才會運行 — 留意它的動作，不要授予多餘權限。

技能和 MCP 伺服器或外掛有何不同？

MCP 伺服器或外掛為模型提供新工具 — 會執行並回傳結果的程式碼。技能提供的是知識與流程：如何處理任務、要遵循哪些步驟、好的成果長什麼樣子。它不需要伺服器或 API 金鑰。

總覽