Back to Details

talk-normal

Compare original and translation side by side

🇺🇸

Original

English
🇨🇳

Translation

Chinese

talk-normal

talk-normal

A curated system prompt that stops your LLM from writing like a LinkedIn post. Measured: 71% character reduction on GPT-4o-mini, 56% on GPT-5.4, across 10 prompts in English and Chinese, without losing information.
一个精心设计的系统提示词，让你的LLM不再写出像LinkedIn帖子那样的官腔内容。实测显示：针对10组中英文提示词，GPT-4o-mini的输出字符量减少71%，GPT-5.4减少56%，且不会丢失信息。

What this skill does

该技能的作用

When invoked, this skill installs the talk-normal rules into your workspace's 
AGENTS.md
file as an always-on behavior modifier. After install, every reply your OpenClaw agent produces follows the rules in 
prompt.md
. The rules live between 
# --- talk-normal BEGIN ---
and 
# --- talk-normal END ---
markers so they do not conflict with your existing rules in 
AGENTS.md
.
This is not a workflow skill you invoke per turn. It is a one-time installer that makes your agent permanently less verbose until you uninstall.
调用后，此技能会将talk-normal规则安装到工作区的
AGENTS.md
文件中，作为持久生效的行为修正器。安装完成后，你的OpenClaw agent生成的每一条回复都会遵循
prompt.md
中的规则。这些规则位于
# --- talk-normal BEGIN ---
和
# --- talk-normal END ---
标记之间，不会与
AGENTS.md
中已有的规则冲突。
这并非需要逐轮调用的工作流技能，而是一次性安装工具，安装后你的agent会永久降低冗余度，直到你卸载它。

How to run

运行方式

To install or update talk-normal in the current workspace:
bash
bash install.sh
The script is idempotent: running it again replaces the existing talk-normal block in place with the latest rules. Nothing else in your 
AGENTS.md
is touched.
To remove:
bash
bash install.sh --uninstall
要在当前工作区安装或更新talk-normal：
bash
bash install.sh
该脚本具有幂等性：再次运行会用最新规则替换现有talk-normal块，不会修改
AGENTS.md
中的其他内容。
卸载方式：
bash
bash install.sh --uninstall

What gets installed

安装内容

The contents of 
prompt.md
get injected into your 
AGENTS.md
. The rules target the specific slop patterns that make LLM output sound corporate and padded, grouped into a few categories:
  • Filler and hedging — banned opening phrases ("Great question", "I'd be happy to", "让我们一起来看看"), no throat-clearing, no restating the question
  • Structural discipline — lead with the answer, match depth to complexity, use bullets only when content is genuinely parallel, cap explanations for conceptual questions
  • Closing patterns — no "In summary" / "Hope this helps" / "综上所述", no hypothetical follow-up offers, no conditional next-step menus ("If you want I can also...")
  • Rhetorical tics — no "不是X，而是Y" / reject-then-correct framing in any variant, no plain-language restatements ("翻成人话", "in other words")
  • Shape of comparisons — give a recommendation with brief reasoning, cap pros/cons lists, no balanced-essay posture
The exact rule list lives in 
prompt.md
and evolves as new slop patterns get caught in the wild. Every commit to that file is a named slop pattern killed.
prompt.md
的内容会被注入到你的
AGENTS.md
中。这些规则针对那些让LLM输出听起来官腔十足、冗余拖沓的特定模式，分为以下几类：
  • 冗余填充与模糊表述 — 禁用开场套话（如“好问题”、“我很乐意解答”、“让我们一起来看看”），禁止铺垫性表述，禁止重复问题
  • 结构规范 — 开门见山给出答案，根据内容复杂度匹配深度，仅当内容真正平行时使用项目符号，限制概念类问题的解释篇幅
  • 结尾模式 — 禁止“总结一下”/“希望这对你有帮助”/“综上所述”这类表述，禁止假设性后续提议，禁止条件式下一步菜单（如“如果你需要，我还可以...”）
  • 修辞陋习 — 禁止“不是X，而是Y”这类先否定再纠正的表述，禁止口语化重述（如“翻成人话”、“in other words”）
  • 对比表述规范 — 给出建议并附上简短理由，限制优缺点列表长度，禁止采用中立论文式的姿态
具体规则列表位于
prompt.md
中，会随着新发现的冗余模式不断更新。该文件的每一次提交都意味着一种冗余模式被终结。

Updating to the latest rules

更新至最新规则

bash
clawhub update talk-normal
bash install.sh
The first command pulls the latest skill bundle from ClawHub. The second command re-runs the idempotent installer, replacing the old rule block in 
AGENTS.md
with the new one.
bash
clawhub update talk-normal
bash install.sh
第一条命令从ClawHub拉取最新的技能包，第二条命令重新运行幂等安装器，用新规则替换
AGENTS.md
中的旧规则块。

Compatibility

兼容性

Works on any LLM that honors system prompts or custom instructions: GPT-5.4, GPT-4o-mini, Claude 4.6, Gemini 2.5, Grok 3, Qwen 3, DeepSeek V3, and others. OpenClaw integration is via 
AGENTS.md
injection, which the agent reads on every turn.
适用于任何支持系统提示词或自定义指令的LLM：GPT-5.4、GPT-4o-mini、Claude 4.6、Gemini 2.5、Grok 3、Qwen 3、DeepSeek V3等。与OpenClaw的集成通过注入
AGENTS.md
实现，agent会在每轮调用时读取该文件。

Measured effect

实测效果

Full benchmark data for 10 prompts across GPT-4o-mini and GPT-5.4 is in 
TEST_RESULTS.md
in the upstream repository. Average reduction: 71% on GPT-4o-mini, 56% on GPT-5.4, while preserving the information content of the original response.
针对GPT-4o-mini和GPT-5.4的10组提示词的完整基准数据位于上游仓库的
TEST_RESULTS.md
中。平均减少率：GPT-4o-mini为71%，GPT-5.4为56%，同时保留了原始回复的信息内容。

Upstream and issues

上游仓库与问题反馈

License

许可证

MIT
MIT