talk-normal is a system prompt that guides large language models to produce direct, informative responses without filler or corporate-sounding language. It is intended for people using LLMs who want shorter, more natural answers.
Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add hexiecs/talk-normal --skill skillgit clone --depth 1 https://github.com/hexiecs/talk-normalWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/hexiecs/talk-normal/skill)<a href="https://agentmods.dev/skills/hexiecs/talk-normal/skill"><img src="https://agentmods.dev/badge/skills/hexiecs/talk-normal/skill/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/hexiecs/talk-normal/skill"><img src="https://agentmods.dev/badge/skills/hexiecs/talk-normal/skill.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00059 | $0.00915 |
| Opus 5.5 | $0.00024 | $0.00366 |
| Sonnet 5.5 | $0.00012 | $0.00183 |
| Haiku 4.5 | $0.00006 | $0.00092 |
Grade A, and why
talk-normal scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
Copies of this mod
1 near-identical copy found in the catalogue:
- talk-normal — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.
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.
What this skill does
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.
How to run
To install or update talk-normal in the current workspace:
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 install.sh --uninstall
What gets installed
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
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 1mo ago First seen · 75 lines · 59 tokens per session scan A 6c9e2d00e55c
talk-normal is a skill published in the GitHub repository hexiecs/talk-normal (1,857 stars, last pushed 5mo ago), licensed MIT. It adds 59 tokens to every session and 915 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
talk-normal
Stop LLM slop. A curated system prompt that cuts verbose, corporate-sounding LLM output by 56-71% (measured) while preserving information. Works bilingually (English + Chinese). Installs into your AGENTS.md as an always-on behavior modifier.
shuorenhua
A writing guide for making Chinese and English text sound more natural and less formulaic while preserving facts, technical terms, and responsibility.
prompt-optimization
Use this skill when the user wants to optimize, modify, or improve the system prompt of an AI agent. This includes requests like 'optimize the prompt', 'make the AI more focused on X', 'change the system prompt', 'improve the agent behavior', or 'modify how the AI responds'.
superpowers-zh
Use when constraining AI coding with Chinese TDD methodology, systematic debugging, code review, and verification workflows. Superpowers-zh: Chinese adaptation of the Superpowers AI-assisted programming skills and methodologies.
system-prompt
Design and review system prompts for any joelclaw agent surface (gateway, codex workers, content review, loops, etc.). Codifies the canonical principles that every system prompt must follow. Use when writing new system prompts, reviewing existing ones, or when any agent needs to generate instructions for another…
anti-slop-design
Autonomous Principal Design Technologist. Cures vibe-coded software from AI frontend slop using curated token archetypes and 7-axis quality gating.