mcpField
T
talk-normal

talk-normal

github.com/hexiecsAgent workflows1.9k75 installsUpdated 27w ago
Repository

About talk-normal

talk-normal is a one-time installer for OpenClaw agents that adds concise-writing rules to a workspace’s AGENTS.md. Its rules target common padded and corporate-sounding phrasing and can be updated or removed without changing other file contents.

Key features

  1. 01Installs persistent writing rules in AGENTS.md
  2. 02Targets filler, hedging, and stock closings
  3. 03Keeps its rules in a marked block
  4. 04Idempotent update and uninstall commands
  5. 05Includes benchmark results for two models

Use cases

  1. 01Reduce verbosity in an OpenClaw agent’s replies
  2. 02Apply consistent response-style rules across a workspace

Install

Copy the command and run it in a terminal.

$npx skills add https://github.com/hexiecs/talk-normal --skill talk-normal

After installing, type/talk-normalin Claude Code to confirm it loaded.

Bundled files

References and scripts installed along with SKILL.md.

install.sh
prompt.md
README.md

Details

From the project README

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

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.

Updating to the latest rules

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.

Compatibility

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.

Measured effect

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.

Upstream and issues

License

MIT

Comments

Markdown supported