Agent skill · writing content · aradotso
talk-normal-llm-prompt
System prompt toolkit that removes AI slop and makes any LLM respond like a normal person — concise, direct, no filler.
Why this skill is useful
Provides a specific system prompt and shell script that enhances LLM responses by reducing verbosity and removing filler, which the AI may not generate on its own.
What it needs
Requires jq installed locally. Requires anthropic, google, openai account access. About 4k tokens when loaded. Last updated 2026-07-09. 70 stars on the source repository.
What this skill does
talk-normal Skill by ara.so — Daily 2026 Skills collection. talk-normal is a system prompt (plus a shell-script helper) that strips AI slop — bullet-point padding, hollow affirmations, corporate filler — from any LLM while preserving all useful information. Tested at ~73% character reduction on GPT-4o-mini and GPT-5.4 with no information loss. --- How it works The project is a single prompt.md file (the system prompt) plus optional shell helpers. You copy the prompt text into the "System" field of any LLM interface or API call. --- Installation 1 — Clone the repo 2 — Read the prompt 3 — Copy into your tool Paste the contents of prompt.md into: ChatGPT → Settings → Customize ChatGPT → Custom Instructions → "How should ChatGPT respond?" Claude.ai → Project Instructions Cursor / Windsurf → .cursorrules or global AI rules API calls → system parameter (see examples below) --- Using the prompt via API OpenAI (Python) OpenAI (curl) Anthropic Claude (Python) Google Gemini (Python) Ollama (local models) Or via the Ollama Python SDK: --- Shell helper: one-liner wrapper A reusable shell function that injects the prompt automatically: Usage: --- Embedding in a project's AI config Cursor (.cursorrules) OpenAI Assistants API --- Combining with your own system prompt talk-normal rules are additive — prepend them before your domain instructions: --- Common patterns Pattern 1: Measure verbosity reduction Pattern 2: A/B test with and without the prompt Pattern 3: Keep the prompt up to date --- Contributing a new rule 1. Fork the repo and create a branch: git checkout -b rule/no-em-dashes 2. Edit prompt.md — add your rule in plain imperative English 3. Add an entry to CHANGELOG.md 4. …
How to use it
Reference it in AdaL, Claude Code, Cursor or any coding agent — nothing to install:
@skills aradotso/talk-normal-llm-prompt