# hexiecs/talk-normal

Make any LLM talk like a normal person. A system prompt that removes AI slop.

Repository: https://github.com/hexiecs/talk-normal
Canonical: https://ross.abutalabs.com/products/talk-normal
Language: Shell
License: MIT
License Family: permissive
Last push: 2026-04-22T03:21:20+00:00

## Health v2 (maintenance only)
Score: 49/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 78, release rhythm 35, longevity 10
- inputs: {"age_days": 147, "days_push": 133, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, young
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1836, forks 59 (observed 2026-08-28T04:05:42.679731+00:00)

## What it is
A curated system prompt that makes any LLM respond concisely and naturally, removing verbose corporate filler. Distributed as a shell-installable prompt resource with benchmarked results across multiple models.

## Use cases
- make chatgpt stop being verbose
- remove ai slop from llm responses
- get direct answers from claude or gemini
- reduce token usage in llm outputs
- find a good anti-fluff system prompt
- make llm output sound human

## When to choose
- you want a ready-made, tested system prompt to cut LLM verbosity
- you use multiple LLM providers and want model-agnostic conciseness
- you want to reduce response length without losing information

## When to avoid
- you need fine-grained programmatic control over output style
- your application requires verbose or formal LLM output
- you need a library or API rather than a prompt

## Facets
- artifact type: learning-resource
- maturity: active
- function: prompt-engineering, llm-inference, chatbot
- domain: large-language-models, artificial-intelligence, chatbots
- platform: cross-platform, cli
- tags: system-prompt, ai-slop, prompt-collection, shell-script

## Member repositories
- hexiecs/talk-normal (main) score 49

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:05:42.679731+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T03:18:28.630642+00:00, confidence not recorded.
  - readme: https://github.com/hexiecs/talk-normal (fetched 2026-08-28T04:05:42.679731+00:00, sha 83b22f7b6a87)
- Data as of 2026-08-30T08:39:29.467469+00:00.