# mikiarlo3/ai-copywriter

An AI copywriter that uses real copywriting skills + real marketing knowledge with human tone.

Repository: https://github.com/mikiarlo3/ai-copywriter
Canonical: https://ross.abutalabs.com/products/ai-copywriter
Language: Python
License: MIT
License Family: permissive
Last push: 2026-08-01T16:30:08+00:00

## Health v2 (maintenance only)
Score: 55/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 95, release rhythm 35, longevity 2
- inputs: {"age_days": 40, "days_push": 32, "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 1048, forks 45 (observed 2026-08-28T04:03:22.407126+00:00)

## What it is
A portable Markdown-based agent skill that writes marketing copy (headlines, descriptions, microcopy, subject lines) with a human tone while removing signs of AI-generated writing. It builds on blader's Humanizer (33 AI-writing patterns) and enso.bot communication research, interviewing the user about the target reader before writing.

## Use cases
- write clickbait titles that don't read like AI
- generate product descriptions with human tone
- create email subject lines that convert
- write UI microcopy and button labels
- remove AI-writing patterns from marketing text
- explain complex product concepts simply in copy

## When to choose
- you need marketing copy that avoids detectable AI-writing patterns
- you use an LLM harness that supports skill-style Markdown instructions
- you want copy grounded in reader-feeling and simple-language methodology

## When to avoid
- you need a full copywriting application with a GUI or API
- your harness does not support skill-style Markdown prompts
- you need automated A/B testing or analytics for copy

## Facets
- artifact type: plugin
- maturity: active
- function: prompt-engineering, agent-framework, nlp
- domain: artificial-intelligence, large-language-models
- platform: cross-platform, cli
- tags: agent-skill, copywriting, humanizer, marketing-copy, markdown-skill, llm-prompt, ai-agents, marketing, natural-language-processing

## Member repositories
- mikiarlo3/ai-copywriter (main) score 55

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:03:22.407126+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 2026-08-30T07:00:46.110945+00:00, confidence not recorded.
  - readme: https://github.com/mikiarlo3/ai-copywriter (fetched 2026-08-28T04:03:22.407126+00:00, sha 9523b5e1c904)
- Data as of 2026-08-30T08:39:29.467469+00:00.