# Ai Writing Tropes

> Detect and eliminate common AI writing tropes from prose. Use when drafting, editing, or reviewing text to avoid the predictable patterns that mark AI-generated writing.

- **Type:** Skill
- **Install:** `agentstack add skill-joshuadavidthomas-agent-skills-ai-writing-tropes`
- **Verified:** Yes — security-reviewed for prompt injection and unsafe behavior
- **Seller:** [joshuadavidthomas](https://agentstack.voostack.com/s/joshuadavidthomas)
- **Installs:** 0
- **Category:** [Agent Skills](https://agentstack.voostack.com/c/agent-skills)
- **Latest version:** 0.1.0
- **License:** MIT
- **Upstream author:** [joshuadavidthomas](https://github.com/joshuadavidthomas)
- **Source:** https://github.com/joshuadavidthomas/agent-skills/tree/main/ai-writing-tropes

## Install

```sh
agentstack add skill-joshuadavidthomas-agent-skills-ai-writing-tropes
```

Requires the [AgentStack CLI](https://agentstack.voostack.com/docs/cli). Works with Claude Code, Cursor, and any MCP-compatible agent.

## About

# AI Writing Tropes to Avoid

Comprehensive catalog of AI writing patterns that make text feel machine-generated. Any single pattern used once might be fine. The problem is when multiple tropes appear together or when one trope repeats throughout a piece.

## How to Use

When writing or editing prose:

1. Draft the content.
2. Check against the trope categories below.
3. If you spot a pattern, rewrite that passage.
4. Re-read the whole piece for pattern density — a few is tolerable, a cluster is not.

## Trope Categories

### Word Choice

Overused vocabulary and phrasing that AI defaults to. See [references/word-choice.md](references/word-choice.md).

Key offenders: "quietly", "delve", "tapestry", "landscape", "serves as", "leverage", "robust", "harness", "streamline".

### Sentence Structure

Formulaic sentence patterns that no human writes at scale. See [references/sentence-structure.md](references/sentence-structure.md).

Key offenders: negative parallelism ("not X — it's Y"), dramatic countdowns ("Not X. Not Y. Just Z."), self-posed rhetorical questions, anaphora abuse, tricolon abuse, gerund fragment litanies.

### Paragraph Structure

Layout and organization patterns that betray AI generation. See [references/paragraph-structure.md](references/paragraph-structure.md).

Key offenders: short punchy fragments as standalone paragraphs, listicles disguised as prose.

### Tone

Voice and framing habits that sound performative. See [references/tone.md](references/tone.md).

Key offenders: false suspense ("Here's the kicker"), patronizing analogies ("Think of it as..."), false vulnerability, stakes inflation, vague attributions, invented concept labels.

### Formatting

Visual and typographic tells. See [references/formatting.md](references/formatting.md).

Key offenders: em-dash addiction, bold-first bullets, unicode decoration.

### Composition

Document-level structural problems. See [references/composition.md](references/composition.md).

Key offenders: fractal summaries, dead metaphors beaten into the ground, historical analogy stacking, one-point dilution, signposted conclusions.

## Quick Self-Check

Before delivering prose, ask:

- Did I use the same sentence structure more than twice in a row?
- Did I use "not X — it's Y" or "Here's the thing" anywhere?
- Did I stack three or more historical examples back-to-back?
- Did I inflate the stakes beyond what the content warrants?
- Would a human actually write a first draft this way?
- Does any passage sound like it belongs on a motivational poster?

## The One Rule

Write like a human: varied, imperfect, specific.

## Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

- **Author:** [joshuadavidthomas](https://github.com/joshuadavidthomas)
- **Source:** [joshuadavidthomas/agent-skills](https://github.com/joshuadavidthomas/agent-skills)
- **License:** MIT

Install and usage instructions live in the source repository linked above.

## Pricing

- **Free** — Free

## Security capabilities

Automated source analysis of v0.1.0 — what this tool can access:

- **Network access:** no
- **Filesystem access:** no
- **Shell / process execution:** no
- **Environment & secrets:** no
- **Dynamic code execution:** no

*"Yes" means the capability is present in the source — more access means more to trust, not that it is unsafe.*


## Versions

- **0.1.0** — security scan: passed — Imported from the upstream source.

## Links

- Listing page: https://agentstack.voostack.com/l/skill-joshuadavidthomas-agent-skills-ai-writing-tropes
- Seller: https://agentstack.voostack.com/s/joshuadavidthomas
- Browse the marketplace: https://agentstack.voostack.com/browse

---
Listed on AgentStack — the marketplace for AI agent skills and MCP servers. Every listing is security-reviewed. Creators keep 70%.