MCP App StoreMCP App Store
from anti-ai-slop-writing106
Transforms drafts into natural, human-sounding text by enforcing structural variety, banned-phrase avoidance, and punctuation/voice rules to reduce AI-detection
Anti-AI-Slop Writing is a directive-style skill that modifies generated text to avoid common AI fingerprints. It enforces rules like varying sentence length, avoiding predictable 'rules of three', banning specified phrases, limiting punctuation (em dashes, exclamations), and preferring active voice and concrete specifics. The skill loads a banned-words list from references and applies structural and punctuation constraints across formats (tweets, emails, articles, README sections).
Use this skill whenever the user asks the agent to write, draft, rewrite, or humanize copy where output must not read as AI-generated — e.g., cover letters, social posts, product copy, or public-facing documentation. Trigger phrases include: 'write', 'rewrite', 'make this sound human', 'not AI', 'anti-slop'.
This skill is written for use with multi-agent prompt harnesses (Claude Code, Codex, Cursor, Gemini CLI and similar assistants that support skill composition and directive injection).
Pure instructional skill with no scripts. Provides detailed anti-AI-pattern writing rules covering structure, punctuation, voice, formatting, and accuracy. References an external banned-words list via references/banned-words.md for progressive disclosure. Well-written and actionable, though the concept isn't unique — many similar prompts exist. Static analysis only; no executable code to test.
No security concerns whatsoever — no scripts, no network calls, no credentials. Clean instructional content. Well-structured but could benefit from before/after examples directly in SKILL.md.
Seedance Prompt — Short
Build, validate, and compress short-form Seedance 2.0 prompts (30–100 words) using a layered compression engine and @Tag delegation for quad-modal (T2V/I2V/V2V/
Prompt Engineering Patterns
A practical collection of prompt engineering techniques and patterns for building reliable, controllable LLM prompts: CoT, few-shot, structured outputs, templat
Colorize — Strategic UI Color Introduction
Introduce purposeful color to monochromatic interfaces to improve hierarchy, meaning, and visual engagement while preserving accessibility.
Copilot Instructions Blueprint Generator
Generates a technology-agnostic blueprint for creating copilot-instructions.md files that align Copilot output with a project's exact architecture, versions, an
MUAPI Photo Pack Generator (Identity-Lock)
Generate themed photo packs from a single reference image while preserving the exact facial identity and enforcing identity-lock guardrails.
TensorsLab Image Generation
Generate and edit images (text→image, image→image, advanced edits) using TensorsLab models with automatic prompt enhancement and local output saving.
Cold Email Prompt Builder
Generate self-contained, research-driven cold email prompt templates that combine company voice, campaign hypotheses, and enrichment fields into ready-to-run pr
Smart Blog Rewrite
Analyze and rewrite blog posts to improve clarity, update outdated data, preserve author voice, and apply humanization rules to reduce AI-style writing artifact