MCP App StoreMCP App Store
from shuorenhua340
Refine Chinese and English text to remove AI/template tone while preserving facts, terminology, and appropriate register for chat, docs, status, or public writi
This skill detects AI-style or template-like writing and rewrites text to sound like a real person in the target scene. It preserves technical terms, responsibility attributions, and factual content while removing boilerplate, performative phrasing, and translation artifacts.
Use when a user asks for ‘去 AI 味’, ‘说人话’, ‘自然一点’, or similar; for editing chat messages, status updates, docs, and public-facing posts. Avoid when exact wording, verbatim translation, or strict technical prose must be preserved.
Commonly used with Claude Code, Cursor, and other editing/assistant runtimes that support prompt-based text transformation and scene-aware rewrites.
Shuorenhua is a prompt-engineering skill for refining Chinese and English text to remove AI-generated tone (template phrases, performance-style writing, jargon drift) while preserving facts, terminology, and appropriate register. No scripts to execute — purely instructional. The SKILL.md is exceptionally thorough: 8-step execution order, scene detection, tier severity system, edit scope controls, reread checks, and annotation mode. Well-organized with references to supplementary docs.
Very well-crafted prompt-engineering skill. No security concerns whatsoever. Instructions are precise and unambiguous with good guardrails (false-kill protection, protected spans, domain-specific caveats). Architecture could be stronger if the references/ directory contents were bundled or their availability verified.
Verifying Markdown Formatting
Checks Markdown files for structural and stylistic formatting issues (headings, lists, code blocks, links) and applies deterministic fixes.
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/
Ubiquitous Language Glossary
Extract a DDD-style ubiquitous language glossary from conversation: identify domain terms, flag ambiguities, propose canonical terms, and write the result to UB
Humanize AI Text
Rewrite AI-generated text into more natural, human-like prose using the HumanizerAI API, with before/after scores and credit tracking.
Prompt Engineering Patterns
A practical collection of prompt engineering techniques and patterns for building reliable, controllable LLM prompts: CoT, few-shot, structured outputs, templat
Content Research Writer
A writing-partner skill that helps research, outline, draft, cite, and iteratively improve articles, tutorials, and thought pieces.
Learn: From Raw Materials to Published Output
Run a disciplined six-phase research-to-publish workflow (collect, digest, outline, fill, refine, publish) for deep domain research and article preparation.
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