MCP App StoreMCP App Store
from paper-humanizer-skill59
Academic text polisher for Chinese and English: removes AI-like phrasing while preserving factual accuracy, citations, and numeric data.
Paper Humanizer is a prescriptive editing skill that refactors academic text to sound more natural and less AI-generated while preserving all factual content, citations, and numeric values. It enforces a strict no-fabrication policy, keeps technical terminology intact, and applies language-specific phrase blacklists to remove common AI-isms. The SKILL.md includes system prompts, blacklist rules, parameter templates, and a recommended 4-section output format for deterministic responses.
Use when preparing drafts for submission (papers, theses, conference abstracts) to polish tone and phrasing without altering results, metrics, or citation markers. Useful for bilingual workflows (Chinese and English) and for editors who must maintain strict factuality.
Suited to agents that compose deterministic prompts and can apply editorial rules (Claude, LLM-based editorial pipelines, code-enabled assistants).
Paper Humanizer is an academic text polisher that removes AI-like phrasing in Chinese and English writing. It provides a structured 4-section output format and configurable parameters. The Python script composes prompts from template files but crashes without the prompts/ directory (no fallback or bundled defaults). The shell wrapper is a thin CLI around the Python script. No security concerns — scripts only read local files and compose text prompts.
Clean, focused skill with no security issues. Main weakness is script fragility — fails outside the full repo context. The prompts/ directory referenced in SKILL.md (references/system_prompt.md, references/phrase_blacklist.md, references/user_template.md) isn't bundled in the scripts dict, so the CLI is non-functional without cloning the full repo. Consider this a prompt-engineering skill that happens to ship optional CLI tooling.
arxiv2md
Convert arXiv papers into clean, LLM-ready Markdown via a REST API or CLI for fast reading, summarization, and downstream processing.
Verifying Markdown Formatting
Checks Markdown files for structural and stylistic formatting issues (headings, lists, code blocks, links) and applies deterministic fixes.
Generate Multilingual Sentences with Contextual Definitions
Produce multiple example sentences using a target word in varied meanings, translate them into a target language, and show the contextual meaning of the word fo
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/
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
DSPy — Declarative LM Programming
Use DSPy to build declarative, modular LM pipelines, optimize prompts automatically, and assemble reliable RAG/agent systems with structured signatures and opti
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