Run any Skill in Manus
with one click

Run any Skill in Manus with one click

Browse Agent Skills

Filter by

Sort by

yunshui/pdf2mdllm

Convert PDF files to Markdown using LLM vision model. Supports single/multi-page, progress bar, resume, and error handling.

lazyst/my-skills

Convert academic PDF papers (especially Chinese academic papers) to well-structured Markdown. Use when the user needs to extract full content from PDF academic papers (thesis, dissertations, journal articles) and convert to Markdown format. Handles text extraction, OCR fallback for font-encoded/custom-encoding PDFs, layout-aware structuring (title/sections/figures/tables/formulas/references), table extraction, math formula preservation, figure caption formatting, and reference list formatting. Not for general PDF manipulation, form filling, or PDF creation tasks.

pdflux-pdf2markdown

PaodingAI/skills

Convert unstructured documents into LLM-ready structured data. Supports PDF, Word, PPT, and images; extracts paragraphs, formulas, tables, charts, and other elements in one step; generates up to 8 levels of headings; and outputs Markdown organized in reading order. Useful for field extraction, comparison and validation, knowledge retrieval, and intelligent Q&A.

camscanner-pdf2markdown

camscanner-ai/CamScanner-skills

Use CamScanner to convert PDF documents to Markdown format, powered by a high-precision document parsing engine that intelligently decomposes paragraphs, precisely recognizes tables and multiple element types, and outputs structured results in reading order, empowering large language models to accurately understand document content. Use when the user wants to convert PDF files to Markdown, extract content, summarize, or process PDFs. Triggers on "PDF to Markdown", "convert PDF to md", "extract PDF content as Markdown", or when the user has a PDF and needs it as Markdown for further editing or processing.

convertidor-documentos

mpperez3/teaching-agent

Gestiona el pipeline de conversión `pdf2Markdown` y `markdown2Pdf`. No toques ficheros de otros agentes.

pdf-to-md-notebooklm

yakeworld/Synthos

PDF→Markdown→NotebookLM 全流程管线。支持批量上传、自动类型检测、大文件处理。

zi-miao/elite20-starter

Generate publication-grade peer reviews of academic papers (PDF) via a multi-stage neuro-symbolic pipeline: PDF→Markdown ingestion, five orthogonal analyses (story, presentation, evaluations, correctness, significance) with accumulated context, synthesis, self-critique, revision, and final quality check. Each analytical stage runs with dual grounding (original PDF for visual context + Markdown for symbolic structure) and stage-appropriate tool augmentation (code interpreter for evaluations/correctness, web search for significance). Preserves the closed-loop pattern `decompose → analyze → synthesize → self-verify → revise` that distinguishes self-improving inference from one-shot generation. Use this skill whenever the user asks to: review a paper, write a peer review, critique a manuscript, generate an AI review, evaluate a submission for a conference/journal, check a paper's correctness or significance, assess a thesis or preprint, or any variant of "review this PDF" where the input is an academic paper. Tri

fulltext-retrieval

Aperivue/medsci-skills

Batch download open-access PDFs by DOI using legitimate OA APIs (Unpaywall, PMC, OpenAlex, Crossref). Optional PDF→Markdown conversion for token-efficient LLM analysis.

Pr0degie/dungeonmaster

Use when ingesting a new PDF or curated source into the RAG store, or when recalibrating retrieval. Converts PDF→markdown with page/spoiler control, inspects a real chunk, ingests with a source tag, wires the source into retrieval, calibrates the distance threshold, and verifies a sample question hits while a spoiler probe stays silent.

scdenney/open-science-skills

Scaffold or audit an entire research project repository organized around its source library. Use whenever the user is starting, structuring, organizing, or reviewing a whole project — "set up a research repo", "how should I structure/organize this project", "initialize my sources folder", "new paper or literature-review project", "audit my repo structure", "is my sources folder set up right", "check my project layout". Builds the full tree from the sources spine outward — sources/{og,md,unprocessed}, references.bib, a PDF→Markdown convert script (OpenDataLoader PDF), a process-source intake command, CLAUDE.md/AGENTS.md, .gitignore, .venv — plus the analysis, manuscript, and review folders; or audits an existing repo and reports what is present, partial, or missing. NOT for intaking or converting a single PDF (use process-source) or building a publication replication package (use replication-package).

thomas-villani/all2md

Convert, read, generate, search, and compare documents with the all2md CLI and Python library. Use whenever a task involves reading or extracting text/tables from a document (PDF, Word, PowerPoint, Excel, HTML, email, EPUB, Jupyter, images, or 100+ source-code and text file types); converting between formats (PDF→Markdown, Markdown→DOCX/PDF/PPTX/HTML/EPUB, any-to-any); generating documents or static sites from Markdown; grepping for patterns inside non-plaintext files; ranked keyword or semantic search across a document collection; or diffing two documents. Triggers include 'read this PDF', 'extract text/tables', 'convert to Word/PDF', 'make slides', 'export to EPUB', 'search these documents', 'grep this docx', or 'what changed between these files'.

fetching-papers

JakoError/claude-research-skills

Use when the user asks to download, fetch, or parse an academic paper into readable markdown, or references a paper by short-name/code-dir that isn't yet under ./papers/. Covers arXiv, HuggingFace Papers, OpenReview, ACL/CVF, and DOI sources; uses mineru for PDF→markdown.

Run any Skill with one click