ingest
73jason-effi-lab/karpathy-llm-wiki-vault
Skill Claude CodeCodex
A knowledge-base import tool that turns unprocessed files in the raw/ folder into Wiki pages, then moves the source files into raw/09-archive/.
15,341 mods in this category, of every kind an agent can take. Each one carries what it costs per session, what the scan found, and whether it is the original.
jason-effi-lab/karpathy-llm-wiki-vault
Skill Claude CodeCodex
A knowledge-base import tool that turns unprocessed files in the raw/ folder into Wiki pages, then moves the source files into raw/09-archive/.
Skill Claude CodeCodex
A documentation tool that reorganizes project files and source code into an offline, book-like website with guided reading, navigation, search, themes, and diagrams.
agarwalvishal/claude-chat-exporter
Instructions file
Instructions for agarwalvishal/claude-chat-exporter, covering claude.md, what this is, core design decision, how the export works and the install page & bookmarklet (docs/index.html).
AgentTeam-TaichuAI/ScienceClaw
Skill Claude CodeCodex
Use this skill whenever the user wants to create, read, edit, or manipulate Word documents (.docx files). Triggers include: any mention of 'Word doc', 'word document', '.docx', or requests to produce professional documents with formatting like tables of contents, headings, page numbers, or letterheads. Also use when…
Skill Claude CodeCodex
Comprehensive PDF manipulation toolkit for extracting text and tables, creating new PDFs, merging/splitting documents, and handling forms. When GLM needs to fill in a PDF form or programmatically process, generate, or analyze PDF documents at scale.
johnsonhk88/AI-Bank-Statement-Document-Automation-By-LLM-And-Personal-Finanical-Analysis-Prediction
Skill Claude CodeCodex
Guidelines for parsing bank statements using YOLO layout detection + OCR + LLM.
Skill Claude CodeCodex
Search and manage private, local document collections (PDF, PPTX, DOCX) offline. Use when you need to find information within your private files, not for web research.
Instructions file CodexOpenCode
Project instructions for feedgrab, a tool that collects content from many online platforms and converts it into structured Markdown files that work with Obsidian, a note-taking app.
op7418/Document-illustrator-skill
Skill Claude CodeCodex
A tool that reads a document, identifies its main topics, and generates matching illustrations. It supports Markdown, plain text, PDFs, and other document formats.
MazzaWill/neo4j-python-pandas-py2neo-v3
Skill Claude CodeCodex
Use when designing, importing, querying, or modernizing Neo4j knowledge graphs from CSV, Excel, pandas, Cypher, py2neo, the official neo4j Python driver, vector indexes, or GraphRAG workflows.
Instructions file CodexOpenCode
Instructions for vivekVells/mcp-pandoc, covering agents.md, what this is, where things are, deeper context and commands.
Plugin Claude Code
Bundles 1 command, 1 agent · 187 tokens together
McKinsey-style PPTX generator with 40 production-ready slide templates (executive summary, BCG matrix, KPI dashboard, roadmap, org chart, historic-forecast, etc.). Ships with a subagent that picks the right template for each slide, defends its choice, and builds a real .pptx file. Built by AX Labs.
Instructions file CodexOpenCode
Instructions for neiltron/apple-health-mcp, covering repository guidance, project, validate changes, code map and invariants.
Command Claude Code
Integrate a new document parsing pipeline into ParseBench: $ARGUMENTS.
ZyhSechub/chinese-thesis-workbench-skill
Skill Claude CodeCodex
Standardize, draft, revise, check, and package Chinese undergraduate thesis or graduation-design papers from school templates, task books, proposals, sample papers, source code, screenshots, databases, APIs, tests, literature PDFs, Word comments, and existing drafts. Use when the user asks to write, generate…
Agent
You are the orchestrator agent for a multi-agent slide production pipeline. You do not personally create every artifact. Your job is to split the work into verifiable stages and ensure that each stage produces outputs clean enough for the next stage to consume reliably.
Skill Claude CodeCodex
Use this skill whenever the user wants to do anything with PDF files. This includes reading or extracting text/tables from PDFs, combining or merging multiple PDFs into one, splitting PDFs apart, rotating pages, adding watermarks, creating new PDFs, filling PDF forms, encrypting/decrypting PDFs, extracting images, and…
Skill Claude CodeCodex
Use this skill any time a .pptx or .potx file is involved in any way — as input, output, or both. This includes: creating slide decks, pitch decks, or presentations; reading, parsing, or extracting text from any .pptx or .potx file (even if the extracted content will be used elsewhere, like in an email or summary)…
Instructions file CodexOpenCode
Instructions for sc932/resume, covering agents.md, purpose, two audiences, file map and how the artifacts relate.
Skill Claude CodeCodex
Parse documents with LiteParse and answer questions with visual citations. Generates an HTML report with the answer, source page images, and bounding box highlights on cited text.
joeseesun/qiaomu-markdown-proxy
Skill Claude CodeCodex
A tool for turning web pages, documents, PDFs, and supported links into clean Markdown. It chooses different ways to retrieve content from sites such as WeChat, Feishu, YouTube, arXiv, and ordinary web pages.
Plugin Claude Code
Bundles 5 agents · 0 tokens together
Generate editable PowerPoint decks from papers, PDFs, code repositories, documents, and existing slides.
Instructions file CodexOpenCode
Instructions for floodtide/dom-docx, covering agent guide: html → docx (dom-docx), design goal for agents, what converts best, tier 1 — excellent (90–96% visual fidelity) and tier 2 — good (80–92%).
Plugin Claude Code
Bundles 1 skill · 159 tokens together
Read web pages, documents (PDF/Office/EPUB), and YouTube transcripts as clean Markdown via PullMD, with WebFetch fallback.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: