26,336 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.
Skill Claude Code
A Paper Scout research-report workflow creates and archives reports in Lark, a collaboration and document platform. It covers document structure, diagrams, local media, delivery through Lark, and user notification.
Skill Claude CodeCodex
Convert academic PDF papers into clean, well-structured Markdown files using LLM vision. Use when the user provides a PDF paper and asks to extract text, tables, figures, or equations into Markdown, or mentions "parse paper", "PDF to markdown", "extract paper content", or similar.
TTAWDTT/elegant-researcher-skill
Skill Claude CodeCodex
Orchestrate a complete AI/ML research project from a user's idea to a finished research artifact by coordinating bundled research skills: autoresearch, research-lookup, brainstorming-research-ideas, scientific-critical-thinking, scholar-evaluation, ml-training-recipes, academic-plotting, scientific-visualization…
andyhan12138/AILiteratureTools
Skill Claude Code
A skill that fetches all papers newly posted that day in selected arXiv sections, then uses a model to screen them against a written research profile. arXiv is an online repository of research papers; the skill summarises papers that pass the first screen and lists those rejected.
zjp1997720/enterprise-clone-builder
Skill Claude CodeCodex
A tool for building a standardized digital knowledge base for a company from its name, local files, and selected public information. The result is a repository that another writing tool can use to create company content.
Plugin Claude Code
Bundles 1 skill · 119 tokens together
Competitive & market-intelligence investigator: verifies whether a company's or market's claimed traction, funding, momentum, or pricing is real, and returns a calibrated verdict with an evidence trail and residual unknowns.
Skill Claude CodeCodex
Open-ended Q&A against the knowledge base. Uses INDEX.base as the vault Bases wiki index, Obsidian CLI (properties, search, tags, backlinks) to traverse the same graph the Base shows in Obsidian, SCHEMA.md for taxonomy, then reads and synthesizes with citations. Use when the user asks questions about vault content…
Skill Claude CodeCodex
A project knowledge tool for adding, finding, and organising external information in a project’s knowledge section. The description is partly in Chinese and does not define the knowledge format.
Erica-byte-lee/codex-ai-interview-workflow-template
Skill Codex
A skill for collecting and comparing public reports from people who have taken job interviews, using a specific job description as the focus. It keeps sources, search effort, and uncertainty visible.
Skill Codex
Perform a deep, evidence-based analysis when the user explicitly says “deep analyze”, “deep analysis”, “analyze this deeply”, or invokes $deep-analysis. Use before making recommendations or edits when the request requires full-project inspection, dependency/reliability review, architecture analysis, risk assessment…
Plugin Claude Code
Bundles 8 skills · 613 tokens together
Shared skills for Zulip-based research harness repos: collaborator onboarding, reference downloads into .knowledge/, Zulip reply drafting, harness scaffolding, and scheduled advisor chambers.
Skill Claude CodeCodex
Search and read academic papers from arxiv via Semantic Scholar API + ar5iv HTML. No OAuth, no PDF parsing. Use when the user wants to find research papers, read a specific paper, look up citations, or explore academic literature. Trigger on "find papers on", "arxiv", "research on", "look up the paper", "academic…
Plugin Claude Code
Bundles 1 skill, 3 agents, 4 hooks · 341 tokens together
Empirical-convergence workflow — adjudicates a claim graph (GSN argument with in-toto evidence) where every claim's confidence must be earned by real external evidence: research citations first, deterministic spike verdicts for machine-checkable claims, then an independent auditor on a different model before a run may.
dungnotnull/ancient-costume-mural-reconstruction-agent-skill
Skill Claude CodeCodex
Ancient Costume Reconstruction & Archaeological Textile History harness — production-grade evidence-backed analysis with real-time data aggregation, recognized domain methods, academic research integration, and continuous self-improvement via knowledge crawl pipeline. Use for ANY ancient costume reconstruction…
dungnotnull/designer-toy-trend-analysis-agent-skill
Skill Claude CodeCodex
Designer Toy (Collectible) Trend Analysis & Forecasting - Professional-grade harness for Designer Toy Collectible Market & Trend Forecasting with real-time data aggregation, recognized domain methods, academic research integration, and risk-disclosed outputs. Use this skill whenever the user asks about designer toy…
Plugin Claude Code
Bundles 10 skills, 5 commands, 2 agents, 1 MCP server · 892 tokens together
Autonomous ML research pipeline: idea discovery → experiment → review → paper writing.
dungnotnull/historical-cadastral-map-restoration-agent-skill
Skill Claude CodeCodex
Restoration & Digitization of Historical Cadastral Maps — Production-grade evidence-backed analysis harness for Historical Cartography Restoration & GIS Digitization with flexible agent/skill architecture, comprehensive quality gates, and self-improving knowledge pipeline.
Plugin Claude Code
Bundles 6 skills, 5 commands, 2 agents, 2 hooks, 1 MCP server · 478 tokens together
Multi-perspective agent team analysis — general-purpose analysis engine with dynamic perspective generation, incident postmortem, strategic planning, and PRD policy review.
Skill Claude CodeCodex
generate a browser-native research conference talk from an arxiv paper, pdf, title, or extracted text. this skill turns a paper into a live-presentation-ready slideshow with mandatory paper figure inclusion, evidence-backed slides, faithful visual redraw, paper-type-aware deck policy, design-system-driven rendering…
timmyw5/knowledge-origin-protocol
Skill Claude CodeCodex
Rules for researching AI and computer-technology topics using current English sources, especially official documentation, specifications, release notes, and research papers. They require conclusions to be tied to versions and dates.
Skill Claude Code
Investment decision engine that fetches real-time market data and produces actionable stock analysis with probability-weighted scenarios, expected value calculations, and capital allocation guidance. ALWAYS use this skill when the user's message involves ANY of these — even if they don't explicitly ask for "analysis"…
ryantlee25-droid/spectrum-protocol
Agent Claude Code
Product research and problem identification agent. Validates that a problem is real, significant, and worth solving before solution exploration. Produces a structured Problem Brief grounded in evidence-based discovery frameworks. user: "what problems should we focus on for our dev tools product?" assistant: uses…
Skill Claude CodeCodex
Build an on-demand RL-Kernel roadmap, dependency, gap, document-plan, and competitor radar dashboard from live GitHub evidence. Use only when the user explicitly invokes $kernel-radar or /kernel-radar, or explicitly asks to use, run, or invoke the kernel-radar skill. Do not trigger for general RL-Kernel reviews…
0-bingwu-0/html-knowledge-base-templates
Skill Claude CodeCodex
Read the CS183B lecture transcripts in course/transcripts/ and extract the startup ideas / company case studies discussed, rendered into course/notes/ using the template at template/index.html.
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: