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 CodeCodex
The morning brief on steroids — full AI-sphere intelligence sweep (last-24h AI news via smol.ai + Hacker News, X/Twitter announcements from Anthropic/OpenAI devs, trending YouTube in the Claude Code/Codex sphere, GitHub trending 7d/30d/velocity, optional Gmail last-24h triage) synthesized into one brief ending in a…
Skill Claude CodeCodex needs its repo
Verify OpenEvidence clinical responses by cross-checking each citation against primary sources and detecting evidence omissions. Two-layer verification: Layer 1 (Haiku agents) checks per-citation accuracy; Layer 2 (Sonnet agent) checks evidence completeness. Use when: user says "/oe-verify", "verify OE", or…
Skill Claude CodeCodex
Upload files for AI analysis. SubAgents extract insights and save structured documents.
wubin1836/ai-hive-agent-skills
Skill Codex
A research and content-planning workflow based on publicly observable methods in 36氪, a Chinese technology and business media outlet. It turns those methods into original content and business analysis without copying identity or protected expression.
Skill Claude CodeCodex
Drive the autonomous research loop round after round — ask the engine which node to expand, plan there, run, read the result, repeat. Use when the user wants to keep improving a repository over many rounds, or wants autorun without an AI API key.
Plugin Claude Code
Bundles 20 skills, 3 hooks · 873 tokens together
Disciplined AI Research Assistant for economists: plan-implement-integrate workflow with implementer–reviewer pair, data-analysis discipline, and drift-test-verified integration.
Cursor rule Cursor
How to drive the Crustdata MCP server, and which Crustdata tool to reach for. Apply whenever using the crustdata MCP server (listtools, getschema, execute).
MCP server Claude CodeCodexCursor +2
MCP server "openwiki" as configured in ishizakahiroshi/many-ai-cli. Launched with openwiki mcp --host claude.
Skill Claude CodeCodex
Author: Dr. Aneesh Joseph Implementation: Claude (Anthropic) Version: 2.2 | December 2025.
Skill Claude CodeCodex
Full-autopilot AI research agent powered by Google NotebookLM (notebooklm-py v0.3.4). Ingests sources (URL, text, PDF, DOCX, YouTube, Google Drive), runs deep web research, asks cited questions, and generates 10 native artifact types (audio podcast, video, cinematic video, slide deck, report, quiz, flashcards, mind…
paarths-collab/github-pr-context-mcp
MCP server Claude CodeCodexCursor +2
Hardened Pure Context Retrieval Engine for GitHub PR History. Runs locally from the github-pr-context-mcp Python package.
Plugin Claude Code
Bundles 9 skills, 1 hook · 255 tokens together
Agent-native research workspace: paper ingestion, concept wiki, knowledge graph, claim verification. Skills drive the magi CLI (install: pipx upgrade --install magi-research).
MCP server Claude CodeCodexCursor +2
Unified web ingestion for AI agents: perceive, discover, search, extract, ingest, watch, convert. Runs locally from the @enconvert/mcp npm package.
MCP server Claude CodeCodexCursor +2
MCP server for Altmetric APIs - track research attention across news, policy, social media, and more. Runs locally from the altmetric-mcp npm package. Needs 3 environment variables to run.
johnnyvincentvitale/touchdesigner-wiki-rag
MCP server Claude CodeCodexCursor +2
MCP server "touchdesigner-wiki-rag" as configured in johnnyvincentvitale/touchdesigner-wiki-rag. Runs locally from the touchdesigner-wiki-rag Python package.
Plugin Claude Code
Bundles 34 skills, 4 agents · 1,536 tokens together
Bioinformatics, literature discovery, scientific writing, and data visualization agents and skills for Claude Code and Cowork.
Skill Codex
Use this skill after every published Jiang Lens episode, or when reassessing an existing episode, to decide and record how that source mutates the corpus, existing lens pages, lens points, atlas structure, chronology, and canon candidates.
Agents365-ai/scientific-thinking-general
Skill Claude CodeCodex
Use when interpreting research findings, evaluating scientific evidence, analyzing mechanisms, comparing competing hypotheses, designing experiments, or constructing scientific arguments.
pinkpixel-dev/skills-collection-1
Skill Claude CodeCodex
Audit how a brand appears in AI-powered search (ChatGPT, Perplexity, Claude, Gemini). Use when user mentions "AI search," "how do I show up in ChatGPT," "AI discoverability," "AEO," "LLM visibility," or wants to understand their brand's AI presence.
Plugin Claude Code
Bundles 12 skills, 2 agents, 1 hook · 520 tokens together
A retrieval architecture that pre-projects sources to task domains at ingestion time. Runtime becomes lookup, not reshape. Ships skills for ingesting sources under a 9-pass source-only protocol, retrieving via two-layer indexes (corpus catalogue + per-task distillation indexes), and a PreToolUse hook that enforces…
liyading1818/obsidian-llm-wiki
Skill Cursor
A tool that turns videos or messy web clippings into structured notes stored in an Obsidian LLM-Wiki vault. Obsidian is a note-taking app that stores linked notes as files.
Skill Claude CodeCodex
A strategy for extracting readable content from web pages, including pages that need JavaScript to load or resist automated access.
JasonCodeMaker/Agentic-Research-Control-Panel
Skill Claude CodeCodex
Use when building, serving, repairing, or validating the read-only .research/interface projection.
Skill Claude CodeCodex
One skill for any YouTube request over the yt-mem-ai CLI — one-shot by URL or id ("summarize: ' '", "highlight: ' '", "qa: ' '", "presentation: ' '"), process the latest subscription uploads into a daily digest, or a cross-video subscriptions review. Ingests and caches transcripts (captions → whisper), anchors…
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: