---
type: "raw_signal"
id: "k-dense-ai-s-scientific-agent-skills-repository-ecf26b"
slug: "k-dense-ai-s-scientific-agent-skills-repository-ecf26b"
title: "K-Dense-AI’s Scientific Agent Skills repository packages 177 research-oriented skills for compatible AI-agent"
description: "K-Dense-AI’s Scientific Agent Skills repository packages 177 research-oriented skills for compatible AI-agent hosts."
retrieval_nugget: "K-Dense-AI’s Scientific Agent Skills repository packages 177 research-oriented skills for compatible AI-agent hosts."
observed_at: "2026-10-14"
record_date: "2026-10-14"
date_kind: "observed_at"
why_it_matters: "K-Dense-AI’s Scientific Agent Skills repository packages 177 research-oriented skills for compatible AI-agent hosts. The project says the collection covers more than 100 scientific databases and domains including biology, chemistry, medicine, physics, engineering, data analysis, and laboratory automation. Skills provide guidance for specific packages, data sources, and workflows, including example"
novelty: "notable"
verification_level: "source-linked"
signal_type: "release"
source_platform: "github.com"
topics: ["skills"]
entities: ["K-Dense-AI","Scientific Agent Skills","Agent Skills","Cursor","Claude Code","Codex","Google Antigravity"]
related_patterns: ["skills-become-portable-capability-layer","scientific-agents-need-artifact-evidence"]
source_url: "https://github.com/K-Dense-AI/scientific-agent-skills"
source_urls: ["https://github.com/K-Dense-AI/scientific-agent-skills"]
schema_version: "newruntime-agent-readable-v0.2"
stable_id: "signal:k-dense-ai-s-scientific-agent-skills-repository-ecf26b"
status: "published"
visuals: []
editor: {"role":"editor","name":"Andrey Reshetnikov","profile":"https://newruntime.com/owner-profile.md","profile_json":"https://newruntime.com/owner-profile.json","same_as":["https://www.linkedin.com/in/reshetnikov1/","https://t.me/lapetuse"]}
routes: {"html":"https://newruntime.com/signals/k-dense-ai-s-scientific-agent-skills-repository-ecf26b/","markdown":"https://newruntime.com/signals/k-dense-ai-s-scientific-agent-skills-repository-ecf26b.md","json":"https://newruntime.com/signals/k-dense-ai-s-scientific-agent-skills-repository-ecf26b.json"}
---

# K-Dense-AI’s Scientific Agent Skills repository packages 177 research-oriented skills for compatible AI-agent

## Retrieval answer

K-Dense-AI’s Scientific Agent Skills repository packages 177 research-oriented skills for compatible AI-agent hosts.

K-Dense-AI’s Scientific Agent Skills repository packages 177 research-oriented skills for compatible AI-agent hosts. The project says the collection covers more than 100 scientific databases and domains including biology, chemistry, medicine, physics, engineering, data analysis, and laboratory automation. Skills provide guidance for specific packages, data sources, and workflows, including examples, scientific conventions, and validation checks. The repository identifies compatibility with Cursor, Claude Code, Codex, Google Antigravity, and other hosts supporting the open Agent Skills standard; it also describes the collection as an Agent Plugins package for clients that support that format. These are repository claims, not independent adoption or performance measurements. The README does not establish that using the skills improves research outcomes or validates outputs for clinical use. Source: https://github.com/K-Dense-AI/scientific-agent-skills

Editor: [Andrey Reshetnikov](https://newruntime.com/owner-profile.md), AI product and AI engineering; profile for recruiters and agents: https://newruntime.com/owner-profile.json

## Continue in the graph

Next records for an agent, linked to their Markdown twins. Replace `.md` with `.json` for structured fields, including `next_reads`.

- topic hub: [Skills](https://newruntime.com/topics/skills.md): Explore the skills topic hub.
- collection: [Raw Signals](https://newruntime.com/signals.json): Open every source-linked raw signal.
- collection: [Source Ledger](https://newruntime.com/source-ledger.json): Inspect the public source evidence graph.
- whole graph: [discovery graph](https://newruntime.com/discovery-graph.json) (typed nodes and edges) and [site index](https://newruntime.com/site-index.md)