# Claude Skills

> Use this tool when you need to discover and retrieve relevant Agent Skills for specialized technical tasks, such as scientific computing workflows in bioinformatics, cheminformatics, and data analysis. It solves problems of skill discovery and implementation by indexing skill descriptions and performing semantic searches to find the most relevant skills. The tool takes in task-specific queries and outputs relevant Agent Skills from GitHub repositories and local directories, complete with accessible Python scripts, references, and assets.

Canonical page: https://skillsregistry.net/skills/k-dense-ai-claude-skills  
JSON: https://api.skillsregistry.net/v1/skills/k-dense-ai-claude-skills

## Description

A vector search-powered MCP server built by K-Dense AI that enables Claude to discover and retrieve relevant Agent Skills from GitHub repositories and local directories using semantic similarity. The server indexes skill descriptions with sentence transformers, performs RAG-based search to find the most relevant skills for specific tasks, and includes document loading capabilities for accessing Python scripts, references, and assets within skills. Designed primarily for scientific computing workflows, it comes pre-configured with 70+ bioinformatics, cheminformatics, and data analysis skills from K-Dense AI's scientific skills repository, plus official Anthropic skills, making it useful for researchers and developers who need contextual guidance on specialized technical tasks and proven implementation patterns.

## Trust

- **Trust score (0–1):** 0.14
- **Verification tier:** scanned
- **Last scanned:** 2026-09-28

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** version-control
- **Updated:** 2026-09-28

## Source

- **Source listing:** [PulseMCP](https://www.pulsemcp.com/servers/k-dense-ai-claude-skills)
- **Repository:** <https://github.com/k-dense-ai/claude-skills-mcp>

## Use it

Resolve this record through the SkillsRegistry MCP server (no auth, read-only):

```
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp
```

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "get_skill",
    "arguments": {
      "slug": "k-dense-ai-claude-skills"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/k-dense-ai-claude-skills` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/k-dense-ai-claude-skills/pull`

---
SkillsRegistry indexes agent skills from public registries and GitHub. Skills we have analysed are scanned with Circle-IR and scored on six dimensions; each listing states its scan coverage. More: https://skillsregistry.net/llms.txt