# blink

> blink — jayemscript-blink. Use this tool when you need to automate code-related tasks, such as reading, creating, or modifying code files, and require intelligent assistance. It solves problems like streamlining development workflows and improving code quality, accepting commands and code files as input and producing modified code files as output. It is ideal for use in software development contexts, particularly with git version control systems.

Canonical page: https://skillsregistry.net/skills/jayemscript-blink  
JSON: https://api.skillsregistry.net/v1/skills/jayemscript-blink

## Description

An AI-powered agentic command-based assistant that can read, create, and modify code files with intelligent assistance from Replicate's Claude models.

## Trust

- **Trust score (0–1):** 0.74
- **Verification tier:** scanned
- **Last scanned:** 2026-09-28

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** container
- **Runtime environment:** vm
- **License:** MIT
- **Updated:** 2026-09-28

## Source

- **Source listing:** [GitHub](https://github.com/jayemscript/blink)

## 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": "jayemscript-blink"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/jayemscript-blink` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/jayemscript-blink/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