# loom

> loom — reslava-loom. Use this tool when you need to maintain AI state across sessions, enabling seamless workflow management from idea to execution. It solves problems of context loss and staleness by providing a scoped context and staleness detection, with human approval at every phase. Ideal for complex workflows, loom takes in chat inputs and outputs a structured plan with a roadmap and history of shipped features.

Canonical page: https://skillsregistry.net/skills/reslava-loom  
JSON: https://api.skillsregistry.net/v1/skills/reslava-loom

## Description

Makes AI stateful across sessions. Workflow: chat → idea → design → reqs → plan → do_step(s) → done, with fresh scoped context, staleness detection, and human approval at every phase. Roadmap & history of shipped features.

## Trust

- **Trust score (0–1):** 0.50
- **Verification tier:** unverified

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** container
- **Runtime environment:** vm
- **License:** MIT
- **Updated:** 2026-09-21

## Source

- **Source listing:** [GitHub](https://github.com/reslava/loom)

## 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": "reslava-loom"
    }
  }
}
```

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