# skillmem

> skillmem — liza-studio-skillmem. Use this tool when you need to enhance coding agents with self-improving skill memory, enabling them to learn, recall, and reinforce coding skills while tracking provenance and trust. It solves problems of knowledge retention and skill decay in coding agents, providing a local and private solution with SQLite storage. Ideal for use cases where autonomous coding skills development and trust management are crucial, with seamless integration with git for version control.

Canonical page: https://skillsregistry.net/skills/liza-studio-skillmem  
JSON: https://api.skillsregistry.net/v1/skills/liza-studio-skillmem

## Description

Self-improving skill memory for coding agents: learn, recall, reinforce, decay — with provenance on every memory and trust only you grant. Local SQLite, no API key, no cloud.

## Trust

- **Trust score (0–1):** 0.00
- **Verification tier:** scanned
- **Last scanned:** 2026-09-28

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** container
- **Runtime environment:** vm
- **License:** Apache-2.0
- **Updated:** 2026-09-28

## Source

- **Source listing:** [GitHub](https://github.com/liza-studio/skillmem)

## 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": "liza-studio-skillmem"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/liza-studio-skillmem` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/liza-studio-skillmem/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