# Curator

> Audit and curate the user's Claude Code skills and MCP servers. Detects overlapping clusters, proposes specialization/deletion, and generates router skills. Use when the user asks to clean up their setup, reduce token bloat, or has too many skills covering similar ground.

- **Type:** Skill
- **Install:** `agentstack add skill-karimjebara-curator-curator`
- **Verified:** Yes — security-reviewed for prompt injection and unsafe behavior
- **Seller:** [KarimJebara](https://agentstack.voostack.com/s/karimjebara)
- **Installs:** 0
- **Category:** [Data & Analytics](https://agentstack.voostack.com/c/data-and-analytics)
- **Latest version:** 0.1.0
- **License:** MIT
- **Upstream author:** [KarimJebara](https://github.com/KarimJebara)
- **Source:** https://github.com/KarimJebara/Curator/tree/main/.claude/skills/curator
- **Website:** https://github.com/KarimJebara/Curator

## Install

```sh
agentstack add skill-karimjebara-curator-curator
```

Requires the [AgentStack CLI](https://agentstack.voostack.com/docs/cli). Works with Claude Code, Cursor, and any MCP-compatible agent.

## About

# curator

When invoked, run the curator audit on the user's `~/.claude/` setup and walk them through the findings.

## How to use

1. Run the scan via Bash: `npx -y @curator/cli scan`.
2. Run the interactive review: `npx -y @curator/cli review`. The CLI walks the user cluster-by-cluster with PASS actions pre-selected and WARN/FAIL pre-skipped — let the user drive that flow themselves.
3. If the user prefers to discuss before running the interactive prompt, read `~/.claude/curator/reports/latest.md`, summarize cluster-by-cluster, and surface verifier WARN/FAIL notes prominently. Then either edit the markdown file to check boxes (and run `curator review --report --apply`) or hand off to the interactive prompt.

## What to flag

- Clusters with mean similarity above 70% — those are usually true duplicates.
- Skills with version-drift suffixes (`-v2`, `-enhanced`, etc.) — almost always safe to delete.
- MCP servers consuming more than 1500 tokens individually — high-value targets for removal or scoping.

## What NOT to do

- Never apply actions without explicit user confirmation per action.
- Never delete a skill that has unique vocabulary or examples not covered elsewhere — even if curator suggested it.
- Never modify the report's structure when checking boxes; only flip `[ ]` to `[x]`.

## Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

- **Author:** [KarimJebara](https://github.com/KarimJebara)
- **Source:** [KarimJebara/Curator](https://github.com/KarimJebara/Curator)
- **License:** MIT
- **Homepage:** https://github.com/KarimJebara/Curator

Install and usage instructions live in the source repository linked above.

## Pricing

- **Free** — Free

## Security capabilities

Automated source analysis of v0.1.0 — what this tool can access:

- **Network access:** no
- **Filesystem access:** no
- **Shell / process execution:** no
- **Environment & secrets:** no
- **Dynamic code execution:** no

*"Yes" means the capability is present in the source — more access means more to trust, not that it is unsafe.*


## Versions

- **0.1.0** — security scan: passed — Imported from the upstream source.

## Links

- Listing page: https://agentstack.voostack.com/l/skill-karimjebara-curator-curator
- Seller: https://agentstack.voostack.com/s/karimjebara
- Browse the marketplace: https://agentstack.voostack.com/browse

---
Listed on AgentStack — the marketplace for AI agent skills and MCP servers. Every listing is security-reviewed. Creators keep 70%.