# Skill Dashboard

> >

- **Type:** Skill
- **Install:** `agentstack add skill-fblissjr-fb-claude-skills-skill-dashboard`
- **Verified:** Yes — security-reviewed for prompt injection and unsafe behavior
- **Seller:** [fblissjr](https://agentstack.voostack.com/s/fblissjr)
- **Installs:** 0
- **Category:** [Data & Analytics](https://agentstack.voostack.com/c/data-and-analytics)
- **Latest version:** 0.1.0
- **License:** Apache-2.0
- **Upstream author:** [fblissjr](https://github.com/fblissjr)
- **Source:** https://github.com/fblissjr/fb-claude-skills/tree/main/apps/skill-dashboard/skills/skill-dashboard

## Install

```sh
agentstack add skill-fblissjr-fb-claude-skills-skill-dashboard
```

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

## About

# skill-dashboard

Interactive ext-apps MCP App dashboard for the fb-claude-skills project. Discovers all skills and plugins, runs quality checks, and renders results as an interactive dashboard.

## Invocation

```
/skill-dashboard
```

Or trigger via natural language: "show skill dashboard", "skill status", "which skills are stale?"

## MCP tool

The `skill-quality-check` tool accepts an optional `filter` parameter (skill name substring) and returns structured content with:

- Per-skill checks: spec compliance, description quality, freshness, token budget, body size
- Per-plugin checks: manifest fields, marketplace listing, README existence
- Repo hygiene: gitignore rules, ambient hooks, state files, duplicate names, best_practices.md freshness
- Summary: passed/failed/total counts
- Meta: generation timestamp, budget thresholds (warn: 4000, critical: 8000)

## What it shows

### Skills table

| Column | Source | Notes |
|--------|--------|-------|
| Skill name | SKILL.md frontmatter | auto-discovered |
| Spec compliance | Agent Skills spec validation | green/red dot |
| Description quality | WHAT verb + WHEN trigger check | green/red dot, detail on hover |
| Freshness | metadata.last_verified | days since verified |
| Token budget | .md file size estimate | bar chart, warn >4k, crit >8k |
| Body size | SKILL.md line count | warn >500 lines |

### Plugins table

| Column | Source | Notes |
|--------|--------|-------|
| Plugin name | .claude-plugin/plugin.json | auto-discovered |
| Manifest | required fields check | green/red dot |
| Marketplace | marketplace.json listing | green/red dot |
| README | file existence check | green/red dot |

### Repo hygiene

Pass/fail list: gitignore rules, ambient hooks, state files, duplicate names, best_practices.md freshness, version alignment.

## Server

TypeScript ext-apps MCP App at `apps/skill-dashboard/mcp-app/`. Build with `bun run build`, run with `node dist/index.cjs --stdio` or as HTTP server on port 3002.

## Source & license

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

- **Author:** [fblissjr](https://github.com/fblissjr)
- **Source:** [fblissjr/fb-claude-skills](https://github.com/fblissjr/fb-claude-skills)
- **License:** Apache-2.0

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-fblissjr-fb-claude-skills-skill-dashboard
- Seller: https://agentstack.voostack.com/s/fblissjr
- 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%.