Crafter Station Docs

skillkit: observability for AI agent skills

Local-first observability for AI agent skills. Track usage, measure cost, detect trigger conflicts, monitor context budget, and prune skills you don't use.

AI coding agents load skills into their context window on every session. More skills means less room for your actual code. skillkit answers which skills you actually use, whether they help, and what they cost, with usage analytics, conflict detection, cost analysis, and context budget monitoring. Everything runs locally on your machine.

Prerequisites

skillkit requires Bun as its runtime (native SQLite and fast TypeScript execution):

curl -fsSL https://bun.sh/install | bash

Quick start

No install needed:

bunx @crafter/skillkit scan
bunx @crafter/skillkit stats
bunx @crafter/skillkit health

Or install globally:

bun add -g @crafter/skillkit
skillkit scan

npm i -g also works if Bun is installed, since the bin entry uses Bun as its runtime.

Commands

CommandDescription
skillkit scanDiscover installed skills and index session data
skillkit listList installed skills with size and context budget
skillkit statsUsage analytics with sparklines (last 30 days)
skillkit healthHealth check: unused skills, context budget, DB
skillkit pruneRemove unused skills to reclaim context budget
skillkit burnSubscription burn rate analysis (cost, models, daily)
skillkit conflictsTest skills for trigger collisions
skillkit coverage <skill-path>Analyze dead weight in a skill
skillkit trace <prompt>Run and record a skill execution trace

skill-creator vs skillkit

Anthropic's skill-creator handles skill authoring and evaluation. skillkit handles production observability. No overlap.

On this page