skillranker

# SkillRanker

**The right skill for the next step, powered by Jev from TypeSafe.ai.**

A standalone Rust CLI that puts **[TypeSafe.ai's Jev](https://typesafe.ai)** at the
center of skill selection: Jev evaluates your agent's live context, compares the
available skills, and estimates which ones fit the next step. SkillRanker supplies
the session integration, local safeguards, and inspectable feedback around it.

**A TypeSafe API key is required to use SkillRanker's ranking system.
Sign up at the [TypeSafe console](https://console.typesafe.ai) to get your own key.**

[](LICENSE)






```bash
sr capabilities --json   # Check implemented commands and integrations in your build
sr demo --case useful     # Inspect an offline fixture before connecting a session
sr rank --allow-network   # Rank skills for the selected session
```

</div>

## Contents

- [TL;DR](#tldr)
- [Quick Example](#quick-example)
- [Design Philosophy](#design-philosophy)
- [How It Compares](#how-it-compares)
- [Installation](#installation)
- [Quick Start](#quick-start)
- [Command Reference](#command-reference)
- [Configuration](#configuration)
- [How Ranking Works](#how-ranking-works)
- [Explain And Replay A Result](#explain-and-replay-a-result)
- [Local Feedback And Calibration](#local-feedback-and-calibration)
- [Evaluation, Sampling, And Risk Monitoring](#evaluation-sampling-and-risk-monitoring)
- [Control Requests And Interruptions](#control-requests-and-interruptions)
- [Agent Hooks](#agent-hooks)
- [Inline TUI](#inline-tui)
- [Architecture](#architecture)
- [Privacy And Local State](#privacy-and-local-state)
- [Performance](#performance)
- [Troubleshooting](#troubleshooting)
- [Limitations](#limitations)
- [FAQ](#faq)
- [About Contributions](#about-contributions)
- [License](#license)

---

## TL;D