GitHub-based review
Submit a skill through a public GitHub repository URL and Tessl scans it automatically for evaluation.
Tessl
Tessl is a registry and evaluator for agent skills, letting developers review skills from GitHub or locally in the terminal. It produces scored feedback, versioned entries, and a public registry listing for evaluated skills.
Overview
Tessl is a registry for agent skills that are versioned, evaluated, and discoverable. The product is positioned as a package manager for agent skills and as a way to give coding agents structured context for software development.
The “Evaluate a skill” flow lets you submit a skill either from a public GitHub repository or from your local machine. Tessl scans the skill, runs evaluation checks, and returns a score and improvement guidance; locally reviewed skills stay private, while GitHub submissions can be added to the public registry.
What Tessl does
Local CLI review
Run `npx tessl skill review ./<path to SKILL.md folder>` from your terminal for local evaluation.
Private and draft workflows
Local reviews work with private repos and work-in-progress skills, which keeps unpublished work out of the registry.
Registry publishing
A successful submission adds the skill to the open registry so other developers can find and install it.
Scored feedback
Evaluations produce a score plus actionable improvements, rather than just a pass/fail result.
Versioned skill records
Skills in the registry are presented as versioned, evaluated, and discoverable assets for agentic software development.
When to use Tessl
Vet a public skill
Check a skill you found on GitHub before relying on it in your own agent workflow. Tessl scans the repository and adds evaluated skills to the public registry.
Evaluate private or draft work
Review a skill that lives in a private repository or an unfinished working tree. The local CLI path keeps the results visible only to you.
Iterate and republish
Publish an improved skill after responding to Tessl’s evaluation feedback. Each publish is versioned, so updates can be tracked over time.
Discover skills by category
Browse the registry when you need skills organized by use case, such as testing, security, documentation, or API development.
Pros and Cons
Pros
- Supports both public GitHub submission and local terminal review.
- Local review works with private repositories and in-progress skills.
- Produces a score and actionable feedback, not just a listing entry.
- Adds evaluated skills to a public registry where others can find and install them.
- Frames skills as versioned assets, which is useful for update and pinning workflows.
Cons
- The source does not list pricing or plan details on the fetched pricing page, which returned a not-found response.
- Specific third-party integrations and supported platforms are not documented in the provided sources.
FAQ
Can I evaluate a skill without publishing it?
No. The page says you can evaluate a skill from a GitHub URL or by running a review locally from your machine.
Does Tessl support private or in-progress skills?
Yes. The local CLI flow is intended for local paths, including private repositories and work-in-progress skills, and the result stays local.
What do I get after evaluating a skill?
A reviewed skill gets a score, actionable improvements, and a page in the registry when submitted through Tessl.
Which integrations or platforms are supported?
The source does not document specific integrations. It does show GitHub-based evaluation and a terminal CLI command for local review.
Quick Facts
- Category
- Developer Tool
- Product type
- Skills registry and evaluator
- Primary workflow
- Evaluate skills from GitHub or locally via CLI
- Source domain
- tessl.io
- Public registry
- Yes, for evaluated GitHub submissions
- Local/private review
- Supported via terminal
Альтернативы Tessl
CreateOS Sandbox
CreateOS Sandbox is an isolated compute environment for running code and agent workloads inside Firecracker micro-VMs. It is designed for workflows that need machine-level isolation, private networking between sandboxes, and programmatic control through SDK, CLI, or MCP.
AakarDev AI
AakarDev AI helps teams manage AI provider access, project-level setups, logs, and analytics from one dashboard. It supports BYOK workflows and lists providers including OpenAI, Google Gemini, Anthropic, Groq, Mistral AI, and Perplexity AI.
Trigger.dev chat agent
Trigger.dev chat agent is a durable AI chat backend for developers building stateful conversations that can survive refreshes, crashes, and long-running turns. It connects with the AI SDK `useChat` flow and runs on managed infrastructure with no timeout on a turn.
Arduino VENTUNO Q
Arduino VENTUNO Q is an edge AI computer for AI and robotics applications. It combines AI inference and deterministic control on a single board and is designed to work with Arduino App Lab.
ByteAsk
ByteAsk is a terminal-first AI coding agent for C and C++ that edits repositories and verifies changes with the real compiler, debugger, sanitizers, and tests before showing a diff. It offers a free tier plus paid plans, with editor connectors and zero-retention handling described in the source.
Codex Plugins
Codex Plugins bundle reusable skills, app integrations, and MCP servers into workflows you can install in the Codex app or use from Codex CLI. They help extend Codex with connected-service tasks, reusable instructions, and shared team workflows.