The package manager for agent skills and context

Versioned, evaluated skills and context for agentic software development.

Get started for free

Tessl helps you find, install, version, and evaluate the skills and context your coding agents rely on, so they behave consistently across tools and projects.

npx tessl search

Explore Tessl Registry

Used by agentic developers at

Context can drive up to 3.3X improvement in agents use of over 300 libraries

Read the blog

How good is your skill? Put it to the test

Evaluate any skill against structured best practices for descriptions and content.

EVALUATE YOUR SKILL

SKILL / V1.2.5 / cisco

software-security

Agent Impact

1.79x

Improvement in agent success rate

Baseline

47%

separator

with Tile

84%

npx tessl i cisco/software-security

SKILL / V1.0.0 / hashicorp

terraform-stacks

Agent impact

2.04x

Improvement in agent success rate

Baseline

47%

separator

with Tile

96%

npx tessl i github:hashicorp/agent-skills --skill terraform-stacks

SKILL / V1.0.0 / elevenlabs

text-to-speech

Agent impact

1.32x

Improvement in agent success rate

Baseline

72%

separator

with Tile

95%

npx tessl i github:elevenlabs/skills --skill text-to-speech

Make agents successful in your environment

BENEFIT

Agents don’t know how to develop in your organization, they need to be onboarded. Turn your APIs, libraries, and conventions into agent-usable skills, docs and rules, so agents stop guessing and start behaving like experienced team members.

Version-matched OSS and internal APIs
Correct imports, calls, and constraints
Fewer retries and review cycles

Get started free

Evaluate what works in real-world scenarios

BENEFIT

Not all context is equal, and mistakes can mislead agents or overwhelm context windows. Evaluate and optimize your skills by running agents through real world scenarios, and testing changes to avoid regressions over time.

Repeatable task evaluations
Regression detection as skills, agents and models evolve
Learn if your context helps or hurts agent performance

Evaluate your skill Evaluate skills on GitHub

Create skills once. Use them across all agents and models

BENEFIT

Tessl gives you a single source of truth for skills and context, reusable across agents, models, and development environments without duplication or drift.

Avoid lock-in with universally compatible context
Consistent behavior across agents
Collaborate on context with your team and agents

Create a workspace

Keep your agent on the rails with better context. Discover thousands of evaluated skills in the Tessl Registry.

Explore Tessl Registry

Don’t take our word for it

We have tens of thousands of engineers using AI tools daily who need support to shift from prompting to context engineering. I believe Tessl's approach to measure, package, and distribute that context automatically is the solution that can unlock agent productivity.

John Groetzinger

Principal Engineer

As someone who's spent 25+ years in software engineering, Tessl's spec-driven approach is the first thing I've seen that bridges the gap between AI's speed and the discipline production systems demand. It's the antidote to throwaway 'vibe coding'.

Mani Sarkar

AI/ML Engineer

The evaluation capability is a big one. It’s hard to build something like that without a centralized system like Tessl. I don’t think we’d realistically create that on our own, so having that constant check on our work is incredibly valuable.