#Glossary

This glossary defines the core concepts you'll encounter when working with Tessl.

#Tessl CLI

Tessl's command line tool for installing, updating and managing context for coding agents.

It enables users to:

• Create, install and manage agent skills and Tessl packages across their coding agents
• Publish skills and Tessl packages to the Tessl Registry
• Locally evaluate skills and Tessl packages

#Tessl Registry

Tessl's online registry for discovering and distributing agent context.

It enables users to:

• Discover agent skills and Tessl packages (plugins) and assess their quality (via evals)
• Connect their repositories to Tessl and automatically generate context for them
• Request new skills and Tessl context

#Skill

Agent Skills are folders of instructions, scripts, and resources that agents can discover and use to do things more accurately and efficiently, giving agents access to procedural knowledge and specific context they can load when the agent determines they're relevant (lazy push).

In Tessl, skills are treated as software with a complete lifecycle: versioned, evaluated, and maintained as dependencies and systems change.

See https://agentskills.io/home for more information.

#Tessl package (Plugin)

Tessl packages (or plugins) are versioned bundles of reusable, agent-agnostic context that make coding agents more effective. They can (but do not always) contain:

• Skills
• Rules

Like software packages in npm or pip, Tessl packages are versioned, dependency-managed, and can be safely updated as libraries and systems evolve.

#Tessl project

The stable home for Tessl in a Git repository. A Tessl project identifies that repository and acts as the anchor for the eval runs and other repository-connected data attached to it.

#Factory

The set of loops working on one repository, such as one that turns tickets into pull requests and one that answers reviews on them. See Automations.

#Loop

One action and the triggers that start it. A loop is app-defined, set up in Tessl, or repo-defined, declared in tessl.json. Loops are listed on a project's Loops tab.

#Action

What a run does: the skill to run and, optionally, its environment, agent, model, inputs, and instructions. Declared in the actions block of tessl.json, or written inline in a trigger or schedule.

#Trigger

What starts an action: an event that matches a trigger's conditions, a schedule's cron, or a manual run with Trigger now or tessl action trigger.

#Schedule

A trigger that fires on a cron. See Schedules.

#Run

One execution of an action in Tessl's cloud, with a status, a result, and a transcript.

#Environment

A named set of secrets and access settings that a run uses, such as its GitHub and Linear access. See Environments.

#Repository

A Git repository containing your code and history.

#Codebase

The code inside a repository.

#Working directory

The directory, or subdirectory, where you run the CLI.

#Project link

The link stored in tessl.json that connects a repository to a Tessl project.

#Rules

Mandatory steering for the agent to always follow, always pushed to the agent's context (eager push).

#Verifier

An LLM-as-judge check that evaluates committed files or a diff against a binary, observable repository invariant. The verifier JSON defines what to judge, while the verify block in tessl.json defines its file scope and whether findings are advisory or blocking.

See Verifiers overview for guidance on when to use one.

#Evaluations (evals)

Structured testing processes to systematically measure AI system performance, accuracy and reliability. Evaluations are typically contextual - they depend on the type of evaluation and the type of AI system or agent.

Tessl uses evaluations to validate that skills and context actually improve agent behavior, catch regressions as systems change, and ensure updates are safe before they reach production workflows.

The evaluations we run at Tessl typically measure the success rate of agents on real world tasks with and without some context, by:

• Generating a representative set of tasks
• Prompting agents to solve the tasks with and without the context
• Scoring the agent's solution to the tasks using grading criteria (we typically use criteria with multiple binary criteria at Tessl)
• Comparing baseline performance against performance with the context over all tasks