# FAQs The following lists a set of questions that we have been asked about Tessl in the past. If you have a different question which isn’t answered here, talk to the community on the [Discord Server](https://discord.com/channels/1233374481364418570/1417176126207426760). ## Getting Started ### How can I install a skill with Tessl? You can install skills using the Tessl CLI. Search for available skills with `tessl search ` and install them with `tessl install `. Tessl automatically evaluates skills to ensure they improve agent behavior. For detailed instructions, see the [Quick start guide](https://github.com/tesslio/docs/blob/main/introduction-to-tessl/quick-start-guide.md). ## Core Concepts ### What is a Tile? Tiles are Tessl packages, which are bundles of reusable context that capture knowledge you want to use across your team and projects. Common Tile content includes: * Agent skills * Usage documentation for libraries, APIs, tools, etc. * Common, repeatable workflows * Styleguides * Policies * ... ### What is the difference between a Tile and a skill? A Tile is a bundle of agent context. A Tile is a container for context - it's what you install and manage via the package manager. A skill is one type of context that can be included inside a Tessl package (along with docs and rules). A helpful analogy is: * Tessl package/Tile = the npm package * Skills, docs, rules, commands = different types of files inside that package Just like npm packages, tiles are versioned and can be updated safely as libraries and dependencies evolve. For detailed definitions, see our [Glossary](/reference/glossary.md). ## Platform ### What agents does Tessl support? Skills are agent and model-agnostic, allowing teams to maintain consistent behavior across tools without locking into a single ecosystem. Tessl installs skills to the appropriate agent-specific directory: * **Claude Code**: `.claude/skills/` * **Cursor**: `.cursor/skills/` * **Codex**: `.codex/skills/` * **Gemini**: `.gemini/skills/` * **Copilot CLI**: `.copilot/skills/` * **Copilot in VSCode**: `.copilot-vscode/skills/` Docs: full support for Claude Code, Cursor, Gemini, Codex, Copilot CLI, and Copilot in VSCode. See the [Supported platforms](/support/supported-platforms.md#agents) reference for the most up-to-date list of supported agents. ### How does Tessl compare to other marketplaces like skills.sh? [skills.sh](https://skills.sh) is a directory and an easy way to browse and copy individual skills. Tessl is a fully fledged package manager and registry for agent context: you install, version, and update skills as dependencies rather than duplicating them to your codebase. Comparing the two: * **skills.sh** – Browse and copy skills from a catalog; no built-in versioning or dependency management. You manually keep skills in sync. * **Tessl** – Install skills with `tessl install `; skills are versioned, tracked in a manifest, and updates are controlled and repeatable across your team. Tessl also adds: * **Evaluation** – Measure whether skills are structured well and if they improve agent behavior * **Lifecycle managemenet** – Ensure skills stay correct and up to date as systems change So Tessl treats skills as software with a full lifecycle (build, evaluate, distribute, optimize), which helps teams move from ad‑hoc agent usage to long-lived, production systems where agent behavior can be inspected, measured, and reasoned about. ## Evaluations ### How does Tessl evaluate skills? Tessl evaluates skills using both task evaluations and conformance reviews: **Task evaluation:** Measure whether agents can successfully complete real-world coding tasks when using the skill. * Creates a representative set of coding tasks that require using the skill * Runs each task with the agent both with and without the skill installed * Scores each task using task-specific success criteria * Compares baseline performance against performance with the skill over all tasks * Reports improvement as a multiplier (e.g., 2× improvement) **Conformance review:** Assess whether the skill conforms to the Agent Skills specification created by Anthropic. * Validates that the skill conforms to the official specification at [agentskills.io/specification](https://agentskills.io/specification) * Checks proper file structure and formatting * Verifies required frontmatter fields (name, description) * Ensures the skill follows best practices defined in the specification ### How does Tessl generate documentation for libraries? Tessl is designed to flexibly generate context for coding agents from existing code repositories, by scanning the codebase and compressing the content into context packages. For documentation, we focus this process primarily on the APIs, methods, conventions, patterns, and idioms in the code. Documentation is continuously evaluated to ensure it helps agents use libraries correctly. As libraries evolve, documentation is version-matched to keep agent behavior aligned with current APIs. We've populated the Tessl Registry with agent-optimized, evaluated documentation for over 10,000 OSS packages. If the one you're looking for is not available, request it at ### How does Tessl evaluate docs? Tessl evaluates documentation using task-based evaluations that test whether agents can correctly use a library's APIs when they have access to the Tessl-generated docs. **API usage tasks:** Creates coding tasks that require proper use of a library's APIs, covering imports, examples, conventions, and common patterns * Runs each task with the agent both with and without having access to the Tessl documentation via MCP * Scores each task using task-specific success criteria, which evaluates whether the agent: * Uses the correct APIs and methods * Follows proper conventions and patterns * Avoids common pitfalls and mistakes * Produces working, idiomatic code * Compares baseline performance against performance with the docs over all tasks * Reports improvement as a multiplier This checks documentation actually improves agent behavior rather than just adding more context that could make things worse. In benchmarks, teams using Tessl saw up to 3.3× improvement in correct API usage across open-source libraries. ## Publishing & Sharing ### How can I publish a skill? To publish a skill: * Create an account and workspace on Tessl * Define visibility (public or private) at the Tessl package level * Use the Tessl CLI to publish: * `tessl skill publish` - If you have a standalone `SKILL.md` file (skill-first workflow) * `tessl tile publish` - If you've created a tile structure with `tile.json` that contains a skill (tile-first workflow) Published skills are evaluated and versioned, so users can see quality metrics and choose versions that match their dependencies. See [Creating skills](/create/creating-skills.md) for a complete tutorial. ### Can I share these with my team? Yes! The Tessl Registry has workspaces which let you share Tessl packages for your own libraries with your team members. Skills and context can be kept private to your workspace or published publicly. This allows teams to onboard agents the same way they onboard developers: with shared assumptions, behavior, and clear expectations about how internal systems should be used. ## Advanced ### Does Tessl support monorepos? Yes! Tessl supports monorepo workflows. Run `tessl init` at the monorepo root to create `tessl.json` and configure your coding agent. From there, use `tessl search` to find tiles and `tessl install` to add them. You can run `tessl install` from any subfolder to add tiles relevant to that part of the repo — all installed tiles are tracked in the single `tessl.json` at the root. **Example:** ```sh # Initialize Tessl at the monorepo root tessl init # Search for and install tiles relevant to a subfolder cd backend tessl search fastapi tessl install tessl/pypi-fastapi ``` ## Support & Help ### How can I check if Tessl services are experiencing issues? Visit the [Tessl Status Page](https://tesslstatus.io/) to check the current status of all Tessl services, view any ongoing incidents, and see historical uptime data. For other support options, see [Giving feedback](/support/giving-feedback.md). --- # Agent Instructions: Querying This Documentation If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question. Perform an HTTP GET request on the current page URL with the `ask` query parameter: ``` GET https://docs.tessl.io/support/faqs.md?ask= ``` The question should be specific, self-contained, and written in natural language. The response will contain a direct answer to the question and relevant excerpts and sources from the documentation. Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.