Skip to main content
Skills let you teach Lovable how to handle recurring tasks. Define a skill once at the workspace level, and Lovable can use it across every project in that workspace. Each skill is a short, named playbook with:
  • a name,
  • a description that tells Lovable when to use it,
  • and markdown instructions that Lovable follows when the skill applies.
You can invoke the skill as a / command paired with your prompt, or let Lovable apply it automatically when the task matches. Skills are portable markdown-based files, so you can inspect exactly what Lovable is being told, share them with teammates, import them from GitHub or ZIP, and improve them over time.

​
Skills vs. instructions

Skills and instructions complement each other.
  • Instructions are always included in context. Use them for rules and conventions that apply to everything Lovable does, such as coding standards, brand guidelines, or your project’s domain terminology.
  • Skills are loaded on demand when the request matches. Use them for instructions that only matter for specific kinds of tasks, such as running a release checklist, drafting a customer reply, or producing a particular kind of content.
If an instruction is relevant on every message, put it in workspace instructions. If it is only relevant when a specific topic comes up, make it a skill.
Skills are loaded only when relevant, so you can maintain many focused skills without loading them all into every conversation.

​
Types of skills

Skills come in three types. They differ in who manages them and who can use them. Custom workspace skills are the skills your team adds, shared with every project in the workspace. Skills you build in the project chat, write yourself, import from GitHub, or upload as a ZIP appear here. Skills built by Lovable are the built-in workspace skills, which every workspace has from the start. They cover common tasks, such as accessibility checks, redesigns, SEO reviews, skill creation, and video creation. Goal, which sets a message as a goal, is listed here too. You can use them when relevant, but you cannot edit, delete, or download them. Personal skills are your own, private to you in one workspace. You add them yourself, with no admin involved, and no one else can see or use them. Custom workspace skills and skills built by Lovable follow the same permission rules, and Workspace settings → Skills shows them in one list. The list opens on Workspace, which shows the custom ones, and the filter beside the search box switches it to Built-in or All skills. Personal skills are not in that list, not even under All skills. Custom workspace skills and your own personal skills appear in the Skills list when you type / in a project chat. Lovable can also apply one automatically when your request matches it.

​
What skills are for

Skills work best for repeatable, task-specific workflows. Use them when you want Lovable to handle the same kind of task the same way each time. Common examples include:
  • Launch checks: pre-ship checklists, release readiness reviews, and go/no-go reviews
  • Recurring content: release notes, changelog entries, support replies, and marketing copy
  • Review playbooks: landing-page reviews, copy reviews, accessibility passes, and search engine optimization reviews
  • Internal processes: onboarding flow reviews, quality assurance passes, billing setup, and partner handoff steps
  • Task-specific style guides: tone of voice, brand persona, or formatting rules for a particular kind of content
  • Reusable team workflows: research routines, document templates, partner integrations, or other repeated team processes
Because skills are shared across the workspace, they are especially useful when you want every project to follow the same process.

​
Role-based access for skills

Access to the skills your workspace shares, both the ones your team adds and the ones built by Lovable, follows your workspace role. Personal skills are the exception: you add your own, with no admin involved. On Enterprise plans, custom workspace skill changes are recorded in your workspace audit log.

​
Add a custom workspace skill

Workspace owners and admins can add custom workspace skills in five ways. Four options are available from Workspace settings → Skills → Add, and one starts from a project chat after Lovable does something you want to reuse.

​
Build with Lovable

Choose Add → Build with Lovable to start a guided skill-building conversation. Lovable opens the dashboard with a starter prompt:
Send the prompt, then answer Lovable’s questions about what the skill should do, when it should trigger, and what instructions it should follow. Lovable drafts the skill for you. When you approve the draft, the skill is published to your workspace.

​
Write manually

Choose Add → Write manually to write a skill from scratch. The form has three fields:
  • Name: a short, permanent ID like launch-checklist or support-reply. Use lowercase letters, numbers, and hyphens only.
  • Description: the trigger Lovable uses to decide when to load the skill. Start with “Use when…” and describe the skill’s scope and boundaries.
  • Content: the instructions Lovable follows once the skill is loaded, such as steps, constraints, examples, and the expected output.
Click Add skill to publish it. The skill is available across the workspace immediately. For field requirements, naming rules, and description examples, see Anatomy of a skill.

​
Import from GitHub

Choose Add → Import from GitHub and paste a public GitHub repository URL. A skill is a directory containing a SKILL.md file, and the URL tells Lovable which directory to take. Two forms work:
  • Whole repository, https://github.com/owner/repo. Use this when the repository has one skill, with SKILL.md at the root.
  • Subdirectory, https://github.com/owner/repo/tree/main/launch-checklist. Use this when one repository has several skills. The directory must contain SKILL.md directly, and any branch works in place of main. A direct file URL also works, such as https://github.com/owner/repo/blob/main/launch-checklist/SKILL.md, and Lovable imports the parent directory that contains SKILL.md.
If you are not sure which URL you need, open the skill’s directory on GitHub and copy the address from your browser. Lovable downloads the repository, validates it, and adds the skill to your workspace. The repository must be public, and a private repository and a mistyped URL fail the same way.

​
Upload a ZIP

Choose Add → Upload ZIP, and drag in or browse for a .zip or .skill file. The archive must contain a SKILL.md file either at the root or inside one wrapping folder. Any bundled files referenced by the skill should sit alongside SKILL.md in the same directory. The file you upload can be up to 50 MB, compressed. After Lovable unpacks it, the skill itself can include up to 200 files and 10 MB, with each file up to 1 MB. macOS metadata files, such as __MACOSX/ and .DS_Store, are ignored at the root. Example: importing a skill from Claude Skills in Lovable use the same SKILL.md shape as Anthropic’s Claude and any other tool that follows the Agent Skills convention. If you already built a skill in Claude, export it as a .skill or .zip file, then upload it in Lovable from Workspace settings → Skills → Add → Upload ZIP. Lovable validates the archive and publishes the skill to your workspace with its name, description, instructions, and bundled files intact. From there, it behaves like any other custom workspace skill. This works in the other direction too: download any custom workspace skill from Lovable as a .zip, then upload it into another tool that supports the same SKILL.md shape.

​
Save from a project chat

You can turn a successful project chat interaction into a reusable skill without leaving the project. After Lovable completes a task the way you want, say “save that as a skill” and describe when the skill should apply. Lovable drafts the skill, including a name, description, and instructions, then shows it in the project chat for you to review. When you approve the draft, the skill is published to your workspace.

​
Use a skill

Lovable can use skills in two ways: automatically, or when you invoke one directly.

​
Let Lovable choose automatically

When your request matches a skill’s description, Lovable can apply that skill automatically. You do not need to do anything special. Just describe what you want. You can keep many skills in the same workspace. Lovable only loads the skills that seem relevant to the current request. A launch-checklist skill, for example, only applies when someone tells Lovable they are about to ship. It does not affect unrelated work.
If a workspace admin has disabled automatic use for a skill, Lovable will not apply it automatically, even when the task matches. You can still invoke the skill yourself with a slash command (/skill-name). See Enable or disable automatic use for details.

​
Invoke a skill directly

Type / in the chat input to open the Skills list, choose a skill, and then continue typing your request. You can also open the same list from the + button next to the chat input, under Add context → Skills. The skill appears as a tag in your message, telling Lovable which instructions to apply. Think of the skill as the how and your prompt as the what. For example, with a launch-checklist skill in your workspace, you could send:
The Skills list filters as you type. On desktop, a panel next to the list shows the skill’s instructions, or its description for skills built by Lovable, so you can confirm you are choosing the right one. After you send the message, the skill appears as a tag in the project chat. Hover over the tag to see its description, click it to open the full skill preview, or use the pencil icon in the preview to open that skill’s settings.
Skills with automatic use disabled still appear in the Skills list and can be invoked directly with /skill-name. When automatic use is disabled, Lovable stops applying the skill on its own. The skill stays visible, and you can still invoke it yourself.

​
Manage custom workspace skills

Use Workspace settings → Skills to manage custom workspace skills. Project settings → Skills shows the same list while you work in a project, because a workspace has one set of skills that every project in it uses. The available actions depend on your role. See Role-based access for skills.

​
Edit or delete a custom workspace skill

Go to Workspace settings → Skills to see every skill in your workspace. Open a custom workspace skill to edit its description or instructions, or delete it if you no longer need it. Deleting a skill removes it from the workspace, so no project in that workspace can use it again.

​
Download a custom workspace skill

Open any custom workspace skill in Workspace settings → Skills and click Download to export the full skill package as a .zip. Use downloads to back up a skill, move it to another workspace, share it with a teammate to edit offline, or upload it into another tool that supports the same SKILL.md shape, such as Claude. Personal skills cannot be downloaded.

​
Enable or disable automatic use

Every custom workspace skill has Use automatically enabled by default. When automatic use is enabled, Lovable can apply the skill automatically whenever the task matches, and you can also invoke it yourself with a slash command (/skill-name). When automatic use is disabled, Lovable does not apply the skill on its own in any project, even when the task matches. The skill stays available to the workspace. It still appears in the Skills list when you type /, and you can invoke it yourself with a slash command. Workspace owners and admins can enable or disable automatic use for a skill from Workspace settings → Skills, or from Project settings → Skills while working in a project. The setting applies across the entire workspace. Personal skills have no such setting, and no one else can disable one.

​
Personal skills

Personal skills are your own, and each workspace you belong to has a separate set. Lovable applies them in every project you open in that workspace. Your teammates never see them, you do not need to be an admin, and they are available on all plans. You find them in Account settings → Personal skills. Choose the workspace at the top of the page before you add anything. A skill you add in one workspace does not appear in your other workspaces, and a workspace you join starts with none.

​
Add a personal skill

Select Add skill and fill in the same three fields as a custom workspace skill: a name, a description, and the instructions. To bring in a skill someone else wrote, open the menu beside Add skill and choose Import skills. You can import from a public GitHub repository, or from a .zip or .skill file. To change or delete a skill, select it in the list. A personal skill has the same parts, naming rules, and limits as a custom workspace skill. An imported one keeps its bundled files. See Anatomy of a skill.

​
Ask Lovable to write a personal skill

Ask Lovable in a project chat to create, change, or delete a personal skill, and Lovable edits your set for you. This works in Build mode. In Chat mode and Plan mode Lovable reads your personal skills but does not change them.
Lovable saves the change without asking you to approve it, and the skill applies from your next message.
Deleting a personal skill cannot be undone, whether you delete it yourself or ask Lovable to. Personal skills cannot be downloaded, so there is no copy to restore from.

​
How personal skills differ

Personal skills work like custom workspace skills, with these differences.
  • Lovable applies a personal skill whenever a task matches it, and you can invoke one by typing / and its name. Personal skills have no setting for automatic use, so workspace admins and owners cannot switch one off.
  • When skill names conflict, Lovable prioritizes personal skills over workspace skills.
  • You cannot download a personal skill. Custom workspace skills offer Download and personal skills do not, so moving one to another workspace means copying its text across yourself.

​
Anatomy of a skill

Each skill has three required parts.
  • Name: a short, permanent identifier for the skill, between 1 and 64 characters. Use lowercase letters, numbers, and hyphens only, for example, launch-checklist, release-notes, or support-reply. Names cannot start or end with a hyphen, and cannot contain consecutive hyphens. The name goal is reserved for the built-in Goal command. The name cannot be changed after creation. To rename a skill, delete it and create a new one.
  • Description: a short sentence that tells Lovable when to use the skill. Start with “Use when…” and describe the trigger as concretely as possible. The description is the main signal Lovable uses to decide whether to load the skill for a message.
  • Instructions: the markdown body Lovable follows once the skill is loaded. Include the steps, constraints, examples, edge cases, and output format Lovable should follow.
A good rule of thumb is to write the instructions you would give a new teammate doing the task for the first time: what to do, what to avoid, what to watch for, and what format to return. The full SKILL.md file can be up to 100,000 characters.

​
Bundled files

A skill can also include bundled files. These are optional extra files that travel with the skill. Use bundled files for longer references, templates, or small scripts that the instructions point to, such as reference.md. Bundled files appear in the Bundled files list when you expand the skill, and they are included when you download or import the skill. Skills authored in the project chat usually do not need bundled files. They are most common for skills imported from GitHub or a ZIP. Each bundled file can be up to 1 MB. A skill can include up to 200 files and up to 10 MB total across all files.

​
Write clear skill descriptions

A well-written description is the most important part of a skill. The description tells Lovable when to load the skill. If the description is vague, Lovable may not load the skill when you expect it to, or may load it for unrelated tasks. Good descriptions define both when the skill should apply and when it should not. Clear boundaries help Lovable load the right skill consistently without pulling it into unrelated tasks. Too vague
This description does not clearly tell Lovable when to use the skill, what kind of SEO task it applies to, or what it should actually do. Specific and scoped
This description names:
  • the trigger (auditing an existing page),
  • the scope (checking metadata, headings, internal links),
  • and the boundary (not for writing new copy).
Well-scoped descriptions make skills load more consistently and reduce conflicts between similar skills.

​
Example skill

Here is a complete example of a pre-launch checklist skill that runs whenever you tell Lovable you are about to ship: Name
Description
Instructions
This skill could also include bundled reference files alongside SKILL.md. For example, the launch checklist could keep deeper search engine optimization and accessibility verification steps in separate bundled files instead of putting everything directly into SKILL.md.

​
Best practices

  • Lead with the trigger. Start the description with “Use when…” and describe the request as concretely as you can. The description is how Lovable decides whether to load the skill.
  • Give each skill one job. A skill that tries to cover too much may load in the wrong situations or fail to give Lovable clear guidance. Split broad guidance into focused skills, and let each one own a specific task.
  • Include boundaries and “avoid” sections. Telling Lovable what not to do is often as important as telling it what to do. Strong skills define both the intended behavior and the behaviors to avoid.
  • Put always-on rules in instructions instead. If a rule should apply to every message, it belongs in workspace instructions. Skills are for behavior that only matters in specific situations.
  • Write the instructions like a short playbook. Use short sections, bullet points, and direct instructions. Skills become part of the context Lovable reads, so shorter, focused instructions are easier to follow.
  • Show, do not just tell. Where helpful, include concrete values, example copy, or example outputs. Lovable follows specific instructions more reliably than abstract ones.
  • Review and prune. As your workspace grows, retire skills that are no longer needed. A skill with stale or incorrect instructions is worse than no skill at all.

​
FAQ

The full SKILL.md, including the description and instructions, can be up to 100,000 characters. Names are limited to 64 characters. A skill can also include bundled files alongside SKILL.md: each file can be up to 1 MB, and a skill can contain up to 200 files totaling 10 MB. Custom workspace skills and personal skills have the same limits.
No. The name is set when the skill is created. To rename a skill, delete it and create a new one with the desired name. The description and instructions can always be edited.
Yes. Every skill defined in a workspace is available to every project in that workspace, and your personal skills are available to every project you open in that workspace. Skills are not available in Chats. Workspace owners and admins can disable automatic use for a custom workspace skill without deleting it, so Lovable will not apply it on its own but workspace members can still invoke it themselves with a slash command (/skill-name).
Yes, for a custom workspace skill. Open Workspace settings → Skills or Project settings → Skills and switch off Use automatically on the skill’s row. This applies across the workspace. Lovable will not apply the skill on its own in any project, even when the task matches, but workspace members can still invoke it themselves with a slash command (/skill-name). Re-enable automatic use at any time from the same place. Personal skills have no such setting.
Lovable reads the description of each skill and decides whether the skill is relevant to your current request. Clear, specific descriptions produce more reliable behavior. If a skill is not triggering when you expect, rewrite the description to be more explicit about the kind of request it applies to.
Instructions are always included as background context for Lovable. Skills are loaded on demand when the request matches the skill’s description. Use instructions for rules that apply to every message, and skills for instructions that only matter for specific kinds of tasks.
Yes. Lovable can use more than one skill in a single message. Keep skills focused so that overlapping skills combine cleanly rather than contradicting each other.
There is no additional skill-specific cost. Credits are tied to the message that uses a skill, not to the skill itself.
  • Creating a skill from the project chat (Build with Lovable or “save that as a skill”): is priced like any other message in the project chat.
  • Adding a skill from Workspace settings (Write manually, Import from GitHub, or Upload ZIP): free. Settings actions do not consume credits.
  • Using a skill: no extra cost on top of the message. The message is priced as build usage, based on its complexity. A skill may indirectly affect cost if the instructions it loads lead Lovable to do more work.
Your personal skills are separate in each workspace, so a skill you added in one does not appear in projects that belong to another. Open Account settings → Personal skills, switch the workspace at the top of the page, and check whether the skill is in the workspace that project belongs to.
No. Personal skills are private to you in the workspace you set them in, and workspace admins and owners cannot see, change, or disable them. Your teammates see only the skills your workspace shares.
No. Deleting a personal skill cannot be undone, whether you delete it yourself or ask Lovable to. Personal skills cannot be downloaded either, so keep a copy of the skill’s text elsewhere if you may want it again.
Custom workspace skills are stored in your workspace. Personal skills are stored separately for you in each workspace, and you manage them in Account settings → Personal skills. On Enterprise plans, every edit and deletion of a custom workspace skill is also recorded in the workspace audit log.
Yes, for a custom workspace skill. Download it as a .zip from one workspace, then import the ZIP into another. The imported skill arrives with the same name, description, and contents. Personal skills cannot be downloaded, and each set stays in the workspace you created it in.
No. Only custom workspace skills can be downloaded. Skills built by Lovable are read-only, and Lovable maintains them.