Skills

Step-by-step guides your agent loads on demand, built in or added by you

A skill is a reusable guide that tells an agent how to do a particular kind of task well: how to build a spreadsheet in the virtual machine, how to write in your brand voice, how to run a monthly report the way your team wants it. Skills stay out of the way until they are needed. The agent sees a short catalog of the skills available to it, and loads the full guide only when a task calls for it, so long procedures don’t crowd its instructions or cost tokens on every turn.

Skills use the open Agent Skills format, the same one used by Claude and a growing set of other tools. A skill is a folder with a SKILL.md file that starts with a short header giving the skill’s name and when to use it, followed by the instructions themselves. It can also bundle supporting files such as reference documents, templates and scripts, which the agent reads on demand.

In Abundly, the skills you add are ordinary documents in a folder called skills, so they get everything documents have: version history, the document editor and a place on the Docs page. You can add a skill to a single agent, or share it with every agent in a team or in the whole workspace.

The Skills tab

Open Capabilities → Skills on an agent to see everything it can load, in up to four groups:

• Added to this agent are the skills you or a colleague added to this agent alone.
• Shared with the team are skills in the team’s documents. Every agent in the team gets them. This group appears when the agent belongs to a team.
• Shared with the workspace are skills in the workspace’s documents. Every agent in the workspace gets them.
• Built-in skills come with the platform. Some are general; others belong to a capability, such as the virtual machine or Slack, and appear here once that capability is enabled. The card is tagged with the capability it came with.

Click a built-in skill to read it. Click any other skill to open it in the document editor, where you can change its text, its description and its name. Editing a team or workspace skill changes it for every agent that uses it. Use the switch on a card to turn a skill off for this agent: the agent will neither see it in its catalog nor be able to load it. For a team or workspace skill, its file is hidden from the agent too, so it doesn’t turn up when the agent searches or browses the shared documents. This is useful when a skill pulls the agent in a direction you don’t want for a particular job.

The switch on an agent only affects that agent. A skill turned off for the whole team or workspace shows as unavailable here, with the reason, and can only be turned back on where it was turned off.

Adding skills

To add a skill to the agent itself, you need Edit access to the agent. To add one to the team or the workspace, you need write access to that team’s or workspace’s documents. Click Add next to the group the skill should go in. You can write one, upload a file, or install a ready-made skill from a link.

Install from a link takes a link to the skill. Any of these work:

• A folder on GitHub that contains a SKILL.md, for example a skill in the Anthropic skills repository or in your own repository. Supporting files in the folder are included.
• A direct link to a SKILL.md file.
• A link to a .skill or .zip archive of the skill folder.

Upload a file takes a .skill or .zip archive, or a single SKILL.md, from your computer. Skills exported from Claude use the .skill format and can be uploaded as they are.

Write one opens the document editor on a new file in that group’s skills folder, so you can paste a skill you have or write a short one on the spot.

For imports, the skill’s name and description come from the SKILL.md header. If the header is incomplete, the platform derives them from the file and tells you what it used. The header is only used at import: afterwards the document’s name and description are what count. Binary files in a skill, such as images, are left out; text files such as reference notes and scripts come along.

Managing skills for a workspace or team

Workspace and team admins manage skills for many agents at once under Capabilities (in Management): pick the workspace, a team or personal agents, and open the Skills tab. A team’s Settings tab links straight there. On the Skills tab you can:

• Add, open, remove and turn on or off the workspace’s or the team’s own skills. Turning one off hides it from every agent there, file included, the same as hiding it on the Documents tab. Who can do this follows who can edit that team’s or workspace’s documents.
• On a team, or for personal agents, turn a workspace skill off for just those agents. It’s hidden from them, file included, while the rest of the workspace keeps it.
• Turn built-in skills off for every agent there, the same way you make a capability unavailable.

Skills are on by default and can only be turned off, like capability availability: a skill the workspace turns off is off in every team, and a team can only turn things off for its own agents. An agent’s own switch comes last. Cards show how many agents, or which teams, have turned a skill off.

Use a skill for steps the agents should follow when a task calls for it, and documents for reference material they look things up in. To turn an existing workspace or team document into a skill, move it into the skills folder on that workspace’s or team’s Documents tab.

Skills are documents

Every skill lives in a folder called skills at the top of the agent’s, the team’s or the workspace’s documents. The layout is the same on all three levels. Anything placed directly in that folder is a skill:

• A sub-folder that contains a SKILL.md, plus any supporting files. This is what adding from a link or uploading creates when the skill brings files along.
• A single file, usually markdown, that is the guide itself. This is what writing one creates, and what an import creates for a skill without supporting files.

Name the document whatever you like; the agent loads it by a short id derived from the name. The document’s description is what the agent reads to decide whether the skill applies, so keep it specific about both what the skill does and when to use it. Because these are documents, you can also create a skill from the Docs page by adding a file or folder to a skills folder, move one between agents or up to the team or workspace, or protect an agent’s skill like instructions. A sub-folder without a SKILL.md is not a skill yet.

For an agent’s own skill, off means hidden from the agent. The on/off switch on the Skills tab hides or shows the skill, the same as its agent visibility setting on the Docs page. A team or workspace skill works the same way: turned off on the Capabilities page or hidden on the Documents tab, it is off for every agent there. Hiding a skill’s SKILL.md also turns the skill off. Hiding a supporting file leaves the skill on, but removes that file from the skill. Hiding the skills folder itself turns off every skill in it, and you can’t turn one back on until the folder is visible again.

When two skills have the same id, the most specific one wins: the agent’s own skill replaces a team skill, a team skill replaces a workspace skill, and any of them replaces a built-in skill. The replaced card shows a “Replaced” badge, and the agent loads the other one instead. This is how you tailor a shared or built-in guide to your own way of working.

Once added, the skill is on and listed in the agent’s catalog right away. There is no need to change the agent’s instructions, though it often helps to mention in the instructions when the agent should reach for a skill.

A skill is a set of instructions the agent will follow. Read a skill from a third party before you add it, just as you would review a document you hand to a new colleague, and only take skills from sources you trust.

How the agent uses skills

In every conversation the agent sees a one-line summary of each available skill. When a task matches one, it loads the full guide, and any supporting file it needs, and follows it. Agents with the Shell capability, which lets an agent work with its documents using shell commands, also see every skill as a file: built-in ones and their own under ~/documents/skills/, and shared ones in the skills folder of the team’s and workspace’s documents.

If you want the agent to always follow a guide rather than load it on demand, put the guide in its instructions or in a protected document instead. Skills are for procedures that only matter some of the time.

Writing a skill

A minimal SKILL.md:

---
name: weekly-report
description: How to compile the weekly sales report. Use when asked for the weekly report or sales summary.
---

# Weekly report

1. Pull last week's orders from the CRM.
2. Group by region and compare with the previous week.
3. Write a short summary with the three biggest changes, then the table.

The description matters most: it is what the agent reads to decide whether the skill applies, so say both what the skill does and when to use it. Keep SKILL.md focused on the procedure and move long reference material into separate files in the folder; the agent loads those only when the guide points to them. When you write a skill directly in Abundly you can skip the header and fill in the document’s description instead.