Skills

Create reusable SKILL.md instructions that agents can invoke manually, automatically, or on every turn.

Skills are reusable instruction bundles for LibreChat Agents. A skill is centered on a SKILL.md file: frontmatter describes when the skill should be used, and the markdown body gives the agent the procedure, rules, examples, or references to follow.

Skills are useful for repeatable work such as:

Applying brand or writing guidelines
Following internal review checklists
Running a standard research workflow
Priming a specialized tool workflow
Packaging reusable scripts, references, and assets with an instruction file

Enable Skills

The skills agent capability is enabled by default. Admins can remove it from the agents endpoint capability list to hide Skills from users.

endpoints:
  agents:
    capabilities:
      - 'deferred_tools'
      - 'execute_code'
      - 'file_search'
      - 'web_search'
      - 'artifacts'
      - 'subagents'
      - 'actions'
      - 'context'
      - 'skills'
      - 'tools'
      - 'chain'
      - 'ocr'

Role permissions also control who can use, create, share, and publicly share skills.

Deployment Skills

Admins can ship read-only Skills from the filesystem with DEPLOYMENT_SKILLS_DIR.

DEPLOYMENT_SKILLS_DIR=./skill

The directory defaults to ./skill at the project root. LibreChat loads deployment Skills at startup and exposes them to users with the Skills capability enabled.

Deployment Skills:

Are read-only in the UI
Use deployment as their source
Take precedence over persisted Skills with the same name
Require a LibreChat restart after files are added, removed, or changed

GitHub Skill Sync

Admins can mirror Skills from GitHub repositories with skillSync.github in librechat.yaml.

skillSync:
  github:
    enabled: true
    intervalMinutes: 60
    runOnStartup: true
    sources:
      - id: librechat-skills
        owner: your-org
        repo: your-skills-repo
        ref: main
        paths:
          - skills
        skillDiscoveryDepth: 2
        token: '${GITHUB_SKILLS_TOKEN}'

GitHub Skill Sync:

Scans configured repository paths for SKILL.md
Imports bundled files beside each skill
Stores mirrored Skills with source: "github"
Updates mirrored Skills when the upstream repository changes
Removes mirrored Skills that no longer exist in the configured source
Supports scheduled, startup, and manual admin-triggered runs

Use a GitHub fine-grained personal access token with read-only Contents and Metadata permissions for the selected repository. See Skill Sync Object Structure for all fields, credential options, tenant scoping, and admin sync endpoints.

Create a Skill

Open Skills from the side panel. You can write a skill directly in LibreChat or upload a .md, .zip, or .skill file that contains SKILL.md.

Minimum SKILL.md:

---
name: brand-guidelines
description: Use when writing public-facing content that must follow the company voice and terminology.
---

# Brand Guidelines

Write in a concise, practical tone.
Prefer active voice.
Use product terminology consistently.

Frontmatter

Key	Type	Description	Example
name	String	Stable kebab-case identifier. It must start with a lowercase letter or digit and can contain lowercase letters, digits, and hyphens.	name: brand-guidelines
description	String	The most important trigger text. Describe when the model should use the skill.	description: Use when writing public-facing launch copy.
always-apply	Boolean	Automatically primes the skill into every turn where it is active.	always-apply: true
user-invocable	Boolean	Set to false to hide the skill from manual `$` invocation. Default: true.	user-invocable: false
disable-model-invocation	Boolean	Set to true to exclude the skill from the model-invoked skill catalog. Manual invocation is still allowed unless `user-invocable` is false.	disable-model-invocation: true
allowed-tools	Array/List of Strings	Temporarily unions these tools into the agent effective tool set when the skill is manually or always applied.	allowed-tools: ["execute_code"]

Invocation Modes

Skills can reach an agent in three ways:

Manual: the user types $ in chat and selects a skill from the popover.
Model-invoked: the model chooses a skill from the injected skill catalog and calls the skill tool.
Always apply: the skill is primed into every turn when active.

Manual invocation is explicit user intent. It can use skills that are hidden from model invocation with disable-model-invocation: true, as long as user-invocable is not false.

Agent Scope

Agents must have Skills enabled before they can use the catalog.

If skills_enabled is false or unset on a persisted agent, skills are inactive for that agent.
If skills_enabled is true and no skill allowlist is set, the agent can use the full active catalog visible to the user.
If skills_enabled is true and skills contains specific skill IDs, the agent is narrowed to that list.

This lets admins expose the Skills feature globally while keeping each agent's usable skill set focused.

Active and Shared Skills

Users can toggle skills active or inactive. Owned skills default to active. Shared skills use the admin-configured default until the user overrides them.

Inactive skills are excluded from:

The $ popover
The model-invoked skill catalog
Always-apply priming

Bundled Files

Uploaded skill bundles can include files alongside SKILL.md, such as:

references/...
scripts/...
assets/...

The backend stores those files with the skill. The agent can resolve skill files when the skill is active and in scope.

Authoring tip

Keep description specific. It is the strongest signal for model-invoked skills. A short or vague description will under-trigger.

Skills

On this page