Updated 5mo ago
by BerriAI
litellm-skills
Agent Skills for managing live LiteLLM proxy deployments — users, teams, keys, orgs, models, MCP servers, agents
99 GitHub stars (99)
+5 in 16 days
| Period | New stars |
|---|---|
| Oct 1 | 0 |
| Oct 2 | 0 |
| Oct 3 | 0 |
| Oct 4 | 0 |
| Oct 5 | +2 |
| Oct 6 | 0 |
| Oct 7 | 0 |
| Oct 8 | 0 |
| Oct 9 | +1 |
| Oct 10 | +1 |
| Oct 11 | 0 |
| Oct 12 | 0 |
| Oct 13 | 0 |
| Oct 14 | 0 |
| Oct 15 | +1 |
| Oct 16 | 0 |
- 21 skills (21 skills found in its SKILL.md files)
- 17 forks (17 forks)
- 5mo ago last update (Last updated 5mo ago)
Install
Skills CLI
npx skills add BerriAI/litellm-skills
Asks which skills and agents to install. Just one: npx skills add BerriAI/litellm-skills --skill add-agent — add -g for every project.
Claude Code
git clone https://github.com/BerriAI/litellm-skillscp -r "litellm-skills/add-agent" ~/.claude/skills/
Copies the add-agent skill into ~/.claude/skills/ for every project (use .claude/skills/ for one project). Repeat for the other skills listed below.
Plugin
/plugin marketplace add BerriAI/litellm-skills
Run inside Claude Code if the repository ships a plugin marketplace, then pick plugins from /plugin.
Skills can run code on your machine — read the SKILL.md first.
What it does
In the author's own words, from each skill's SKILL.md.
-
add-agent
Create a new AI agent on a live LiteLLM proxy. Asks for agent name, the underlying model, and optional MCP server access, then calls POST /v1/agents.
add-agent/SKILL.md on GitHub (opens in a new tab) -
add-key
Generate a new API key on a live LiteLLM proxy. Asks for alias, scope (user/team), budget, models, and expiry, then calls POST /key/generate. Use when the user wants to create, generate, or provision an API key on a LiteLLM proxy instance.
add-key/SKILL.md on GitHub (opens in a new tab) -
add-mcp
Register a new MCP server on a live LiteLLM proxy. Asks for the server name, transport type, URL, and optional auth, then calls POST /v1/mcp/server.
add-mcp/SKILL.md on GitHub (opens in a new tab) -
add-model
Add a new model to a live LiteLLM proxy. Walks the user through picking a provider, entering the deployment name and credentials, calls POST /model/new, then test-calls the model to confirm it routes correctly. Use when the user wants to add, register, deploy, or configure a new model on a LiteLLM proxy instance.
add-model/SKILL.md on GitHub (opens in a new tab) -
add-org
Create a new organization on a live LiteLLM proxy. Asks for org name, budget, and allowed models, then calls POST /organization/new.
add-org/SKILL.md on GitHub (opens in a new tab) -
add-team
Create a new team on a live LiteLLM proxy. Asks for team name, budget, and allowed models, then calls POST /team/new and shows the result. Use when the user wants to create a new team, set up team budgets, or configure model access for a team on the proxy.
add-team/SKILL.md on GitHub (opens in a new tab) -
add-user
Create a new user on a live LiteLLM proxy. Asks for email, role, and optional budget/model limits, then calls POST /user/new and shows the result.
add-user/SKILL.md on GitHub (opens in a new tab) -
delete-agent
Delete an AI agent from a live LiteLLM proxy. Ask for the agent_id and confirm before calling DELETE /v1/agents/{agent_id}.
delete-agent/SKILL.md on GitHub (opens in a new tab) -
delete-key
Delete one or more API keys from a live LiteLLM proxy. Ask for the key(s) and confirm before calling POST /key/delete.
delete-key/SKILL.md on GitHub (opens in a new tab) -
delete-mcp
Delete an MCP server from a live LiteLLM proxy. Ask for the server_id and confirm before calling DELETE /v1/mcp/server/{server_id}.
delete-mcp/SKILL.md on GitHub (opens in a new tab) -
delete-model
Delete a model from a live LiteLLM proxy. Asks for the model name or model_id and confirms before calling POST /model/delete. Use when the user wants to remove, delete, or unregister a model from a LiteLLM proxy instance.
delete-model/SKILL.md on GitHub (opens in a new tab) -
delete-org
Delete one or more organizations from a live LiteLLM proxy. Ask for the organization_id(s) and confirm before calling DELETE /organization/delete.
delete-org/SKILL.md on GitHub (opens in a new tab) -
delete-team
Delete one or more teams from a live LiteLLM proxy. Ask for the team_id(s) and confirm before calling POST /team/delete.
delete-team/SKILL.md on GitHub (opens in a new tab) -
delete-user
Delete one or more users from a live LiteLLM proxy. Ask for the user_id(s) and confirm before calling POST /user/delete.
delete-user/SKILL.md on GitHub (opens in a new tab) -
update-agent
Update an existing AI agent on a live LiteLLM proxy. Ask for the agent_id and what to change (model, description, MCP servers), then call PATCH /v1/agents/{agent_id}.
update-agent/SKILL.md on GitHub (opens in a new tab) -
update-key
Update an existing API key on a live LiteLLM proxy. Ask for the key and what to change (budget, models, expiry), then call POST /key/update.
update-key/SKILL.md on GitHub (opens in a new tab) -
update-mcp
Update an existing MCP server on a live LiteLLM proxy. Ask for the server_id and what to change (URL, auth, description), then call PUT /v1/mcp/server.
update-mcp/SKILL.md on GitHub (opens in a new tab) -
update-model
Update an existing model on a live LiteLLM proxy. Ask for the model_id and what to change (API key, base URL, etc.), then call POST /model/update.
update-model/SKILL.md on GitHub (opens in a new tab) -
update-team
Update an existing team on a live LiteLLM proxy. Ask for the team_id and what to change (budget, models, limits), then call POST /team/update.
update-team/SKILL.md on GitHub (opens in a new tab) -
update-user
Update an existing user on a live LiteLLM proxy. Ask for the user_id and what to change (budget, role, models, etc.), then call POST /user/update.
update-user/SKILL.md on GitHub (opens in a new tab) -
view-usage
Query spend and token activity on a live LiteLLM proxy. Shows daily usage broken down by user, team, org, tag, job, or model. Use when the user wants to see costs, token counts, request volume, or job-level attribution for a given date range.
view-usage/SKILL.md on GitHub (opens in a new tab)
No skill matches that filter.
Review before you install
A skill is a set of instructions and scripts your agent will follow, and it can run code on your machine. Read the SKILL.md and any scripts first — this listing is not a security review.