BerriAI

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.

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 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.

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.

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 an AI agent from a live LiteLLM proxy. Ask for the agent_id and confirm before calling DELETE /v1/agents/{agent_id}.

Delete one or more API keys from a live LiteLLM proxy. Ask for the key(s) and confirm before calling POST /key/delete.

Delete an MCP server from a live LiteLLM proxy. Ask for the server_id and confirm before calling DELETE /v1/mcp/server/{server_id}.

Triage a GitHub pull request for BerriAI/litellm and decide whether it is ready for human review. Classifies each failing check as PR-related vs infra/pre-existing, factors in Greptile score and CircleCI presence, and emits a thumbs-up/thumbs-down verdict with a 5-item checklist. Use when summarizing the state of a litellm PR, deciding if it is merge-ready, or triaging CI failures. Triggers on "review this PR", "is this PR ready", "triage litellm PR", or any github.com/BerriAI/litellm/pull/<N> URL.

Iteratively fix a BerriAI/litellm PR until the litellm-bot reviewer returns a 5/5 READY verdict. Posts the PR to the bot (via Slack @-mention or its /chat/api endpoint), parses the merge-confidence card, fixes every blocker the card and drilldown call out, pushes, and re-asks. Use when a contributor wants their PR fully greenlit by the bot before requesting a human review. Triggers on "loop my PR through litellm-bot", "/litellm-loop", "make this PR pass review", or "drive PR <url> to READY".

Karpathy-style senior-engineer pre-merge review for a litellm PR as if it ships to an AI gateway at 10k+ RPS on a large codebase with many flows. Answers whether the change is safe to merge, what unintended consequences could appear under load, and whether scope matches the linked issue. Detects narrow bug-class misses, scope expansion beyond the ticket, dead/unreachable code paths, hot-path perf risk, and sink-not-source fixes. Use after CI triage says READY. Triggers on "production merge review", "safe to merge at scale", "karpathy check", or a BerriAI/litellm PR URL in stdin JSON.

Review a BerriAI/litellm PR for conformance with the repo's documented and de-facto code patterns. Pulls patterns from docs/my-website/docs/ first, then from sibling files in the diff's directories. On conflict, docs win and contradicting code is flagged as tech debt rather than precedent. Use when the user asks "does this PR follow our patterns", "is this idiomatic litellm", or pastes a github.com/BerriAI/litellm/pull/<N> URL with a pattern/convention question. Do NOT use for general PR triage or CI status — that is the litellm-pr-reviewer skill.

Standard procedures for a coding agent — memory hygiene and PR workflow.

Audits all Markdown files in a repository for internal inconsistencies, contradictions, stale CLI commands/flags, and broken cross-references. Returns a structured findings report. Use when asked to check, audit, or verify docs for correctness or consistency.

Scans a GitHub pull request for security vulnerabilities including OWASP Top 10 issues, hardcoded secrets, and dependency CVEs. Returns a structured JSON findings report. Use when asked to review, audit, or scan a PR for security issues.

Knowledge and utilities for creating animated GIFs optimized for Slack. Provides constraints, validation tools, and animation concepts. Use when users request animated GIFs for Slack like "make me a GIF of X doing Y for Slack."