Updated 2mo ago
by doggy8088
litellm-skills
LiteLLM 教學 Agent Skills，包含 SDK 基礎、Proxy Gateway、Routing、Cost Governance、Observability、Guardrails 及 MCP 等教學實作引導。
25 GitHub stars (25)
+1 in 16 days
| Period | New stars |
|---|---|
| Oct 1 | 0 |
| Oct 2 | 0 |
| Oct 3 | 0 |
| Oct 4 | 0 |
| Oct 5 | 0 |
| Oct 6 | 0 |
| Oct 7 | 0 |
| Oct 8 | 0 |
| Oct 9 | 0 |
| Oct 10 | +1 |
| Oct 11 | 0 |
| Oct 12 | 0 |
| Oct 13 | 0 |
| Oct 14 | 0 |
| Oct 15 | 0 |
| Oct 16 | 0 |
- 7 skills (7 skills found in its SKILL.md files)
- 13 forks (13 forks)
- 2mo ago last update (Last updated 2mo ago)
Install
Skills CLI
npx skills add doggy8088/litellm-skills
Asks which skills and agents to install. Just one: npx skills add doggy8088/litellm-skills --skill litellm-cost-governance — add -g for every project.
Claude Code
git clone https://github.com/doggy8088/litellm-skillscp -r "litellm-skills/litellm-cost-governance" ~/.claude/skills/
Copies the litellm-cost-governance skill into ~/.claude/skills/ for every project (use .claude/skills/ for one project). Repeat for the other skills listed below.
Plugin
/plugin marketplace add doggy8088/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.
-
litellm-cost-governance
設計或審查 LiteLLM virtual keys、spend tracking、budgets、rate limits、request tags 與 provider budget routing。當任務涉及用量限制、模型 allowlist、成本歸因或報表時使用；一般 Proxy 拓樸與觀測平台設定改用對應專門技能。
litellm-cost-governance/SKILL.md on GitHub (opens in a new tab) -
litellm-guardrails-safety
設定或審查 LiteLLM 內容安全、PII masking、prompt injection、tool permission、MCP guardrails 與 call hooks。當任務需要修改、拒絕或限制 LLM／tool／MCP 請求時使用；MCP server 註冊與一般 virtual-key 預算改用對應專門技能。
litellm-guardrails-safety/SKILL.md on GitHub (opens in a new tab) -
litellm-mcp-skills-gateway
設計或審查 LiteLLM MCP Gateway、MCP permissions、toolsets、MCP REST API、Skills Gateway 與官方管理 skills。當任務要註冊工具來源、授權 agent 工具或發布 skills 時使用；一般 tool calling 與 guardrail 規則分別搭配 SDK 或安全技能。
litellm-mcp-skills-gateway/SKILL.md on GitHub (opens in a new tab) -
litellm-observability
設定或審查 LiteLLM callbacks、logging、OpenTelemetry、request correlation、spend logs 與故障診斷。當任務要追蹤延遲、tokens、cost、provider、fallback 或 guardrail 事件時使用；權限政策與 guardrail 規則改用安全技能。
litellm-observability/SKILL.md on GitHub (opens in a new tab) -
litellm-proxy-gateway
建立或審查 LiteLLM Proxy 的基礎拓樸、model alias、config.yaml、啟動方式與 OpenAI-compatible client。當任務是架設集中式模型入口或遷移既有 OpenAI client 時使用；成本治理、觀測、安全、可靠性與 MCP 細節必須搭配對應專門技能。
litellm-proxy-gateway/SKILL.md on GitHub (opens in a new tab) -
litellm-routing-reliability
設計或審查 LiteLLM Router、load balancing、retry、timeout、fallback、rate-limit routing 與 health checks。當任務要求多 deployment、跨 provider 備援或可靠性測試時使用；預算政策交由成本治理技能，trace 後端交由觀測技能。
litellm-routing-reliability/SKILL.md on GitHub (opens in a new tab) -
litellm-sdk-basics
使用 LiteLLM Python SDK 建立或審查 completion、streaming、structured output、tool calling、Responses API 與基礎成本追蹤。當任務是在 Python 程式內直接呼叫 LiteLLM 而非管理 Proxy 時使用；Proxy、virtual key、集中式預算或 gateway 維運改用對應專門技能。
litellm-sdk-basics/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.
Similar skills
-
superpowersby obra An agentic skills framework & software development methodology that works.
-
skillsby mattpocock Skills for Real Engineers. Straight from my .agents directory.
-
ECCby affaan-m The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Cod…
-
reaby morluto Reverse engineer anything with agents, from app behavior down to native binaries.
-
andrej-karpathy-skillsby multica-ai A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls.
-
skillsby anthropics Public repository for Agent Skills