SGLang Structured Serving
Orchestra-Research/AI-Research-SKILLs
Covers serving LLMs with SGLang, whose RadixAttention reuses cached prefixes, and constraining output to JSON, regex or grammar for agent and tool-calling workloads.
A skill your agent uses for direct LiteLLM Python SDK work: chat/text completions, async calls, streaming, embeddings, structured outputs, tools, token/cost checks, caching, callbacks, import/smoke…
Install SDK Core
$ npx skills add VectorSpaceLab/AREX-Skill --skill sdk-core -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install VectorSpaceLab/AREX-Skill sdk-core --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/VectorSpaceLab/AREX-Skill.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/repositories/repo-skills/litellm/sub-skills/sdk-core .claude/skills/sdk-core && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "sdk-core" agent skill from https://github.com/VectorSpaceLab/AREX-Skill/tree/main/skills/repositories/repo-skills/litellm/sub-skills/sdk-core into .claude/skills/sdk-core/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "sdk-core", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/VectorSpaceLab/AREX-Skill/tree/main/skills/repositories/repo-skills/litellm/sub-skills/sdk-coreType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add VectorSpaceLab/AREX-Skill --skill sdk-core -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install VectorSpaceLab/AREX-Skill sdk-core --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/VectorSpaceLab/AREX-Skill.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/repositories/repo-skills/litellm/sub-skills/sdk-core .agents/skills/sdk-core && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "sdk-core" agent skill from https://github.com/VectorSpaceLab/AREX-Skill/tree/main/skills/repositories/repo-skills/litellm/sub-skills/sdk-core into .agents/skills/sdk-core/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "sdk-core", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add VectorSpaceLab/AREX-Skill --skill sdk-core -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install VectorSpaceLab/AREX-Skill sdk-core --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/VectorSpaceLab/AREX-Skill.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/repositories/repo-skills/litellm/sub-skills/sdk-core .cursor/skills/sdk-core && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "sdk-core" agent skill from https://github.com/VectorSpaceLab/AREX-Skill/tree/main/skills/repositories/repo-skills/litellm/sub-skills/sdk-core into .cursor/skills/sdk-core/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "sdk-core", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/VectorSpaceLab/AREX-Skill.git --path skills/repositories/repo-skills/litellm/sub-skills/sdk-core--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add VectorSpaceLab/AREX-Skill --skill sdk-core -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install VectorSpaceLab/AREX-Skill sdk-core --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/VectorSpaceLab/AREX-Skill.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/repositories/repo-skills/litellm/sub-skills/sdk-core .gemini/skills/sdk-core && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "sdk-core" agent skill from https://github.com/VectorSpaceLab/AREX-Skill/tree/main/skills/repositories/repo-skills/litellm/sub-skills/sdk-core into .gemini/skills/sdk-core/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "sdk-core", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install VectorSpaceLab/AREX-Skill sdk-coreInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add VectorSpaceLab/AREX-Skill --skill sdk-core -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/VectorSpaceLab/AREX-Skill.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/repositories/repo-skills/litellm/sub-skills/sdk-core .github/skills/sdk-core && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "sdk-core" agent skill from https://github.com/VectorSpaceLab/AREX-Skill/tree/main/skills/repositories/repo-skills/litellm/sub-skills/sdk-core into .github/skills/sdk-core/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "sdk-core", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add VectorSpaceLab/AREX-Skill --skill sdk-core -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install VectorSpaceLab/AREX-Skill sdk-core --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/VectorSpaceLab/AREX-Skill.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/repositories/repo-skills/litellm/sub-skills/sdk-core .opencode/skills/sdk-core && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "sdk-core" agent skill from https://github.com/VectorSpaceLab/AREX-Skill/tree/main/skills/repositories/repo-skills/litellm/sub-skills/sdk-core into .opencode/skills/sdk-core/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "sdk-core", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
sdk-core- GitHub stars
- 330
- Token cost
- ~1.1k tokens
- SKILL.md length
- 333 words
- Files
- 5 (incl. scripts, references)
- Skills in repo
- 159
- Repo updated
- First seen
- Licence
- Custom licence
At a glance
A skill your agent uses for direct LiteLLM Python SDK work: chat/text completions, async calls, streaming, embeddings, structured outputs, tools, token/cost checks, caching, callbacks, import/smoke…
- Works in 4 steps: For API signatures and parameter… → For copy-ready SDK patterns, read… → For failures and diagnostics, read… → …
- Direct LiteLLM Python SDK work: chat/text completions
- SKILL.md covers Route Elsewhere, Start Here, Core Mental Model and Quick Patterns, plus 2 more sections
- Runs Python scripts from its folder; calls python; needs OPENAI_API_KEY
What it does
SDK Core is an agent skill from VectorSpaceLab/AREX-Skill. Use for direct LiteLLM Python SDK work: chat/text completions, async calls, streaming, embeddings, structured outputs, tools, token/cost checks, caching, callbacks, import/smoke validation, and shared SDK troubleshooting.
Its SKILL.md is about 1.1k tokens, which your agent loads only when the skill is triggered. The skill folder holds 6 other files, including scripts and reference files (for example `references/api-reference.md`, `references/troubleshooting.md` and `references/workflows.md`).
It sits in AI & LLM Engineering, covering Model routing and gateways, Embeddings and Structured output and tool calling. It works with Python. The repository describes itself as: A Skill Library for Automated Machine Learning.
When your agent uses it
- Direct LiteLLM Python SDK work: chat/text completions
- Structured outputs
- Token/cost checks
- Import/smoke validation
Example prompts
- “/sdk-core”
Requirements
- Python 3
- A credential in OPENAI_API_KEY
Workflow steps
4 steps, taken from the first numbered list in SKILL.md.
- For API signatures and parameter mapping, read references/api-reference.md.
- For copy-ready SDK patterns, read references/workflows.md.
- For failures and diagnostics, read references/troubleshooting.md.
- For a safe local check, run
What it can do on your machine
Read from SKILL.md and the folder at commit ac3fe1a. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
Ships 1 file in scripts/ (Python), which the agent can run.
Shell commands in SKILL.md call:
python
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names these keys or tokens, usually read from environment variables:
OPENAI_API_KEY
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
SDK Core loads about 1.1k tokens when it runs, and up to ~6.8k if it reads all its reference files. Until then it costs about 58 tokens; SKILL.md has 333 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.
SKILL.md
Its licence (Custom licence) doesn't allow us to republish the file, so here is its outline and opening line. It has 333 words (~1,059 tokens).
“Use this sub-skill when the task is about calling LiteLLM as a Python library. LiteLLM exposes OpenAI-format SDK calls across providers, with safe local validation available through mock_response and the bundled smoke script.”
- name
- sdk-core
- disable-model-invocation
- true
- metadata.disco-role
- operating
- license
- NOASSERTION
Files
SKILL.md and 4 other files (scripts, references) in skills/repositories/repo-skills/litellm/sub-skills/sdk-core of VectorSpaceLab/AREX-Skill.
- SKILL.md
- references/api-reference.md
- references/troubleshooting.md
- references/workflows.md
- scripts/sdk_smoke.py
Open the folder on GitHubat commit ac3fe1a
Compare with similar skills
SDK Core next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| SDK Core this skillVectorSpaceLab/AREX-Skill | 330 | — | ~1.1k | Automated safety check: Pass | Custom licence | |
| SGLang Structured ServingOrchestra-Research/AI-Research-SKILLs | 13k | 2 repos | ~2.9k | Automated safety check: Pass | MIT | |
| Senior Prompt Engineeralirezarezvani/claude-skills | 28k | 1 repos | ~2.5k | Automated safety check: Pass | MIT | |
| Context Engineering Reviewmohitagw15856/pm-claude-skills | 1.4k | — | ~1.4k | Automated safety check: Pass | MIT | |
| Routerbase Model Routingaiskillstore/marketplace | 430 | — | ~964 | Automated safety check: Pass | None | |
| Caching Architecturemajiayu000/litellm-rs | 117 | — | ~2k | Automated safety check: Pass | MIT |
Similar skills
Senior Prompt Engineer
alirezarezvani/claude-skills
A skill your agent uses when the user asks to optimize prompts, design prompt templates, evaluate LLM outputs with an eval set, measure RAG retrieval quality, validate agent/tool configurations…
Context Engineering Review
mohitagw15856/pm-claude-skills
Review what an LLM feature or agent actually puts in its context window — and find what's bloating, missing, or fighting itself.
Routerbase Model Routing
aiskillstore/marketplace
Choose RouterBase model IDs and routing strategies for chat, image, video, audio, and embeddings workloads.
Caching Architecture
majiayu000/litellm-rs
LiteLLM-RS response caching architecture. An agent skill from majiayu000/litellm-rs.
Ag2 Structured Output
ag2ai/build-with-ag2
Get a typed Python value back from an AG2 beta Agent instead of free text.
More from VectorSpaceLab/AREX-Skill
All 159 skills in this repoAgent Lightning
VectorSpaceLab/AREX-Skill
Use this repo skill for Agent Lightning package tasks: authoring trainable agents, tracing rewards and spans, running LightningStore/Trainer loops, using agl CLI services, choosing examples, and…
Agent Tools
VectorSpaceLab/AREX-Skill
A skill your agent uses when configuring LiteLLM for MCP tools, A2A agents, Claude Code/Cursor agent gateway traffic, MCP auth/OAuth, tool permissions, semantic filtering, or agent-specific proxy…
Agents And Awel
VectorSpaceLab/AREX-Skill
Build and debug DB-GPT agents, tools, skills, teams, and AWEL workflows, including deterministic local DAG runs and HTTP-trigger topology without assuming an LLM, credential, or external service.
Agents And Middleware
VectorSpaceLab/AREX-Skill
Work on the actively maintained LangChain v1 agent package: initchatmodel, createagent, structured output, tools, middleware, embeddings initialization, provider routing, and agent runtime…
Agents Workflows
VectorSpaceLab/AREX-Skill
A skill your agent uses for giskard.agents async chat workflows, tools, prompt templates, structured outputs, retries, rate limiting, embeddings, and optional LiteLLM backend.
Alphafold3
VectorSpaceLab/AREX-Skill
A skill your agent uses for AlphaFold 3 input preparation, prediction command planning, output interpretation, and Python API inspection.
Related
Works with
Categories
Questions about SDK Core
What does SDK Core do?
A skill your agent uses for direct LiteLLM Python SDK work: chat/text completions, async calls, streaming, embeddings, structured outputs, tools, token/cost checks, caching, callbacks, import/smoke…. SDK Core is an agent skill from VectorSpaceLab/AREX-Skill. Use for direct LiteLLM Python SDK work: chat/text completions, async calls, streaming, embeddings, structured outputs, tools, token/cost checks, caching, callbacks, import/smoke validation, and shared SDK troubleshooting.
When should I use SDK Core?
SDK Core fits situations like: direct LiteLLM Python SDK work: chat/text completions; structured outputs; token/cost checks; import/smoke validation.
How do I install SDK Core in Claude Code?
Run `npx skills add VectorSpaceLab/AREX-Skill --skill sdk-core -a claude-code`. Or copy the skill folder (skills/repositories/repo-skills/litellm/sub-skills/sdk-core in VectorSpaceLab/AREX-Skill) into .claude/skills/sdk-core in your project. Claude Code loads it when a task matches its description.
How do I install SDK Core in Codex?
Run `npx skills add VectorSpaceLab/AREX-Skill --skill sdk-core -a codex`. Or copy the skill folder (skills/repositories/repo-skills/litellm/sub-skills/sdk-core in VectorSpaceLab/AREX-Skill) into .agents/skills/sdk-core in your project. Codex loads it when a task matches its description.
Can I use SDK Core in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add VectorSpaceLab/AREX-Skill --skill sdk-core -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/sdk-core, .gemini/skills/sdk-core, .github/skills/sdk-core and .opencode/skills/sdk-core in your project.
What does SDK Core need to run?
Going by SKILL.md and its folder, SDK Core needs Python for the scripts in its folder, the command-line tools its instructions call (python) and credentials named OPENAI_API_KEY. Our summary lists: Python 3; A credential in OPENAI_API_KEY.
Does SDK Core access the network?
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Is SDK Core safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.
What licence does SDK Core use?
SDK Core has a licence file (declared in SKILL.md) that doesn't match a standard licence. Read it on GitHub before reusing the skill.
How many tokens does SDK Core use?
About 1.1k tokens (SKILL.md is roughly 4.2k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 5.8k tokens, read only when the agent opens those files.
What are the alternatives to SDK Core?
Skills that share tags, products or a category with SDK Core: SGLang Structured Serving (Orchestra-Research/AI-Research-SKILLs, 13k stars), Senior Prompt Engineer (alirezarezvani/claude-skills, 28k stars), Context Engineering Review (mohitagw15856/pm-claude-skills, 1.4k stars) and Routerbase Model Routing (aiskillstore/marketplace, 430 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains SDK Core?
VectorSpaceLab (a GitHub organization) maintains it in VectorSpaceLab/AREX-Skill, which has 330 GitHub stars. The repository holds 159 skills in this directory. The repository was last updated on September 3, 2026.
Source: VectorSpaceLab/AREX-Skill on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.