Vllm
Prism-Shadow/penguin-harness
Deploy and serve LLMs with vLLM behind an OpenAI-compatible endpoint, with tool calling enabled for agent workloads.
Use this vLLM sub-skill for structured outputs, JSON/regex/grammar constraints, tool calling, reasoning parsers, chat-template/tool-parser routing, streaming tool-call deltas, and parser/backend…
Install Structured Tool Reasoning
$ npx skills add VectorSpaceLab/AREX-Skill --skill structured-tool-reasoning -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install VectorSpaceLab/AREX-Skill structured-tool-reasoning --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/vllm/sub-skills/structured-tool-reasoning .claude/skills/structured-tool-reasoning && 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 "structured-tool-reasoning" agent skill from https://github.com/VectorSpaceLab/AREX-Skill/tree/main/skills/repositories/repo-skills/vllm/sub-skills/structured-tool-reasoning into .claude/skills/structured-tool-reasoning/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "structured-tool-reasoning", 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/vllm/sub-skills/structured-tool-reasoningType 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 structured-tool-reasoning -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install VectorSpaceLab/AREX-Skill structured-tool-reasoning --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/vllm/sub-skills/structured-tool-reasoning .agents/skills/structured-tool-reasoning && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "structured-tool-reasoning" agent skill from https://github.com/VectorSpaceLab/AREX-Skill/tree/main/skills/repositories/repo-skills/vllm/sub-skills/structured-tool-reasoning into .agents/skills/structured-tool-reasoning/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "structured-tool-reasoning", 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 structured-tool-reasoning -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install VectorSpaceLab/AREX-Skill structured-tool-reasoning --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/vllm/sub-skills/structured-tool-reasoning .cursor/skills/structured-tool-reasoning && 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 "structured-tool-reasoning" agent skill from https://github.com/VectorSpaceLab/AREX-Skill/tree/main/skills/repositories/repo-skills/vllm/sub-skills/structured-tool-reasoning into .cursor/skills/structured-tool-reasoning/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "structured-tool-reasoning", 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/vllm/sub-skills/structured-tool-reasoning--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 structured-tool-reasoning -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install VectorSpaceLab/AREX-Skill structured-tool-reasoning --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/vllm/sub-skills/structured-tool-reasoning .gemini/skills/structured-tool-reasoning && 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 "structured-tool-reasoning" agent skill from https://github.com/VectorSpaceLab/AREX-Skill/tree/main/skills/repositories/repo-skills/vllm/sub-skills/structured-tool-reasoning into .gemini/skills/structured-tool-reasoning/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "structured-tool-reasoning", 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 structured-tool-reasoningInstalls 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 structured-tool-reasoning -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/vllm/sub-skills/structured-tool-reasoning .github/skills/structured-tool-reasoning && 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 "structured-tool-reasoning" agent skill from https://github.com/VectorSpaceLab/AREX-Skill/tree/main/skills/repositories/repo-skills/vllm/sub-skills/structured-tool-reasoning into .github/skills/structured-tool-reasoning/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "structured-tool-reasoning", 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 structured-tool-reasoning -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 structured-tool-reasoning --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/vllm/sub-skills/structured-tool-reasoning .opencode/skills/structured-tool-reasoning && 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 "structured-tool-reasoning" agent skill from https://github.com/VectorSpaceLab/AREX-Skill/tree/main/skills/repositories/repo-skills/vllm/sub-skills/structured-tool-reasoning into .opencode/skills/structured-tool-reasoning/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "structured-tool-reasoning", 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
structured-tool-reasoning- GitHub stars
- 328
- Token cost
- ~823 tokens
- SKILL.md length
- 282 words
- Files
- 6 (incl. scripts, references)
- Skills in repo
- 157
- Repo updated
- First seen
- Licence
- Apache-2.0
At a glance
Use this vLLM sub-skill for structured outputs, JSON/regex/grammar constraints, tool calling, reasoning parsers, chat-template/tool-parser routing, streaming tool-call deltas, and parser/backend…
- Tasks that involve Structured output and tool calling
- SKILL.md covers Route by Task, Safe Local Helper, Boundaries and Hardware and Runtime Notes
- Runs Python scripts from its folder; calls python
- Tasks that involve LLM inference and serving
What it does
Structured Tool Reasoning is an agent skill from VectorSpaceLab/AREX-Skill. Use this vLLM sub-skill for structured outputs, JSON/regex/grammar constraints, tool calling, reasoning parsers, chat-template/tool-parser routing, streaming tool-call deltas, and parser/backend troubleshooting.
Its SKILL.md is about 820 tokens, which your agent loads only when the skill is triggered. The skill folder holds 7 other files, including scripts and reference files (for example `references/reasoning-parsers.md`, `references/structured-outputs.md` and `references/tool-calling.md`).
It sits in AI & LLM Engineering, covering Structured output and tool calling and LLM inference and serving. It works with vLLM and OpenAI. The repository describes itself as: A Skill Library for Automated Machine Learning. The licence is Apache-2.0.
When your agent uses it
- Tasks that involve Structured output and tool calling
- Tasks that involve LLM inference and serving
Example prompts
- “/structured-tool-reasoning”
Requirements
- Python 3
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 no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Structured Tool Reasoning loads about 823 tokens when it runs, and up to ~9.7k if it reads all its reference files. Until then it costs about 59 tokens; SKILL.md has 282 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
The full file from VectorSpaceLab/AREX-Skill at commit ac3fe1a, republished under its Apache-2.0 licence (© VectorSpaceLab). 282 words, ~823 tokens.
Download SKILL.mdSave it as
.claude/skills/structured-tool-reasoning/SKILL.md (or your agent's skills folder). This skill also uses 5 other files; get the full folder from GitHub.- name
- structured-tool-reasoning
- description
- Use this vLLM sub-skill for structured outputs, JSON/regex/grammar constraints, tool calling, reasoning parsers, chat-template/tool-parser routing, streaming tool-call deltas, and parser/backend troubleshooting.
- disable-model-invocation
- true
- metadata.disco-role
- operating
- license
- Apache 2.0
Structured Tool Reasoning
Use this sub-skill when the task involves constrained generation, OpenAI-compatible response_format or structured_outputs, tool/function calling, reasoning parser output, or debugging parser/template/backend behavior in vLLM.
Route by Task
- For JSON schema, JSON object, choice, regex, grammar, or structural-tag constraints, read references/structured-outputs.md.
- For OpenAI-compatible
tools,tool_choice, auto tool choice, strict tool schemas, parser names, chat templates, and streaming tool-call assembly, read references/tool-calling.md. - For
--reasoning-parser,reasoningfields, reasoning streaming deltas, thinking controls, and combining reasoning with tools or structured outputs, read references/reasoning-parsers.md. - For unsupported schema keywords, invalid grammars, backend dependency issues, parser name mismatches, incompatible chat templates, missing streamed tool calls, or absent reasoning content, read references/troubleshooting.md.
Safe Local Helper
Use the bundled validator before contacting a server when a user provides a request fragment:
# From this sub-skill directory:
python scripts/validate_structured_request.py --input request.json
python scripts/validate_structured_request.py --example tool-streaming
# From the root vLLM skill directory:
python sub-skills/structured-tool-reasoning/scripts/validate_structured_request.py --input request.jsonThe helper checks request-shape consistency for response_format, structured_outputs, tools, tool_choice, reasoning flags, common backend compatibility risks, and streaming tool-call handling. It does not import vLLM, download models, start a server, execute tools, or call external APIs.
Boundaries
- Route general server startup, authentication, host/port, OpenAI endpoint coverage, and deployment layout to
../openai-serving/when present. - Route basic
LLM.generateorLLM.chatsetup without structured constraints to../offline-inference/when present. - Route multimodal, pooling, embeddings, adapters, and LoRA-specific requests to
../modalities-adapters-pooling/when present. - Route performance tuning of structured decoding backends, throughput, batching, and benchmark questions to
../deployment-performance/when present.
Hardware and Runtime Notes
- Offline and serving examples require user-provided models and hardware appropriate for the selected model; CPU-only or precompiled inspection environments prove imports and signatures, not GPU throughput.
- OpenAI-compatible examples assume the user already has a running vLLM server exposing
/v1. - Tool execution is always application-owned: vLLM returns tool-call names and argument strings; caller code validates and executes the actual functions.
© VectorSpaceLab, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
SKILL.md and 5 other files (scripts, references) in skills/repositories/repo-skills/vllm/sub-skills/structured-tool-reasoning of VectorSpaceLab/AREX-Skill.
- SKILL.md
- references/reasoning-parsers.md
- references/structured-outputs.md
- references/tool-calling.md
- references/troubleshooting.md
- scripts/validate_structured_request.py
Open the folder on GitHubat commit ac3fe1a
Compare with similar skills
Structured Tool Reasoning 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 |
|---|---|---|---|---|---|---|
| Structured Tool Reasoning this skillVectorSpaceLab/AREX-Skill | 328 | — | ~823 | Automated safety check: Pass | Apache-2.0 | |
| VllmPrism-Shadow/penguin-harness | 2.5k | — | ~1k | Automated safety check: Pass | Apache-2.0 | |
| Aider DelegateamElnagdy/delegate-skills | 2.3k | 3 repos | ~3k | Automated safety check: Pass | MIT | |
| Perfupraullenchai/Rapid-MLX | 3.9k | — | ~1.6k | Automated safety check: Notes | Custom licence | |
| Model Serving MinefieldBlackwellboy/model-serving-minefield | 135 | — | ~2.1k | Automated safety check: Pass | MIT | |
| Outlines Structured GenerationOrchestra-Research/AI-Research-SKILLs | 13k | 10 repos | ~4k | Automated safety check: Pass | MIT |
Similar skills
Aider Delegate
amElnagdy/delegate-skills
Delegate a coding task to Aider (aider) as a background implementer, then review its diff and land it yourself.
Perfup
raullenchai/Rapid-MLX
Autonomous performance optimization: research, PoC, benchmark, implement, review, PR
Model Serving Minefield
Blackwellboy/model-serving-minefield
Diagnose OpenAI-compatible model-serving failures from symptoms, endpoint reports, explicit configuration files, or logs while preserving evidence status and requiring confirm/refute checks.
Outlines Structured Generation
Orchestra-Research/AI-Research-SKILLs
Uses the Outlines library to constrain model output to a JSON schema, Pydantic model, regex or fixed set of choices when running local models.
vLLM Model Serving
Orchestra-Research/AI-Research-SKILLs
Deploys LLMs with vLLM for high-throughput serving, covering the OpenAI-compatible server, offline batch inference, monitoring and a Docker rollout.
More from VectorSpaceLab/AREX-Skill
All 157 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
Categories
Questions about Structured Tool Reasoning
What does Structured Tool Reasoning do?
Use this vLLM sub-skill for structured outputs, JSON/regex/grammar constraints, tool calling, reasoning parsers, chat-template/tool-parser routing, streaming tool-call deltas, and parser/backend…. Structured Tool Reasoning is an agent skill from VectorSpaceLab/AREX-Skill. Use this vLLM sub-skill for structured outputs, JSON/regex/grammar constraints, tool calling, reasoning parsers, chat-template/tool-parser routing, streaming tool-call deltas, and parser/backend troubleshooting.
When should I use Structured Tool Reasoning?
Structured Tool Reasoning fits situations like: tasks that involve Structured output and tool calling; tasks that involve LLM inference and serving.
How do I install Structured Tool Reasoning in Claude Code?
Run `npx skills add VectorSpaceLab/AREX-Skill --skill structured-tool-reasoning -a claude-code`. Or copy the skill folder (skills/repositories/repo-skills/vllm/sub-skills/structured-tool-reasoning in VectorSpaceLab/AREX-Skill) into .claude/skills/structured-tool-reasoning in your project. Claude Code loads it when a task matches its description.
How do I install Structured Tool Reasoning in Codex?
Run `npx skills add VectorSpaceLab/AREX-Skill --skill structured-tool-reasoning -a codex`. Or copy the skill folder (skills/repositories/repo-skills/vllm/sub-skills/structured-tool-reasoning in VectorSpaceLab/AREX-Skill) into .agents/skills/structured-tool-reasoning in your project. Codex loads it when a task matches its description.
Can I use Structured Tool Reasoning 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 structured-tool-reasoning -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/structured-tool-reasoning, .gemini/skills/structured-tool-reasoning, .github/skills/structured-tool-reasoning and .opencode/skills/structured-tool-reasoning in your project.
What does Structured Tool Reasoning need to run?
Going by SKILL.md and its folder, Structured Tool Reasoning needs Python for the scripts in its folder and the command-line tools its instructions call (python). Our summary lists: Python 3.
Does Structured Tool Reasoning 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 Structured Tool Reasoning 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 Structured Tool Reasoning use?
Structured Tool Reasoning is published under the Apache-2.0 licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Structured Tool Reasoning use?
About 823 tokens (SKILL.md is roughly 3.3k 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 8.8k tokens, read only when the agent opens those files.
What are the alternatives to Structured Tool Reasoning?
Skills that share tags, products or a category with Structured Tool Reasoning: Vllm (Prism-Shadow/penguin-harness, 2.5k stars), Aider Delegate (amElnagdy/delegate-skills, 2.3k stars), Perfup (raullenchai/Rapid-MLX, 3.9k stars) and Model Serving Minefield (Blackwellboy/model-serving-minefield, 135 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Structured Tool Reasoning?
VectorSpaceLab (a GitHub organization) maintains it in VectorSpaceLab/AREX-Skill, which has 328 GitHub stars. The repository holds 157 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.