vllm-tool-parsers

Official

Master vLLM tool-parsers for AI workflows.

Authorair-gapped
Version1.0.0
Installs0

System Documentation

What problem does it solve?

The vLLM tool-parsers skill provides a central reference for all built-in and custom tool-parsing strategies, mapping parser implementations, their capabilities, and debugging guidance to help teams integrate tool-calling with vLLM deployments.

Core Features & Use Cases

  • Comprehensive parser index and registry mapping for tool-parsing across vLLM projects.
  • Diagnostic playbook and troubleshooting guidance for streaming and non-streaming parsers, reasoning-pairing, and template compatibility.
  • Clear guidance on building or plugging in custom tool-parsers via plugins with skeletons and examples.
  • Up-to-date alignment with the RFC 11522 parse_delta migration and recent PRs, ensuring forward-compatibility.
  • Practical use cases across model debugging, plugin development, and integration testing.

Quick Start

Review the index to select a compatible parser, then implement or plug in a new parser following the custom-parser plugin guidelines.

Dependency Matrix

Required Modules

None required

Components

references

💻 Claude Code Installation

Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.

Please help me install this Skill:
Name: vllm-tool-parsers
Download link: https://github.com/air-gapped/skills/archive/main.zip#vllm-tool-parsers

Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
View Source Repository

Agent Skills Search Helper

Install a tiny helper to your Agent, search and equip skill from 510,000+ vetted skills library on demand.