claude-api-tool-runtime

This skill should be used when the user asks to build, audit, or harden a Claude Platform Messages API client-side tool execution loop, handle tool_use and tool_result messages, correlate tool_use_id values, stream partial tool JSON, enforce strict:true schemas, handle stop_reason values, or design retry/error behavior for Anthropic Messages API tools. Do not use it for Claude Code headless CLI or Agent SDK automation, prompt-cache design, MCP server design, tool catalog descriptions, or individual tool implementations.

SKILL.md

Quality

Evals

Security

No review data available

This skill hasn't been reviewed yet

Repository: JaviMontano/claude-plugins
Path: plugins/claude-native-toolkit/skills/claude-api-tool-runtime/SKILL.md
Commit: e8f986b

Reviewed: 3 days ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.