/ai--tool-calling

/ai--tool-calling is a Claude Code skill in the AI & Agents section. Audits or implements the tools a model can call: clear schemas, parallel calls, error handling that lets the model recover, and an accuracy eval.

Author's description

Robust LLM tool calling - schema design, parallel calls, errors, eval harness

How to ask for it

/ai--tool-calling design the tool schema so the model stops mis-calling it
/ai--tool-calling let the agent call several tools in parallel
/ai--tool-calling handle errors when a tool call fails

Install

curl -fsSL https://raw.githubusercontent.com/sgomez-dev/claude-skills/main/install.sh | bash

After installing with the script, type /ai--tool-calling. Using Cursor, Windsurf or Codex? Platform guides

Demo coming soon

/ai--voice-agentReal-time voice agent
Designs a low-latency voice agent that handles interruptions: speech-to-text and text-to-speech choice, latency budget and conversation design.
Built here
/deep-researchIn-depth web research
Applies a multi-phase research method, with several angles and sources, before answering or creating content that needs up-to-date information.
By Hainrixz
/meta--health-checkSkills health check
Checks every installed skill for structure, declared permissions and safety, then produces a health report of what passes and what fails.
Built here
/meta--pipeline-runRunning a skill pipeline
Runs a chain of skills defined in a pipeline file, with quality gates between steps and a final summary showing the result of each step.
Built here
/meta--skill-forgeCreating a new skill
Generates a new skill from a plain-language description, together with its permission manifest and a test file.
Built here
/meta--skills-initProject-specific skills setup
Scans your project, detects its tech stack and activates only the relevant skills, saving the choice as a project configuration file.
Built here

How to ask for it

Install

More from this section