harness-model-protocol

Analyze the protocol layer between agent harness and LLM model. Use when (1) understanding message wire formats and API contracts, (2) examining tool call encoding/decoding mechanisms, (3) evaluating streaming protocols and partial response handling, (4) identifying agentic chat primitives (system prompts, scratchpads, interrupts), (5) comparing multi-provider abstraction strategies, or (6) understanding how frameworks translate between native LLM APIs and internal representations.

$ 安裝

git clone https://github.com/Dowwie/agent_framework_study /tmp/agent_framework_study && cp -r /tmp/agent_framework_study/.claude/skills/harness-model-protocol ~/.claude/skills/agent_framework_study

// tip: Run this command in your terminal to install the skill