Agent skill · research science · aiskillstore
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.
Why this skill is useful
Adds detailed analysis of wire protocols and message formats that enhance understanding of LLM interactions, including executable translation patterns.
What it needs
About 9k tokens when loaded. Last updated 2026-08-07. 405 stars on the source repository.
What this skill does
Harness-Model Protocol Analysis Analyzes the interface layer between agent frameworks (harness) and language models. This skill examines the wire protocol, message encoding, and agentic primitives that enable tool-augmented conversation. Distinction from tool-interface-analysis tool-interface-analysis harness-model-protocol ------------------------ ------------------------ How tools are registered and discovered How tool calls are encoded on the wire Schema generation (Pydantic → JSON Schema) Schema transmission to LLM API Error feedback patterns Response parsing and error extraction Retry mechanisms at tool level Streaming mechanics and partial responses Tool execution orchestration Message format translation Process 1. Map message protocol — Identify wire format (OpenAI, Anthropic, custom) 2. Trace tool call encoding — How tool calls are requested and parsed 3. Analyze streaming mechanics — SSE, WebSocket, chunk handling 4. Catalog agentic primitives — System prompts, scratchpads, interrupts 5. Evaluate provider abstraction — How multi-LLM support is achieved Message Protocol Analysis Wire Format Families OpenAI-Compatible (Chat Completions) Anthropic Messages API Google Gemini (Generative AI) Key Dimensions Dimension OpenAI Anthropic Gemini ----------- -------- ----------- -------- System prompt In messages Separate field In contents (optional) Tool calls toolcalls array Content blocks functionCall in parts Tool results Role tool Role user + toolresult functionResponse Multi-tool Single message Single message Single message Streaming SSE data: {...} SSE event: ... …
How to use it
Reference it in AdaL, Claude Code, Cursor or any coding agent — nothing to install:
@skills aiskillstore/harness-model-protocol