Back to Skills Library
Reverse EngineeringTeardownArchitectureAI Agent Skill

protocol-reverse-engineering

Reverse-engineers a competitor's protocol and data flow from observed network traffic and behavior, instead of relying on marketing claims.

wshobson/agents
10.3k stars
10.3k installs
Updated: 2026-07-16

Install Options

Install into Claude Code, Cursor, Codex, or Antigravity with:

$ npx skills add wshobson/agents@protocol-reverse-engineering

Real Work Situation Solved

Deconstruct a competitor's AI feature without falling for marketing hype

A competitor announced a "100% Autonomous AI Agent" - how do you reverse-engineer what's real under the hood?

5-Step Action Framework

  1. 1Test adversarial edge cases, malformed inputs, and out-of-domain requests to find where the system breaks.
  2. 2Observe latency and rendering patterns: streaming implies an LLM call; instant response implies caching or rule-based logic.
  3. 3Determine whether the feature relies on proprietary model training or is simply a thin prompt wrapper around a commodity LLM API.
  4. 4Identify human-in-the-loop boundaries: where the workflow pauses for manual user confirmation.
  5. 5Compile a 4-factor matrix: core user problem solved, observed real-world accuracy, estimated unit cost, and actual defensibility.
Before

"The competitor's AI looks revolutionary, we must copy it immediately."

After

"Live teardown: feature is a simple prompt wrapper on GPT-4o with 6s latency that fails 4/10 numeric tasks. Proposal: solve with local rule engine in 50ms instead of blind imitation."

Related Course Lesson

AI Product ManagementLesson 8

Go to Lesson

SKILL.md Source Instructions

SKILL.md • Read-only preview
# Protocol Reverse Engineering Skill

Capture and inspect network traffic and response timing to infer the real architecture behind a feature, distinguishing genuine model calls from cached or rule-based shortcuts.