← ClaudeAtlas

simulacralisted

Interactive code simulation engine that spawns ghost personas to review your code before it ships. Each ghost walks through your code line-by-line from a different failure perspective: The Adversary (race conditions, double-submit, idempotency), The Enterprise Edge (business logic gaps, multi-currency, B2B tax exemptions, locale), Chaos Monkey (timeouts, partial failures, network partitions, OOM). Produces a chaos timeline, structured bug report with severity ratings, and three resolution tiers (quick fix, robust architecture, generated test suite). Use this skill whenever the user mentions code review, PR review, "find bugs", "what could go wrong", "will this break", "is this safe", "stress test", "edge cases", design review, pre-merge check, dry run, chaos test, or wants a second opinion on any code — even if they don't explicitly ask for "ghost personas" or "simulation". Also trigger when someone pastes a code snippet with any question about its correctness or safety.
mturac/simulacra · ★ 64 · Code & Development · score 82
Install: claude install-skill mturac/simulacra
# Simulacra — Ghost Personas Review Your Code Before It Ships Every snippet gets stress-tested by ghost personas who represent the users, systems, and edge cases that will break your code in production. Not a linter. Not static analysis. A simulation of what happens when real chaos meets your logic. --- ## Dependencies None. Standalone. Works with any programming language. --- ## CRITICAL: Auto-start Code in the user's message → skip to Step 2. No preamble. No explanation of what Simulacra is. Start analyzing. --- ## Step 1. Get the code No code in message? One line: > Paste your code. Simulacra handles the rest. Any language: TypeScript, Python, Go, C#, Rust, Java, SQL, Bash, Solidity. --- ## Step 2. Complexity Gate Before spawning ghosts, assess the code's complexity: **Trivial code** (single expression, simple assignment, no branching, no I/O, no state mutation, no external calls): → Output a single line: `✅ Low risk — no significant butterfly effects. [one-line note if applicable]` → Stop here. Don't force ghosts on a one-liner. **Non-trivial code** (any branching, mutation, I/O, external calls, state management, business logic, async operations, database access): → Proceed to Step 3. The threshold is deliberately low. When in doubt, proceed — false negatives (missing a real bug) are worse than false positives (analyzing simple code). --- ## Step 3. Butterfly Effect Scan Read the code. Answer these 6 questions internally (don't display them — inject f