CtrlK
BlogDocsLog inGet started
Tessl Logo

markusdowne/memory-roundtrip-guard

Tests memory writes, confirms read-back accuracy, and validates retrieval success to ensure saved information can actually be recovered. Use when you need to verify memory was saved correctly, check if stored data can be retrieved, confirm a memory entry is discoverable, or escalate when saved information appears lost or corrupted. Covers write confirmation, read-back comparison, retrieval smoke testing, and failure escalation. Includes explicit untrusted-content/prompt-injection guardrails for third-party inputs.

92

1.19x

Quality

90%

Does it follow best practices?

Impact

97%

1.19x

Average score across 5 eval scenarios

Overview
Skills
Evals
Files

task.mdevals/scenario-2/

User Preference Persistence Verification

Problem/Feature Description

A mobile productivity app team has just shipped an onboarding flow that collects user preferences — things like display theme, notification frequency, preferred language, and default dashboard layout. These preferences are stored via the app's memory/storage layer so they persist across sessions. The team has had a couple of bug reports where users say their preferences "reset" after logging out and back in, but the engineering team can't reproduce it reliably.

You are tasked with building a small verification script that simulates saving a set of user preferences to a memory store and then confirms the data was actually persisted correctly. The script should save the preferences, then produce a structured verification report that the QA team can review to confirm the process succeeded — or flag any issues.

Output Specification

Produce two files:

  1. verify_preferences.py — A Python script that simulates writing a user preference entry to a memory store (you can use a dict, SQLite, a simple file-based store, or any in-memory/persistent approach), then performs verification steps, and prints a structured report to stdout.

  2. report.json — The verification report produced by running the script. It should document the outcome of each step in the verification process and include a final status classification and any recommended follow-up action.

The script should be self-contained and runnable with python verify_preferences.py using only Python standard library modules (no third-party packages).

Input Files

The following user preferences should be persisted as the test data:

{
  "user_id": "u_4821",
  "theme": "dark",
  "language": "en-GB",
  "notifications": "daily-digest",
  "dashboard_layout": "compact"
}

Install with Tessl CLI

npx tessl i markusdowne/memory-roundtrip-guard

evals

SKILL.md

tile.json