concierge-testing

Conduct manual concierge tests with real users to measure commitment for gap hypotheses.

Updated Feb 17, 2026
One-click install
npx skills add https://github.com/0xHoneyJar/construct-observer --skill concierge-testing
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: concierge-testing
Source: https://github.com/0xHoneyJar/construct-observer/tree/main/skills/concierge-testing
Command: npx skills add https://github.com/0xHoneyJar/construct-observer --skill concierge-testing

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This skill helps product teams validate gap hypotheses by manually simulating features for a single user and measuring commitment rather than general sentiment, ensuring decisions are grounded in observed behavior.

Core Features & Use Cases

  • Manual validation for hypotheses that have reached Pattern level, using real-user canvases to gather concrete commitment signals.
  • Provenance logging, canvas-driven user selection, and structured handoffs to product teams for decision-making.
  • End-to-end workflow from hypothesis selection to canvas update with a recorded commitment outcome.

Quick Start

Run /concierge-test {hypothesis-id} to begin validating the strongest canvas hypothesis.

Frequently Asked Questions about concierge-testing

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I validate a gap hypothesis with real users before building a feature?

You can validate a gap hypothesis by running manual concierge-style tests that measure real user commitment rather than general sentiment, ensuring product decisions are grounded in observed behavior.

When should I use concierge testing for product hypothesis validation?

Use concierge testing when a gap hypothesis has reached Pattern level and requires measured commitment data from real users before you decide to file a GitHub issue or discard the idea.

How do I manually simulate a feature to test user commitment?

You manually simulate a feature by selecting your strongest-evidence user from canvases, constructing a concrete manual simulation for them, and recording the provenance of their commitment outcome.

Can I use canvases to select users for manual feature validation?

Yes, you can use real-user canvases to select the strongest-evidence user for manual validation, gathering concrete commitment signals and updating the canvases with the final commitment results.

What is the difference between measuring user commitment and gathering general sentiment?

Measuring user commitment grounds decisions in observed behavior through manual simulations, whereas general sentiment only captures opinions, making commitment a stronger signal for validating hypotheses.