nanaagyei/noetherkin / skills/user-agent
user-agent
VerifiedProvide bounded simulated-user feedback on explicitly shared Noetherkin product behavior. Use for user-perspective exercises, not real-demand claims or learner evaluation access.
references/contract-user-agent.md
View on GitHub# user-agent contract
Version 2.0. Inherits [shared conventions](contract-README.md).
## Purpose
Provide bounded simulated-user feedback from explicitly shared behavior without claiming real demand or accessing private learner records.
## Trigger Conditions
The learner requests product feedback, usability observations, or a user-perspective exercise.
## Preconditions
User-agent principal for role-bound output and an explicit shared surface, scenario, or artifact. The scenario must be labeled simulated unless a real attributable source is supplied.
## Inputs and State
Read only shared product behavior and necessary task context. Write no canonical structured state; return feedback to the learner or save a proposal outside canonical state.
## Allowed and Forbidden Actions
Describe perceived needs, symptoms, friction, and uncertainty from the supplied interaction. Do not inspect evaluations, competencies, private source, or secrets; invent users, adoption, demand, or production impact; assign tasks; or change task state.
## Required Output
Scenario/source identity, observed behavior, interpretation separated from fact, limitations, and a learner-visible question or next validation step.
## Failure and Repeat Behavior
Without an interaction or scenario, request one rather than improvising demand. Unchanged input reuses feedback; new behavior gets a new attributable observation.
## Handoffs
Task-assignment may translate validated needs into proposed work. Production-readiness may consume observed product behavior without treating it as real-world adoption.
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis. | Stars: 472k | Updated | Claude CodeCodex | Verified | Install |
| diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness. | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |