kata-pov-feedback-attach

Define measurable feedback loops for engineering agent PoVs with HITL or objective metrics.

Updated Sep 3, 2025
One-click install
npx skills add https://github.com/guardiatechnology/design-system --skill kata-pov-feedback-attach
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: kata-pov-feedback-attach
Source: https://github.com/guardiatechnology/design-system/tree/main/.claude/skills/kata-pov-feedback-attach
Command: npx skills add https://github.com/guardiatechnology/design-system --skill kata-pov-feedback-attach

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill prevents a PoV from becoming “fake documentation” by forcing you to attach a real feedback loop that either includes lightweight human-in-the-loop (HITL) approval signals or uses an objective, quantified metric.

Core Features & Use Cases

  • HITL or objective metric selection: Choose lightweight human approval/rejection/edit capture for consequential actions, or define an objective environment signal for advisory outputs (or both for Tier-1/2).
  • Operationalizes feedback collection: Specify how frequently feedback is captured/aggregated and how it is reviewed.
  • Defines pivot behavior with quantified thresholds: Set a windowed threshold that triggers a PoV re-scope via kata-pov-scope-define, distinct from discontinuation.
  • Persists feedback for downstream use: Writes feedback.md to the required docs/{context}/agents-pov/{agent}/ location with cross-links.

Quick Start

Ask an agent to read your pov.md, decide whether you need lightweight HITL, an objective metric, or both, and then generate the required feedback.md at docs/{context}/agents-pov/{agent}/feedback.md.

Frequently Asked Questions about kata-pov-feedback-attach

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

FAQPage Schema
How do I set up a measurable feedback loop for an engineering agent PoV?

To set up a measurable PoV feedback loop, define a lightweight human-in-the-loop approval process or select a quantified objective metric to capture operational signals and persist them in a feedback.md file.

What is the best way to trigger a PoV pivot review using quantified metrics?

Trigger a PoV pivot review by setting windowed thresholds on your aggregated feedback metrics, which initiates a re-scope via kata-pov-scope-define rather than discontinuing the project.

When do I need human-in-the-loop capture versus an objective metric for PoV feedback?

Use human-in-the-loop capture for consequential actions requiring approval or edit signals, and apply an objective metric for advisory outputs to quantify environment signals automatically.

How do I capture and aggregate HITL feedback on a regular cadence?

Capture and aggregate HITL feedback by specifying a collection frequency and review schedule within your engineering workflow, persisting technical capture details and cadence in feedback.md.

Does this PoV feedback mechanism integrate with existing observability value metrics?

Yes, the generated feedback.md includes a cross-reference to observability/value-metrics.md, integrating the defined feedback loop directly with your existing PoV value metrics documentation.

Can I use both HITL and objective metrics simultaneously for Tier-1 and Tier-2 agents?

Yes, you can select both lightweight human-in-the-loop approval signals and objective environment metrics simultaneously to capture comprehensive PoV feedback for Tier-1 and Tier-2 agents.