llo-uat-eval

Grade LLO UAT compilations against PDD success metrics for launch readiness.

1|2|Updated Apr 1, 2026
One-click install
npx skills add https://github.com/dimagi-internal/ace --skill llo-uat-eval
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: llo-uat-eval
Source: https://github.com/dimagi-internal/ace/tree/main/skills/llo-uat-eval
Command: npx skills add https://github.com/dimagi-internal/ace --skill llo-uat-eval

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Unvalidated LLO UAT result compilations often let unready Connect opportunities proceed to launch, missing gaps in PDD success metric coverage, unresolved UAT blockers, or missing LLO sign-offs that create post-launch operational and user experience risks.

Core Features & Use Cases

  • 6-Dimension Grading Rubric: Evaluates UAT compilations across weighted dimensions including PDD metric coverage completeness, UAT outcome fitness, LLO sign-off clarity, blocker resolution, evidence citation discipline, and launch readiness recommendation accuracy.
  • Hard Block Guardrails: Automatically fails opportunities with critical gaps like insufficient PDD metric coverage, missed primary success metric thresholds paired with launch recommendations, unresolved UAT blockers, or LLO no-go sign-offs paired with launch recommendations.
  • Archetype Support: Adapts grading logic for atomic visit, focus group, and multi-stage Connect opportunity types, with specialized checks for per-session facilitator and participant sign-offs for focus group use cases.
  • Use Case: For ACE Phase 9 execution managers, this skill acts as the final quality gate before llo-launch, ensuring UAT compilations fully align with PDD requirements and all stakeholder sign-offs are documented before activation.

Quick Start

Use the llo-uat-eval skill to grade the Phase 9 LLO UAT results compilation for your current Connect opportunity against its PDD success metrics and generate a formal launch readiness verdict.

Frequently Asked Questions about llo-uat-eval

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

FAQPage Schema
How do I validate UAT results against product design document success metrics before launch?

Validate UAT results by grading the compilation against PDD success metrics to check coverage completeness, metric outcome fitness, and blocker resolution. This ensures launch readiness for Connect opportunities by enforcing hard blocks on insufficient PDD metric coverage or unresolved UAT blockers.

What happens if primary success metric thresholds are missed during user acceptance testing?

Missing primary success metric thresholds triggers a hard block rule that fails the launch readiness recommendation. This prevents unready features from activating when UAT outcome fitness does not meet the product design document requirements.

How does LLO sign-off clarity affect launch readiness for ACE Phase 9 execution?

LLO sign-off clarity determines whether the opportunity passes the quality gate. An LLO no-go sign-off paired with a launch recommendation automatically triggers a hard block, preventing the unready Connect opportunity from proceeding to activation.

Can I grade UAT compilations for different Connect opportunity archetypes like focus groups?

Yes, UAT evaluation adapts grading logic for atomic visit, focus group, and multi-stage opportunity archetypes. Focus group use cases include specialized checks for per-session facilitator and participant sign-offs to ensure complete stakeholder documentation.

What dimensions are evaluated in a UAT results compilation quality gate?

A 6-dimension grading rubric evaluates PDD metric coverage completeness, UAT outcome fitness, LLO sign-off clarity, blocker resolution, evidence citation discipline, and launch readiness recommendation accuracy to validate launch readiness.

Why does an unresolved UAT blocker prevent a feature from launching?

Unresolved UAT blockers trigger a hard block rule because they indicate remaining operational or user experience risks. Enforcing blocker resolution ensures all stakeholder sign-offs are documented and gaps are closed before activation.