13-prioritisation-agent — Experiment Prioritisation

Rank experiments using C×I×S scoring and generate Jira stories after PM approval.

10|1|Updated Apr 6, 2026
One-click install
npx skills add https://github.com/lilyydavid/ai-diagnostic-loop-mirror --skill 13-prioritisation-agent-experiment-prioritisation
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: 13-prioritisation-agent — Experiment Prioritisation
Source: https://github.com/lilyydavid/ai-diagnostic-loop-mirror/tree/main/shared/agents/13-prioritisation-agent
Command: npx skills add https://github.com/lilyydavid/ai-diagnostic-loop-mirror --skill 13-prioritisation-agent-experiment-prioritisation

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

The prioritisation agent connects diagnosis outputs to experiments, scores and ranks them so PM can decide which to advance, ensuring a consistent, auditable decision process across cycles.

Core Features & Use Cases

  • Connects cycle signals, hypotheses, and experiment designs into a traceable prioritisation chain.
  • Applies C×I×S scoring to rank experiments and flags sprint-ready candidates for PM approval.
  • Generates Jira stories and publishes a Confluence summary for stakeholder visibility after PM confirmation.

Quick Start

Run the intelligence loop to trigger prioritisation and generate sprint-ready experiments for PM review.

Frequently Asked Questions about 13-prioritisation-agent — Experiment Prioritisation

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

FAQPage Schema
How do I rank experiments and gate PM approvals in Jira?

Experiment prioritisation maps signals and hypotheses into a ranked output, applying C×I×S scoring to flag sprint-ready candidates and gating Jira ticket creation until PM approval is confirmed.

What is the C×I×S scoring method for experiment prioritisation?

C×I×S scoring is the mechanism used to rank experiments within the prioritisation chain, evaluating candidates based on cycle signals to determine which are sprint-ready for PM review.

How do I generate Jira stories and Confluence summaries from experiment hypotheses?

After PM confirmation, the prioritisation agent automatically generates Jira stories and publishes a Confluence summary to provide stakeholder visibility across the experiment cycle.

Does experiment prioritisation require intelligence loop outputs to rank sprint-ready candidates?

Yes, prioritisation ingests intelligence loop signals, agent scores, and lineage history to compute experiment priority, validating inputs against the code-grounding audit log before gating PM approvals.

What's the best way to maintain an auditable decision process for agile experiment prioritisation?

Connect cycle signals, hypotheses, and experiment designs into a traceable prioritisation chain that validates inputs against audit logs and enforces PM approvals, ensuring consistent and auditable decisions.