plan

Generate structured PRDs and prioritized issue plans for software projects.

50|7|Updated Apr 2, 2026
One-click install
npx skills add https://github.com/Kanevry/session-orchestrator --skill plan-kanevry
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: plan
Source: https://github.com/Kanevry/session-orchestrator/tree/main/skills/plan
Command: npx skills add https://github.com/Kanevry/session-orchestrator --skill plan-kanevry

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill eliminates ad-hoc, unstructured planning by turning stakeholder input and repository context into research-backed, prioritized Product Requirement Documents and corresponding issue plans so teams can ship consistently.

Core Features & Use Cases

  • Multi-mode planning: supports full project kickoffs (new), compact feature PRDs (feature), and data-driven retrospectives (retro).
  • Research-first Q&A engine: dispatches parallel Explore agents before each question wave to synthesize market, baseline, and repo context.
  • Template-driven outputs + VCS integration: fills PRD/retro templates, saves documents to configured paths, runs idempotent repo scaffolding, and creates labeled issues via glab/gh with review gating.
  • Use cases: onboard a new project with repo scaffolding and issues, generate a feature PRD with acceptance criteria and issue breakdown, or run a metrics-backed retro that yields actionable improvements.

Quick Start

Invoke the plan skill in the desired mode (new, feature, or retro) to run a research-first Q&A, generate a PRD or retro document, and produce a proposed issue structure for review.

Frequently Asked Questions about plan

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

FAQPage Schema
How do I generate a structured PRD and issue plan for a new software project?

To generate a structured PRD and issue plan, you can use a research-first Q&A engine that synthesizes market and repository context before filling baseline templates and creating labeled VCS issues via gh or glab.

What is the best way to run a data-driven retrospective that produces actionable issues?

The best way to run a data-driven retrospective is to use a planning mode that integrates baseline templates and repository analysis to yield actionable improvements and propose labeled VCS issues with review gating.

Can I create idempotent VCS issues with review gating from a feature PRD?

Yes, you can create idempotent VCS issues from a feature PRD by using a template-driven output system that runs issue creation via glab or gh, ensuring no duplicates are generated during repository scaffolding.

Does this planning approach work with both GitLab and GitHub for issue creation?

Yes, this planning approach supports issue creation on both GitLab and GitHub by utilizing glab and gh command-line tools to generate labeled issues directly from the finalized Product Requirement Documents.

How to scope a compact feature PRD with acceptance criteria and issue breakdown?

To scope a compact feature PRD, invoke a feature planning mode that uses parallel Explore agents to gather context, fill acceptance criteria templates, and output a proposed issue structure for team review.