sprint-planning_skill

This skill guides sprint planning, capacity calculations, and backlog grooming, helping you estimate work and select stories within team velocity.
  • JavaScript

1

GitHub Stars

1

Bundled Files

2 months ago

Catalog Refreshed

4 months ago

First Indexed

Readme & install

Copy the install command, review bundled files from the catalogue, and read any extended description pulled from the listing source.

Installation

Preview and clipboard use veilstrat where the catalogue uses aiagentskills.

npx veilstrat add skill sethdford/claude-plugins --skill sprint-planning

  • SKILL.md11.1 KB

Overview

This skill assists teams with sprint planning, backlog grooming, story point estimation, and sprint capacity management. It provides concrete calculations, JQL queries, estimation techniques, and recommendations to create realistic sprint commitments. Use it to turn backlog input into a prioritized, capacity-aligned sprint plan.

How this skill works

I analyze backlog readiness, past velocity, and team availability to calculate sprint capacity and suggest a committed backlog. I use estimation techniques (planning poker, reference stories, three-point) and provide JQL queries to find ready or unestimated issues. I flag dependencies, risks, and offer a sprint goal, stretch goals, and a Definition of Done checklist.

When to use it

  • Before a sprint planning meeting to prepare candidate stories and capacity numbers
  • During backlog grooming to add estimates and acceptance criteria
  • When you need to estimate story points or run planning poker
  • If you want a capacity calculation that accounts for PTO, meetings, and buffers
  • When analyzing velocity trends to set realistic commitments
  • If you need JQL queries to locate ready, unestimated, or carry-over issues

Best practices

  • Use historical velocity (average of last 3–5 sprints) as the primary planning guide
  • Apply a buffer (10–20%) for unexpected work and avoid overcommitment
  • Ensure stories have clear acceptance criteria and are unblocked before committing
  • Prefer relative estimation (Fibonacci) and reference stories for consistency
  • Revisit estimates when scope changes and keep a short grooming cadence

Example use cases

  • Plan a two-week sprint for a team of 6 with one member on PTO and calculate adjusted capacity
  • Run a planning poker session to estimate a set of new features using Fibonacci points
  • Refine backlog items: add acceptance criteria, split epics, and flag dependencies
  • Generate JQL to list unestimated stories or sprint-ready backlog candidates
  • Convert historical sprint completions to a weighted velocity and recommend committed points

FAQ

Use velocity (historical completed points) as the primary guide and adjust with capacity for known availability changes; velocity reflects real throughput.

What estimation scale should we use?

Fibonacci is recommended for relative effort and uncertainty; t-shirt sizes work as a simpler alternative if your team prefers.

Built by
VeilStrat
AI signals for GTM teams
© 2026 VeilStrat. All rights reserved.All systems operational