Ticket Writer

Draft, write, structure, or improve engineering tickets — user stories, bug reports, spikes, feature requests — for any tracker (Jira, Linear, GitHub Issues, Shortcut, Asana). Enforces a problem-first structure (outcome → context → constraints → acceptance criteria → dependencies → open questions) drawn from Daniel Starling's "Anatomy of a Software Ticket", Bill Wake's INVEST and SMART, and Marty Cagan / SVPG's "Empowered Product Teams". Actively rejects the standard anti-patterns — prescribed solutions / "files to change", missing outcome, untestable acceptance criteria, PM-supplied estimates

5 stars 2 forksWriting & Content Plugin marketplace

Install

Claude Code plugin
/plugin marketplace add vnovakovits/claude-skills

The repo is a Claude Code plugin marketplace. Run /plugin afterwards to pick the plugin that includes this skill.

skills CLI (Claude Code, Cursor, Codex and more)
npx skills add vnovakovits/claude-skills --skill ticket-writer
Manual install
git clone --depth 1 https://github.com/vnovakovits/claude-skills.git /tmp/claude-skills
mkdir -p ~/.claude/skills
cp -r /tmp/claude-skills/plugins/engineering-practices/skills/ticket-writer ~/.claude/skills/ticket-writer

Personal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.

From the SKILL.md

# Ticket Writer

Apply this skill when writing or reviewing any engineering ticket — story, bug, spike, or feature request — for any tracker. The goal is a ticket that gives an *empowered team* a problem worth solving and the constraints that bound it, then trusts the team to find the solution.

## Core Philosophy

**Problems, not features.** Empowered teams are "given problems to solve rather than features to build" (Marty Cagan, SVPG). A good ticket describes the outcome and the constraints — not the implementation.

**Outcome before instructions.** Every ticket leads with one sentence a non-engineer can read: the business result we'll know we achieved. If you can't write the outcome, the work isn't ready to be a ticket.

**Acceptance criteria are testable, or they're not criteria.** "Works correctly" / "is fast" / "looks good" are opinions. Replace with concrete thresholds, examples, and yes/no checks.

**A ticket is a placeholder for a conversation, not a contract.** Negotiable. Refined together. The detail belongs on the *problem and examples*, not on which files to edit (Bill Wake — INVEST: Negotiable).

**The team owns the estimate.** Estimates supplied by the requester anchor the team and erode trust. If an estimate exists at *Ready* time, the team wrote it.

**Hidden dependencies kill flow.** A ticket with unresolved blockers should not be *Ready* — it will stall mid-sprint. Surface them early, name them, schedule them.

## When to use this skill
Read the full skill on GitHub

Details

Skill name
ticket-writer
Path
plugins/engineering-practices/skills/ticket-writer/SKILL.md
License
MIT
Repo updated
16 November 2026

FAQ

What does the Ticket Writer skill do?

Draft, write, structure, or improve engineering tickets — user stories, bug reports, spikes, feature requests — for any tracker (Jira, Linear, GitHub Issues, Shortcut, Asana). Enforces a problem-first structure (outcome → context → constraints → acceptance criteria → dependencies → open questions) drawn from Daniel Starling's "Anatomy of a Software Ticket", Bill Wake's INVEST and SMART, and Marty Cagan / SVPG's "Empowered Product Teams". Actively rejects the standard anti-patterns — prescribed solutions / "files to change", missing outcome, untestable acceptance criteria, PM-supplied estimates

How do I install the Ticket Writer skill?

Claude Code plugin: /plugin marketplace add vnovakovits/claude-skills. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.

Is Ticket Writer popular?

It lives in vnovakovits/claude-skills, which has 5 GitHub stars and 2 forks.

Related skills

Accidental Cio

5

vnovakovits/claude-skills

Apply Scott Millett's "The Accidental CIO — A Lean and Agile Playbook for IT Leaders" (Wiley, 2024) when designing or reviewing how a technology organisation decides, funds, governs and delivers work. Covers the five components of an adaptive IT operating model (organised, work, govern, talent, lead) and its four themes (outcomes over output, intrinsic motivation, being not doing agile, manage flow not people); matching method and governance to context via Cynefin and Wardley evolution; governance as demand management + funding + measurement + decision rights, shifting from project funding to

Frontend & Design

Agent Retro

5

vnovakovits/claude-skills

Run a retrospective on a coding-agent session and improve the agent's environment, not the code. Combines Derby & Larsen's five-stage retrospective, Shigeo Shingo's poka-yoke (turn a mechanical mistake into a check that makes it impossible), and Matt Pocock's retro categories — navigation, automated checks, coding standards, steering files, tool economy, information access. Covers mining the session transcript for corrections, wrong turns and slow searches; deciding where each fix belongs (analyzer, hook, CI, reviewer standards, CLAUDE.md pointer, skill, doc or memory); the no-op test for stee

AI, LLMs & Agents

API Design

5

vnovakovits/claude-skills

Design APIs that are clear, evolvable, and idiomatic to their protocol — covering REST (Fielding, Richardson Maturity Model, Massé), GraphQL, gRPC/protobuf, versioning strategies, pagination, error responses (RFC 7807 Problem Details), idempotency, authentication, documentation (OpenAPI), and the pragmatic trade-offs between RESTful purity and developer ergonomics. Use when designing a new endpoint, choosing between REST/GraphQL/gRPC, defining versioning, structuring error responses, deciding pagination strategy, or evaluating an existing API's evolvability.

Software Development

Update Workspace Map

8

Freddy-CHEN-ux/00_claude_skills

Validate workspace-map.md accuracy against actual 04-workspace/ structure (3 levels deep). Load when user says "validate workspace map", "update workspace map", "check workspace map", or from close-session. Ensures deep structure validation with comprehensive documentation.

Writing & Content

Splitting User Stories

5

vnovakovits/claude-skills

Split user stories into small, valuable, independently-shippable slices using INVEST (Bill Wake), Richard Lawrence's 9-pattern flowchart, Mike Cohn's SPIDR, Gojko Adzic's hamburger method, Jeff Patton's story mapping, and Henrik Kniberg's MVP analogies. Use when a story is too big to ship in one sprint, when "we'll do it all at once" feels risky, when carving an MVP, when planning incremental delivery, or when a story has hidden complexity that needs to be exposed in slices.

Writing & Content

User Story Mapping

5

vnovakovits/claude-skills

Apply Jeff Patton's User Story Mapping (O'Reilly, 2014) — arranging user stories into a two-dimensional map that preserves the user's narrative journey, which a flat backlog destroys. Covers the map's anatomy (backbone and ribs; activities, tasks, details), the two axes (narrative flow left-to-right, priority/necessity top-to-bottom), the core philosophy (shared understanding over documents; minimize output, maximize outcome and impact), running a mapping workshop (frame, map breadth-first, explore alternatives/exceptions, distill a backbone, slice), slicing releases into a walking-skeleton MV

Writing & Content

Browse the most popular Claude skills, all writing & content skills, or write your own with the skills generator.