storywright
Turns vague prompts into Jira-ready user stories for Claude Code.
About
storywright is a pure-Markdown skills pack that converts ambiguous inputs — half-baked stories, screenshots, raw backlogs — into INVEST-checked user stories with Given/When/Then acceptance criteria and Fibonacci estimates. Every story ships as two files: a PM-facing version with zero technical detail and a dev-facing version with edge cases, risks, and analytics events.
Honest limitations: it is deliberately project-less, so technical specifics in the dev file are domain-knowledge inferences marked as assumed, never scraped from your repo. Splits always wait for your approval, which keeps control but slows bulk backlog processing.
What it can do
- Ambiguous-input to user-story generation
- INVEST checklist and story splitting
- PM/dev two-file output
- Batch backlog processing
Setup
- Run npx skills add pavp/storywright (detects your agent automatically).
- Or clone the repo into your agent's skills directory, e.g. ~/.claude/skills/storywright.
- Describe the task in plain language; the router detects generate/refine/split/batch intent.
Prerequisites
A SKILL.md-compatible agent (Claude Code, Cursor 2.4+, Copilot agent mode, or Codex CLI).
Use cases
Works with
Trust score — 6/10
Scored 6/10 (metrics tier, metrics-v1). Evidence: 0 GitHub stars observed, but 113 commits and 52 releases show real maintenance; Clean-room MIT rewrite with methodological credits; CI, semantic-release, and committed examples; Project-less by design: dev-file technicals are marked assumptions, never scraped. License: MIT.
★ 0 GitHub stars
How the trust score is built
Full methodology →- Adoption · stars/downloads, log-scaled vs peers
- 3.0/10
- Maintenance · recency, releases, issue load
- 7.0/10
- Openness · license + docs
- 9.0/10
- Manual review · sanity read + red-flag check
- 6.0/10
- · 0 GitHub stars observed, but 113 commits and 52 releases show real maintenance
- · Clean-room MIT rewrite with methodological credits; CI, semantic-release, and committed examples
- · Project-less by design: dev-file technicals are marked assumptions, never scraped
Sources
Every fact above was checked against these sources. Where a claim comes from the provider and couldn't be independently verified, the text says so.