By jdinkla
27 skills and slash commands for user story refinement across the full lifecycle — discovery, refinement, planning, QA, compliance, and post-release.
Check a user story against WCAG 2.2 — find accessibility issues with cited criteria, conformance level, impact, and fixes.
Assess whether a user story is suitable for implementation by an autonomous AI agent across 8 criteria, with a suitability score.
Propose 2–4 alternative technical/UX approaches to deliver the same business value, with tradeoffs and a recommendation.
Pre-draft documentation updates for a user story — overview, user guide, API reference, configuration, changelog, in markdown.
Audit a user story for algorithmic bias — bias types, proxy variables, protected groups, fairness metrics, regulatory requirements.
Check a user story against WCAG 2.2 standards — find accessibility issues with cited WCAG criteria, conformance level (A/AA/AAA), impact, affected users, code examples, and assistive-tech considerations. Use when the user asks for an a11y review, accessibility check, WCAG audit, or to catch a11y issues before implementation.
Assess whether a user story is suitable for implementation by an autonomous AI agent (Claude with tool use, etc.) — scores across 8 criteria including decomposability, tool availability, determinism, and observability. Use when the user asks "can an AI agent build this?", wants to decide between human vs. agent implementation, or is planning agent workloads.
Propose 2–4 alternative technical/UX approaches to deliver the same business value, with tradeoff analysis, effort estimates, and a recommendation. Use when the user asks "what are other ways to solve this?", wants to explore options before committing to an approach, or needs a build-vs-buy-vs-hybrid comparison.
Pre-draft documentation updates for a user story — Overview, User Guide, API Reference, Configuration, Changelog — ready for Confluence, Notion, README, or API docs. Use when the user asks "draft the docs for this", wants release notes, or needs markdown-ready documentation before a feature ships.
Audit an AI/ML or data-driven user story for algorithmic bias and discrimination — identify bias types, proxy variables, protected groups affected, fairness metrics, regulatory requirements (EU AI Act, NYC LL144, EEOC, etc.), and testing recommendations. Use when the user asks about algorithmic fairness, bias audit, AI ethics review, or discrimination risk on a feature.
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
Claude Code skills and slash commands for user story refinement across the full lifecycle — from discovery through post-release.
Each analysis is available as:
.claude/skills/story-<name>/SKILL.md) — Claude auto-selects it based on intent, e.g. "review this story for INVEST".claude/commands/story-<name>.md) — explicit invocation, e.g. /story-invest <story text>This repository is a Claude Code plugin. It is listed in jdinkla-marketplace — inside Claude Code:
/plugin marketplace add jdinkla/claude-marketplace
/plugin install user-story-skills@jdinkla-marketplace
After install, all 27 skills auto-trigger by intent and all 27 /story-* slash commands are available.
Maintainers of other marketplaces: add an entry like the following to your
marketplace.jsonpluginsarray to list this plugin:{ "name": "user-story-skills", "source": { "source": "github", "repo": "jdinkla/user-story-skills" }, "description": "27 skills and slash commands for user story refinement." }The
versionfield is intentionally omitted —plugin.jsonalready pins it, and setting it in both places silently letsplugin.jsonwin.
If you prefer to drop the files directly into a project:
git clone https://github.com/jdinkla/user-story-skills.git /tmp/uss
mkdir -p .claude/skills .claude/commands
cp -r /tmp/uss/skills/* .claude/skills/
cp /tmp/uss/commands/*.md .claude/commands/
For a single skill:
cp -r /tmp/uss/skills/story-invest .claude/skills/
cp /tmp/uss/commands/story-invest.md .claude/commands/
For global install across all projects, copy into ~/.claude/skills/ and ~/.claude/commands/ instead.
Once installed, either describe what you want and let Claude pick the skill…
review this user story against INVEST criteria
<story text>
…or call the slash command directly:
/story-invest /story-gherkin @stories/login.md /story-edge-cases
Every skill accepts the story via:
args to the skill / slash command@path/to/story.md)All 27 analyses, grouped by lifecycle stage:
| Skill | Purpose |
|---|---|
story-persona-empathy | Simulate 2–4 user personas and critique whether the story actually solves their pain points |
story-user-journey | Map the story to 1–3 broader user journeys and surface gaps, dead ends, broken handoffs |
| Skill | Purpose |
|---|---|
story-invest | Score against INVEST (Independent, Negotiable, Valuable, Estimable, Small, Testable) with coaching notes |
story-kickoff | Development-readiness checklist across Clarity, Scope, Dependencies, Design, Technical, Team |
story-questions | Surface unknowns, assumptions, and clarifying questions by category and priority |
story-business-value | Articulate user, business, strategic, and technical value + success metrics |
story-summary | 30-second quick-reference synopsis for handoff, docs, or backlog scanning |
story-alternative-solutions | Propose 2–4 alternative technical/UX approaches with tradeoff analysis |
story-stakeholder-impact | Identify downstream teams, communication plan, and timing |
story-requirements-breakdown | Split into 3–7 independently deliverable sub-stories with dependencies |
story-nonfunctional | Extract 6–12 measurable NFRs (performance, scalability, security, reliability, a11y, …) |
story-gherkin | Translate to 2–5 BDD scenarios in Given/When/Then form |
| Skill | Purpose |
|---|---|
story-implementation | 6–12 technical tasks broken down by phase, with effort estimates and risks |
story-agentic-ai | Score suitability for autonomous AI-agent implementation across 8 criteria |
story-auto-documentation | Pre-draft Confluence / Notion / README / API doc updates |
story-synthetic-data | Specify test data entities, scenarios, constraints, and seed SQL |
npx claudepluginhub jdinkla/claude-marketplace --plugin user-story-skillsPrompts for software architecture, DDD, ADRs, QA, and content processing — ADR create/refine/review, DDD analysis, tech-debt and test audits, plus markdown/X summarizers.
Comprehensive skill pack with 66 specialized skills for full-stack developers: 12 language experts (Python, TypeScript, Go, Rust, C++, Swift, Kotlin, C#, PHP, Java, SQL, JavaScript), 10 backend frameworks, 6 frontend/mobile, plus infrastructure, DevOps, security, and testing. Features progressive disclosure architecture for 50% faster loading.
Develop, test, build, and deploy Godot 4.x games with Claude Code. Includes GdUnit4 testing, web/desktop exports, CI/CD pipelines, and deployment to Vercel/GitHub Pages/itch.io.
Comprehensive PR review agents specializing in comments, tests, error handling, type design, code quality, and code simplification
Comprehensive feature development workflow with specialized agents for codebase exploration, architecture design, and quality review
A growing collection of Claude-compatible academic workflow bundles. Covers scientific figures, manuscript writing and polishing, reviewer assessment, citation retrieval, data availability, paper reading, literature search, response letters, paper-to-PPTX conversion, and evidence-grounded Chinese invention patent drafting. Rules are organized as reusable skill folders with explicit workflows and quality checks.
Tools to maintain and improve CLAUDE.md files - audit quality, capture session learnings, and keep project memory current.