user-story-skills
claude27 skills and slash commands for user story refinement across the full lifecycle — discovery, refinement, planning, QA, compliance, and post-release.
27 skills · 27 commands
Generate RenPy visual novels for desktop and browser: a brief with a branch outline and required paths, a native RenPy scaffold with save/load, menus and ending galleries, and a write, test, review and refine loop with independent editorial review. Optional scene art uses the Polyptych narrative pipeline through three human gates. Build desktop applications and a browser/PWA release from the same story, with optional GitHub Pages publishing.
Plugin visual-novel-generator from marketplace jdinkla-marketplace in jdinkla/claude-marketplace. Commands read from the repo's manifest — 1 month ago.
No skills, commands, agents, hooks or MCP servers were found in the standard plugin folders.
27 skills and slash commands for user story refinement across the full lifecycle — discovery, refinement, planning, QA, compliance, and post-release.
27 skills · 27 commands
Prompts for software architecture, DDD, ADRs, QA, and content processing: ADR create/refine/review, DDD analysis, tech-debt & test audits, session handover, repo setup (just, backlog), and markdown summarize/condense/translate. 15 slash commands.
15 commands
A software factory: drives a product idea from an empty directory to a built, tested, QA'd implementation through gated agent stages — discover, specify (PRD + BDD/Cucumber), scaffold, plan with independent review, backlog-driven build loop, and final QA. Ships verified Kotlin + Cucumber, Rust + Cucumber, and TypeScript (Node) + Cucumber stack templates.
A dark (lights-out) website factory for Jekyll sites: a person is present exactly twice — the brief at the start and the publish at the end — and every gate between them is held by an LLM judge on a pinned model floor. Brief, a design.html mock judged by a fable design agent instead of a human, scaffold, a build → shoot → judge → refine loop with independent visual and editorial agents and an explicit stall exit, then a stop: a screenshot contact sheet, a review packet and a running preview, built so one reviewer can approve or reject in ten minutes without reading the repo. Every generated site carries an append-only gate ledger recording what each gate caught — including the human's own catch at publish — which the retro skill reads across runs to find escapes and idle gates. Thin plugin: consults website-factory's craft knowledge and jekyll-lean template at runtime rather than vendoring copies.
A demo studio: builds visual idea demos (three.js / WebGL, one self-contained HTML page) through an iterate-and-judge pipeline — brief with a shot list as definition of done, scaffold with a deterministic observation harness and headless Playwright capture, then a build → shoot → judge → refine loop where an independent vision agent critiques the rendered screenshots, capped rounds, human feel check at the end. Sibling of first-factory for exploratory visual work.
A sim factory: drives a deterministic browser-sim idea (turn-based games, interactive models — TypeScript, no backend) from an empty directory to a playable, verified app through gated stages — brief with mission list and screen inventory as definitions of done, engine spec (PRD + BDD + missions), a human-gated design.html mock, a verified scaffold with a pure engine kernel and observation harness, then a two-phase build: hard-gated engine (floor + independent engine-reviewer) followed by a judged UI loop (visual + editorial agents, capped rounds, human play check). Missions are executable acceptance tests; a Playwright gate plays them through the real UI. Optional GitHub Pages publish. Sibling of first-factory, demo-factory, and website-factory.
Talk like caveman. Cut filler. Keep technical details explicit.
22 skills · 1 command · 3 agents · hooks
Persistent memory for Claude Code: the next session starts where the last one left off.
29 skills · 1 MCP server · hooks
tasteskill 2.5.1: professional company websites at the figma.com and x.ai level, with one section per screen, real photographs, real product UI, effects kept for tech and gaming pages, and a real-browser checker and finish gate.
1 skill
Open-source AI job search that runs locally in your AI coding CLI: scan job portals, evaluate listings into a structured A-H report with a 1-5 score, tailor your CV, track applications
5 skills · hooks
Cross-session memory and token savings for coding agents.
6 skills · 1 agent · 1 MCP server · hooks
Package any website or local web build into a lightweight desktop app with Pake CLI.
1 skill
This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.