By jporre
Pipeline conversacion -> issue -> PR -> merge para SvelteKit: genesis de issues con slices verticales desde la conversacion (b0), triage (b1), worktrees aislados (b1-add-worktree), build (b2), commit (b3), PR (b4), review (b6), orquestadores (b7 single, b8 cluster, b10 epic) y cierre con gate humano (b9). Validado end-to-end en un epic real de 10 sub-issues.
Convierte el HISTORIAL de la conversacion (o un plan/PRD/doc) en uno o varios GitHub issues bien scopeados, sliceados en VERTICAL (tracer-bullet), con dependencias y un epic de tracking — listos para drenar con b10-ship --epic. Es el paso GENESIS del pipeline, antes de b1-triage. Usar cuando el usuario diga "crea el/los issue(s) de esto", "convierte esto en issues/tareas", "arma las tareas en github", "saca los issues de lo que hablamos", "abre los tickets de esta conversacion", "turn this into issues", "create issues from this conversation/plan", "break this into tickets", "split this into vertical slices". Tambien cuando una sesion de diseño/brainstorm/planificacion converge en trabajo concreto que hay que registrar. Antes de crear NADA verifica con el usuario lo que REALMENTE pide (gate humano). NO implementa codigo, NO triagea, NO abre PRs — solo produce la estructura de issues que el resto del pipeline procesa.
Create an isolated git worktree for feature development. Use when the user says /b-add-worktree, asks to create a worktree, wants to start working on a feature in isolation, or mentions needing a separate workspace for a branch. Requires the worktree name as an argument.
Evaluate, label, and respond to GitHub issues before development starts. Use ALWAYS when a GitHub issue number or URL is mentioned as the starting point for work, when asked to "evaluate issue", "triage", "review issue", "revisar issue", "evaluar issue", "evaluar tarea N", "revisar tarea N", "check issue
Orquestador del pipeline completo issue -> worktree cerrado. Encadena b1-triage-issue, b7-issue-to-pr, b6-pr-review y b9-close con gates humanos exactos (triage con dudas, pre-merge, epic-review). Use cuando el usuario diga "ship issue N", "lleva el issue N hasta el merge", "/b10-ship N", "procesa el epic N", "drena el epic". Idempotente: re-correr el mismo comando reconcilia el estado desde GitHub y retoma donde quedo. NO implementa, NO revisa, NO mergea por si mismo — solo decide y encadena skills existentes.
End-to-end SvelteKit feature development. Use ALWAYS when building new features, CRUD screens, forms, dashboards, data pages, or any UI that reads/writes data. Covers planning, implementation (remote functions + Svelte 5 + Drizzle + shadcn-svelte), and browser verification. Prevents React anti-patterns. Triggers on "build feature", "create page", "new screen", "CRUD", "implement", "agregar modulo", "crear pantalla", "necesito una pagina", "add feature for", "build me a". Use even when the user just describes a screen or data operation without saying "feature".
Executes bash commands
Hook triggers when Bash tool is used
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.
A Claude Code plugin that drives a GitHub issue all the way to a merged pull request — triage → isolated worktree → build → screenshots → commit → draft PR → code review → gated merge — by chaining a set of small, focused skills.
It is built for SvelteKit projects (Remote Functions, Svelte 5 runes, Drizzle, shadcn-svelte) and keeps a human in the loop at the points that matter: nothing complex gets built, and nothing ever merges, without a person saying yes.
Throughout this plugin, "task" = GitHub issue. The two terms are used interchangeably.
You give it an issue number. It:
It runs unattended where it is safe to do so, and stops and asks where judgement is required (complex builds, every merge).
Don't have the issues yet? Start one step earlier with b0-conversation-to-issues: it turns the current conversation (a design chat, a brainstorm, a plan) into well-scoped GitHub issues, sliced vertically (tracer-bullet), ordered by dependency, and grouped under an epic — the exact shape b10-ship --epic drains. It verifies what you really want before creating anything.
A few ideas explain the whole design:
b10-ship, b7-issue-to-pr, b8-swarm) do not implement anything themselves — they decide and call the small skills (b1-triage-issue, b1-add-worktree, b2-build-feature, b3-git-commit, b4-pull-request, b6-pr-review, b9-close). The value is the orchestration, the budgets, and the gates.<!-- b7:status -->), and PR review verdicts (<!-- b6:verdict=... -->) are the source of truth. This is why the pipeline is idempotent: re-running the same command reconciles state from GitHub and resumes where it left off (see §13).git worktree on its own branch, with its own dev-server port. Your main working tree is never edited.| Requirement | Why | Check |
|---|---|---|
| Claude Code | The plugin runs inside Claude Code. | claude --version |
gh CLI, authenticated | All GitHub state (issues, labels, PRs, comments) goes through gh. | gh auth status |
| A git repo with a GitHub remote | The pipeline reads issues and opens PRs against origin. | gh repo view |
| A SvelteKit project | b2-build-feature is SvelteKit-specific (Remote Functions, Svelte 5, Drizzle, shadcn-svelte). | — |
| Node + a dev server | The worktree runs vite so screens can be verified. | npm run dev works |
| Google Chrome + the claude-in-chrome extension | Visual screen review drives your real Chrome and reuses your logged-in session. | Extension connected |
If you only want issue → draft PR and you do not need visual review, Chrome is optional — screens are skipped with a note when the dev server or browser is unavailable.
npx claudepluginhub jporre/sveltekit-verticalslices --plugin b-pipelinePermanent coding companion for Claude Code — survives any update. MCP-based terminal pet with ASCII art, stats, reactions, and personality.
Intelligent prompt optimization: injects the right context at the right moment so Claude lands a better first output. Clarifies vague prompts with research-based questions, plus targeted nudges for approach selection, plan readability, workflow routing, background execution, subagent routing, output readability, user-decision questions, and plan-mode assessment
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.
v9.44.1 — Patch release for Gemini environment/version detection and qwen auth gating. Run /octo:setup.
Complete creative writing suite with 10 specialized agents covering the full writing process: research gathering, character development, story architecture, world-building, dialogue coaching, editing/review, outlining, content strategy, believability auditing, and prose style/voice analysis. Includes genre-specific guides, templates, and quality checklists.
Harness-native ECC operator layer - 67 agents, 271 skills, 92 legacy command shims, reusable hooks, rules, selective install profiles, and production-ready workflows for Claude Code, Codex, OpenCode, Cursor, and related agent harnesses