By mwguerra
Interactive PRD (Product Requirements Document) builder with comprehensive interview-driven discovery, gap analysis, and taskmanager integration.
Document a bug fix with problem analysis, root cause investigation, and regression testing strategy
Create a feature-focused PRD with lighter interview process optimized for new features within existing products
Start a comprehensive PRD interview to transform an idea into a complete Product Requirements Document
Analyze and enhance an existing PRD by identifying gaps and asking targeted questions to fill weak areas
Uses power tools
Uses Bash, Write, or Edit tools
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.
Six plugins for Claude Code. Five compose into one end-to-end workflow — turn an idea into a
verified, shipped change with frontier-grade rigor (requirements → design → tasks → execution →
living docs), with verification that actually enforces before work is called done — and a
sixth (laravel) supplies stack-specific conventions that compose with the rest.
| Plugin | Role |
|---|---|
| maestro | Engineering discipline: always-on behavior skills, phased process (deep-analysis, implementation, deep-work, adversarial-verify, regression), a risk-sized route front door, and lifecycle hooks — six advisory + two enforcing verification gates (hard-block a commit / turn-end until verified). |
| prd-builder | Interview-driven PRDs → docs/prd/. |
| architect | The system-design layer between PRD and tasks → docs/architecture/ + ADRs, adversarially challenged. |
| taskmanager | Decompose a PRD into tasks (SQLite), execute, and prove value via an adversarial done-gate (criteria + regression). |
| scribe | The living docs/ single source of truth: capture → curate → verify, so a stale doc is a defect. |
| laravel | Opinionated Laravel 13 + Filament 5 + Pest 4 conventions — artisan-first, the Filament UI standard, fail-closed multi-tenancy, parallel-safe Pest — applied by default on Laravel projects. The stack idiom that composes with maestro's stack-agnostic discipline. |
Install (from this marketplace):
/plugin marketplace add mwguerra/plugins
/plugin install maestro@mwguerra-plugins prd-builder@mwguerra-plugins architect@mwguerra-plugins taskmanager@mwguerra-plugins scribe@mwguerra-plugins laravel@mwguerra-plugins
Requires jq, sqlite3 (taskmanager's store), and a sha256 tool (sha256sum/shasum/openssl) for maestro's verification gates.
Not sure where to begin? Ask maestro:route — it sizes a request by scope/risk and names
the pipeline to run. See a feature whole: maestro:journey <slug> renders one feature's full
path across the suite (idea → PRD → design → tasks → verified → regression-clean → shipped).
Greenfield (new project):
scribe:init — scaffold the docs/ single source of truth.prd-builder:prd — interview an idea into docs/prd/.architect:design — turn the PRD into docs/architecture/ + ADRs.taskmanager:init → taskmanager:plan docs/prd/prd-<slug>.md → taskmanager:run.scribe:sync — fold the work into living docs; scribe:verify checks docs against the code.Brownfield (existing code): start with scribe:init (it reverse-engineers docs/ via a
maestro deep-analysis pass), then use maestro:route per task. For a quick change, just
maestro:implement; for an audit, maestro:deep-analysis.
verify_commit_gate hard-blocks git commit
until the change is recorded as tests-green and adversarially checked in .maestro/ledger.log
(or a logged waiver is filed); verify_stop_gate blocks ending a turn with unverified work. One
command satisfies it: bash <maestro>/hooks/lib/ledger.sh pass all "<what you ran + what survived>".
See the verify-gates smoke test. To disable, remove the
gate entries from maestro/hooks/hooks.json.docs/ is the contract. Every plugin reads docs/ first and writes it after; the
doc-verifier checks each claim against the code. The canonical layout lives in
scribe/skills/documentation-discipline/references/docs-layout.md.Per-plugin READMEs: maestro · prd-builder · architect · taskmanager · scribe · laravel. Suite architecture & conventions: CLAUDE.md.
bash taskmanager/tests/test_sql_queries.sh # SQL layer (queries, views, done-gate)
bash taskmanager/tests/test_lifecycle_e2e.sh # full init→plan→run→verify lifecycle
bash maestro/tests/test_verify_gates.sh # the enforcing gates + ledger
npx claudepluginhub mwguerra/plugins --plugin prd-builderProactive Pest 4 testing for PHP, Laravel, Livewire, and Filament apps. Auto-generates tests for models, controllers, policies, and Livewire components. Analyzes coverage gaps and runs test suites with detailed reporting.
Docker-local (mwguerra/docker-local) CLI expert for Laravel Docker development environments. Provides 50+ commands for managing PHP, MySQL, PostgreSQL, Redis, MinIO, Traefik, and multi-project isolation. Diagnoses issues, checks conflicts, manages databases, queues, Xdebug, and guides users through setup and troubleshooting.
Manage an Obsidian vault as your development knowledge base and automatic work journal. Auto-captures commits, tasks, and Claude Code components with structured frontmatter.
Expert FilamentPHP v4 assistant with complete official documentation. Generates resources, forms, tables, actions, widgets, infolists, and Pest tests following v4 patterns. Includes diagnosis and troubleshooting.
Create publication-ready technical articles and social media posts (LinkedIn, Instagram, X/Twitter) with author voice profiles, web research, runnable code examples, and multi-language output. Supports interactive single-article creation, social media post generation, or autonomous batch processing from a task queue.
Upstash Context7 MCP server for up-to-date documentation lookup. Pull version-specific documentation and code examples directly from source repositories into your LLM context.
AI-powered wiki generator for code repositories. Generates comprehensive, Mermaid-rich documentation with dark-mode VitePress sites, onboarding guides, deep research, and source citations. Inspired by OpenDeepWiki and deepwiki-open.
Claude + Obsidian knowledge companion. Sets up a persistent, compounding wiki vault (Karpathy's LLM Wiki pattern). v1.7 "Compound Vault" + v1.8 methodology modes close 5 of 5 priority gaps from the May 2026 compass artifact. Ships: substrate alignment with kepano/obsidian-skills, default Obsidian CLI transport, hybrid retrieval (contextual prefix + BM25 + cosine rerank per Anthropic's Sept 2024 research), per-file advisory locking for multi-writer safety, pre-commit verifier agent, AND methodology modes (LYT / PARA / Zettelkasten / Generic) for first-class organizational support no other Claude+Obsidian competitor offers. v1.7.x audit closure: every BLOCKER + HIGH + MEDIUM + LOW finding from the v1.7.0 audit is CLOSED or DEFERRED-with-rationale. Optional DragonScale Memory extension (log folds, deterministic addresses, semantic tiling lint, boundary-first autoresearch).
Complete AI coding workflow system. Self-correcting memory + persistent FTS5-indexed research wikis + auto-research loop + multi-LLM council on a single SQLite store. 33 skills, 8 agents, 22 commands, 37 hook scripts across 24 events. Cross-agent via SkillKit.
Comprehensive C4 architecture documentation workflow with bottom-up code analysis, component synthesis, container mapping, and context diagram generation
Build and maintain an LLM-curated personal knowledge base in your project — Andrej Karpathy's LLM Wiki pattern, designed to scale to thousands of pages without becoming a context bottleneck. Now with an optional compiled graph layer for typed, provenance-backed relationships.