great-minds

Plugin great-minds from marketplace great-minds-constellation in sethshoultes/great-minds-constellation. Commands read from the repo's manifest — 1 month ago.

Skills (23)

• agency-anatomy

  Generate or regenerate the .wolf/anatomy.md file index with token estimates for the current project.

• agency-board-review

  Run a full board review with 4 board members reviewing a project, decision, or deliverable in parallel from different strategic angles. Produces individual reviews and a consolidated board verdict.

• agency-content

  End-to-end content pipeline — research to published blog post with companion video. Uses the full creative team (Maya, Rick, Margaret, Steve, Aaron, Shonda, Jony) and produces a live article + YouTube video.

• agency-crons

  Install the autonomous cron system — pipeline runner, heartbeat, QA, git monitor, dispatch, dream. The pipeline runner IS the autonomous loop — Claude agents don't loop, the cron does.

• agency-daemon

  Install and run the Great Minds autonomous daemon — a single persistent Node.js process that watches for work and runs the full GSD pipeline. Replaces the cron-based scripts with a unified daemon. Use when setting up a new agency project's runtime infrastructure or restarting the daemon after a rebo

• agency-debate

  Run a structured 2-round debate between Steve Jobs and Elon Musk on a topic, PRD, or decision. Includes Rick Rubin essence check. Produces rounds of positions, challenges, locked decisions, and a distilled essence file.

• agency-execute

  Wave-based parallel execution of XML task plans. Spawns fresh-context sub-agents for each task, runs independent tasks in parallel waves, and creates atomic git commits per task. Inspired by GSD (Get Shit Done) methodology. When the Superpowers plugin is installed, this skill composes with `superpow

• agency-launch

  Launch the Great Minds agent swarm using Agent tool with worktree isolation. No tmux dispatch — proven unreliable. Phil orchestrates from admin, spawns sub-agents via Agent tool.

• agency-memory

  Query and manage the Great Minds agency vector store — semantic search over memories stored in SQLite with embeddings. Subcommands - search, add, list, import, export, stats. Filters by type (learning, decision, board-review), agent, project. Use to recall prior decisions, learnings, or critiques ac

• agency-plan

  Structured phase planning with XML task plans. Researches the codebase, generates atomic task plans in XML format, verifies them against requirements, and organizes them into dependency-aware execution waves. Inspired by GSD (Get Shit Done) methodology.

• agency-publish

  Review and publish blog content. Maya writes, Rick Rubin strips to essence, Jony Ive reviews layout, Oprah checks accessibility, then publish.

• agency-setup

  Interactive project initialization wizard — scans the working directory, asks targeted questions, and generates .great-minds.json, STATUS.md, SCOREBOARD.md, TASKS.md, and a cron reference script.

• agency-ship

  Ship phase — merge feature branches to main, update status and scoreboard, write ship report, save learnings to memory, clean up branches, and verify deploy. Final phase in the GSD pipeline.

• agency-start

  Initialize a Great Minds agency project. Creates all system files, directory structure, memory store, crons, and sets the project to idle state ready for a PRD.

• agency-status

  Comprehensive agency health check — pipeline state, cron health, memory stats, DO server status, GitHub issues/PRs, and recent commits.

• agency-tokens

  View token usage statistics from the token ledger — session, project, agent, and lifetime totals.

• agency-verify

  UAT verification of executed phase work. Runs acceptance tests against requirements, spawns debug agents for failures, generates a verification report with SHIP/FIX/BLOCK recommendation. Inspired by GSD (Get Shit Done) methodology.

• agency-video

  Create product videos using Aaron Sorkin (script), Shonda Rhimes (narrative review), Jony Ive (visual review), Remotion (React video framework), and OpenAI TTS (voiceover). Full pipeline from concept to rendered MP4.

• constellation-assemble

  Integrate the parallel Build phase outputs into a single assembled artifact, verifying the build-contract first and flagging any contradictions. Reads build-contract.md, every build/*.md file, and the plan's assembled-artifact template. Dispatches a functional implementer (not a named persona) to do

• constellation-start

  The discoverable entry point for newcomers to the Great Minds constellation. Asks 2-3 questions about project shape and routes to the right plugin's project-init skill or channels Phil Jackson for ambiguous projects. Always ensures the bible at .great-authors/project.md exists — that's the shared sp

• constellation-status

  Single-glance project status for a constellation pipeline run. Reads the plan, checks which build artifacts have been produced, surfaces what phase the project is in, lists active background tasks, and computes elapsed time. Use during a parallel-dispatch run to answer the question 'what's the swarm

• scope-check

  Compare current work against the original plan to detect scope creep. Reads .planning/*-PLAN.md or prds/*.md, checks git diff --stat and recent commits, maps each changed file to a planned deliverable, flags unplanned work, and reports drift percentage. Use during execution when context-guard signal

• team-build

  Phil Jackson's pre-flight skill — given a project brief, recommends which constellation plugins to enable and which personas to dispatch at each pipeline phase. Reads the project brief, inspects what plugins are installed, maps the project shape to the constellation's pipeline (discovery → debate →

Subagents (22)

• aaron-sorkin-screenwriter

  Use this agent for video scripts, demo walkthroughs, tutorial content, launch videos, and workshop materials. Aaron Sorkin brings razor-sharp dialogue, precise pacing, and the rare ability to make technical work feel urgent and alive. Use when you need to explain something visually, create compellin

• backend-engineer

  Implement backend logic — APIs, services, business logic, data access, integrations. Use when a director (Elon, Steve, Margaret) dispatches implementation work that involves server-side code, REST/GraphQL endpoints, business logic, queue handlers, scheduled jobs, or third-party API integrations. Ret

• code-reviewer

  Review code for craft, convention, and obvious correctness. Use when Margaret, Steve, or Elon dispatches a pre-merge review. Returns a structured findings list — what's good, what's wrong, what's worth flagging. Functional-role implementer (Haiku tier).

• database-architect

  Design and modify database schemas, write migrations, optimize queries, manage indexes. Use when Elon dispatches data-layer work — new tables, schema changes, query performance, indexing strategy, or migration planning. Returns production-grade schema with migration scripts and rollback plan. Functi

• devops-engineer

  Implement CI/CD, infrastructure, observability, deploys. Use when Elon or Margaret dispatches infra work — GitHub Actions workflows, deploy scripts, environment setup, monitoring/logging wiring, cron jobs, container configs. Returns production-grade configs with clear rollback paths. Functional-role

• documentation-writer

  Write or update technical documentation — README sections, in-code docs, API references, user guides, in-product help text. Use when a director (typically Steve, sometimes Elon or Margaret) dispatches doc work. For brand voice, marketing copy, or anything that needs warmth/rhythm/dignity, use Maya A

• elon-musk-persona

  Use this agent when the user wants to interact with an Elon Musk-style persona, get advice or perspectives channeling Elon Musk's mentality, brainstorm with a first-principles thinker, or discuss topics like technology, space, AI, electric vehicles, entrepreneurship, and ambitious ventures from Musk

• frontend-developer

  Implement frontend code — React components, UI logic, accessibility wiring, responsive layouts, client-side state. Use when a director (Steve, Elon, Margaret) dispatches implementation work that involves UI code, component composition, styling, accessibility, or browser-side behavior. Returns produc

• jensen-huang-board

  Use this agent for strategic board-level reviews, competitive analysis, ecosystem/platform thinking, data moat strategy, pricing model evaluation, and 'what would Jensen Huang do?' perspectives. Jensen thinks in platforms, ecosystems, and compounding advantages. He spots risks the builders are too c

• jony-ive-designer

  Use this agent for visual design reviews, UI/UX audits, design system work, and product aesthetics. Jony Ive is the eye — he sees what's wrong with a layout before anyone can articulate it. Use for design critiques, component design, responsive layouts, visual polish, and making things feel 'inevita

• marcus-aurelius-mod

  Use this agent for orchestration, conflict mediation, project management, quality gates, and neutral facilitation. Marcus is the Stoic moderator — calm under pressure, fair-minded, decisive when needed. Use when agents disagree, when work needs coordinating, or when someone needs to make the call.\n

• margaret-hamilton-qa

  Use this agent for QA, testing, code review, and quality assurance. Margaret Hamilton invented software engineering at MIT, wrote the Apollo guidance computer code, and pioneered error detection and recovery. Use for test suites, build verification, regression testing, accessibility audits, security

• maya-angelou-writer

  Use this agent for copywriting, brand storytelling, customer-facing messaging, email sequences, and any writing that needs to connect emotionally. Maya writes with warmth, rhythm, and dignity. Use for landing pages, onboarding copy, email campaigns, error messages, and any text a customer reads.\n\n

• oprah-winfrey-board

  Use this agent for board-level reviews focused on audience connection, storytelling clarity, accessibility, onboarding experience, messaging, and the human side of product decisions. Oprah asks the questions nobody else asks — the ones that start with 'but would a real person actually...

• phil-jackson-orchestrator

  Use this agent for orchestration, system coordination, cron management, agent dispatch, resource optimization, and keeping the swarm running efficiently. Phil Jackson is the Zen Master — he manages legendary egos, never scores a point, but wins championships by making the system work. Use when you n

• rick-rubin-creative

  Use this agent for creative direction, brand voice review, content editing, and stripping things down to their essence. Rick Rubin is about reduction — removing everything that isn't essential until only the truth remains. Use for copy reviews, brand audits, creative blocks, and 'is this real?' gut

• sara-blakely-growth

  Use this agent for growth strategy, conversion optimization, scrappy marketing, small business empathy, and 'how would a real founder sell this?' thinking. Sara built Spanx from $5K to a billion-dollar brand with zero advertising budget. Use for go-to-market plans, landing page conversion, pricing p

• security-auditor

  Audit code, endpoints, and configurations for security issues. Use when Margaret or Elon dispatches a pre-merge or pre-deploy security review — auth gaps, input validation, secrets exposure, error leaking, OWASP-class vulnerabilities. Returns a structured findings report with severity levels. Functi

• shonda-rhimes-board

  Use this agent for retention strategy, engagement hooks, narrative arcs, and 'what keeps people coming back' analysis. Shonda Rhimes is the master of the cliffhanger — she built Shondaland by understanding that engagement is narrative, not features. Use when reviewing onboarding flows, notification

• steve-jobs-visionary

  Use this agent when the user wants feedback, ideas, or decisions filtered through a Steve Jobs-like mentality — focusing on simplicity, taste, user experience, bold product vision, and uncompromising quality. This includes product critiques, design reviews, strategic thinking, pitching ideas, or whe

• test-engineer

  Write tests — unit, integration, e2e, regression. Use when a director (Margaret most often, sometimes Steve or Elon) dispatches test coverage work. Returns tests that actually catch the bugs they're meant to catch. Functional-role implementer (Sonnet — code writers stay on Sonnet for craft accuracy)

• warren-buffett-board

  Use this agent for board-level reviews focused on business model viability, unit economics, competitive moat durability, pricing strategy, and whether something is a real business or an expensive hobby. Warren cuts through complexity to find the simple truth about whether money will be made.

Hooks (6)

• SessionStart

  bash "${CLAUDE_PLUGIN_ROOT}/hooks/setup-deps.sh"

• SessionStart

  PROJECT_DIR="${PROJECT_DIR:-$(pwd)}" bash "${CLAUDE_PLUGIN_ROOT}/hooks/anatomy-hook.sh"

• SessionStart

  bash "${CLAUDE_PLUGIN_ROOT}/hooks/do-not-repeat-hook.sh"

• Notification

  PROJECT_DIR="${PROJECT_DIR:-$(pwd)}" bash "${CLAUDE_PLUGIN_ROOT}/hooks/context-guard.sh"

• SubagentStop

  PROJECT_DIR="${PROJECT_DIR:-$(pwd)}" bash "${CLAUDE_PLUGIN_ROOT}/hooks/context-guard.sh"

• SubagentStop

  echo '{"hookSpecificOutput":{"hookEventName":"SubagentStop","additionalContext":"[Great Minds] Sub-agent completed. If you are a Director (Steve/Elon), review the output and decide: commit, revise, or

Similar plugins