A powerful AI orchestrator and skill system for Antigravity, featuring 40+ specialized domain expert skills, disciplined development workflows, and RTK token optimization.

Project description

Mega-Mind Skills System

A unified superpowers + virtual company skill set for Antigravity IDE

This is a comprehensive skill-based workflow system that combines the disciplined development workflows of Superpowers with the domain expertise of Virtual Company. It provides structured, reliable behavior for AI coding assistants across the entire software development lifecycle.

Overview

Mega-Mind brings together 42 skills organized into categories:

The Mega-Mind Orchestrator (1 skill)

The master controller that routes requests and coordinates skill chains:

mega-mind - Primary entry point via /mega-mind command

Core Workflow Skills (13 skills)

Structured development discipline that ensures quality at every step:

brainstorming - Explore approaches before committing
writing-plans - Create detailed implementation plans
executing-plans - Disciplined execution with tracking
single-flow-task-execution - Sequential task decomposition
test-driven-development - Write tests first, implement second
systematic-debugging - Root cause analysis methodology
requesting-code-review - Structured review requests
receiving-code-review - Handle feedback systematically
verification-before-completion - Prove it works before done
finishing-a-development-branch - Clean branch management
using-git-worktrees - Parallel development workflows
using-mega-mind - Master skill routing
writing-skills - Create new custom skills

Domain Expert Skills (27 skills)

Specialized expertise for specific technical domains:

Architecture: tech-lead, frontend-architect, backend-architect, infra-architect, api-designer
Development: code-polisher, migration-upgrader, mobile-architect, legacy-archaeologist
Testing: test-genius, e2e-test-specialist, bug-hunter
DevOps: ci-config-helper, docker-expert, k8s-orchestrator, observability-specialist
Data: data-engineer, data-analyst, ml-engineer, search-vector-architect
Security: security-reviewer
Performance: performance-profiler
Documentation: doc-writer
UX: ux-designer
Product: product-manager, workflow-orchestrator
Meta: skill-generator

Token Optimization (1 skill)

Reduce LLM Token consumption:

RTK: rtk - CLI proxy for 60-90% token savings on common dev commands

Quick Start

1. Install the CLI

# pip
pip install mega-mind-orchestrator

# pipx (recommended — isolated, globally available)
pipx install mega-mind-orchestrator

# uv
uv tool install mega-mind-orchestrator

2. Initialize skills in your project

# From your project root
cd /path/to/your/project
mega-mind init

This copies the full .agent/ directory into your project — all 42 skills, workflows, and agents are ready to use.

# Overwrite an existing installation
mega-mind init --force

3. Verify the installation

bash .agent/tests/run-tests.sh

📖 For full installation details see USAGE.md

Using Mega-Mind

The `/mega-mind` Command

The /mega-mind command is your primary entry point to the skill system. It acts as an intelligent orchestrator that:

Analyzes your request to understand intent
Routes to the appropriate skill(s)
Coordinates skill chains for complex tasks
Tracks progress throughout

Available Commands

/mega-mind status             - Show current session state
/mega-mind skills             - List all available skills
/mega-mind workflows          - List available workflows
/mega-mind route <request>    - Analyze and route a request
/mega-mind execute <workflow> - Execute a named workflow
/mega-mind help               - Show help message

Direct Skill Commands

Command	Skill	Purpose
`/brainstorm`	brainstorming	Explore approaches before deciding
`/plan`	writing-plans	Create implementation plan
`/execute`	executing-plans	Execute plan with tracking
`/debug`	systematic-debugging	Debug systematically
`/review`	requesting-code-review	Request code review
`/ship`	finishing-a-development-branch	Deploy to production
`/tdd`	test-driven-development	Test-first development
`/verify`	verification-before-completion	Verify before marking done

Example Usage

User: /mega-mind I need to add user authentication with OAuth

🧠 Mega-Mind Orchestration
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━

📋 Request Analyzed: New feature - User Authentication with OAuth

🔄 Routed to skill chain:
   1. tech-lead                        → Define architecture
   2. brainstorming                    → Explore OAuth providers
   3. api-designer                     → Design auth API
   4. writing-plans                    → Create implementation plan
   5. test-driven-development          → Write auth tests
   6. backend-architect                → Implement auth service
   7. frontend-architect               → Implement login UI
   8. security-reviewer                → Security audit
   9. verification-before-completion   → Verify

📍 Starting with: tech-lead

File Structure

mega-mind-skills/
├── README.md                    # Main documentation (this file)
├── USAGE.md                     # Installation guide
├── COMPLETE_REFERENCE.md        # Detailed reference
├── quick-install.sh             # Simple copy installer (legacy)
│
└── .agent/
    ├── AGENTS.md                # Master contract and rules
    │
    ├── skills/
    │   ├── mega-mind/           # 🧠 Master orchestrator
    │   │
    │   ├── # Core Workflow Skills
    │   ├── brainstorming/
    │   ├── writing-plans/
    │   ├── executing-plans/
    │   ├── single-flow-task-execution/
    │   ├── test-driven-development/
    │   ├── systematic-debugging/
    │   ├── requesting-code-review/
    │   ├── receiving-code-review/
    │   ├── verification-before-completion/
    │   ├── finishing-a-development-branch/
    │   ├── using-git-worktrees/
    │   ├── using-mega-mind/
    │   └── writing-skills/
    │
    │   ├── # Domain Expert Skills
    │   ├── tech-lead/
    │   ├── frontend-architect/
    │   ├── backend-architect/
    │   ├── infra-architect/
    │   ├── api-designer/
    │   ├── code-polisher/
    │   ├── migration-upgrader/
    │   ├── mobile-architect/
    │   ├── legacy-archaeologist/
    │   ├── test-genius/
    │   ├── e2e-test-specialist/
    │   ├── bug-hunter/
    │   ├── ci-config-helper/
    │   ├── docker-expert/
    │   ├── k8s-orchestrator/
    │   ├── observability-specialist/
    │   ├── data-engineer/
    │   ├── data-analyst/
    │   ├── ml-engineer/
    │   ├── search-vector-architect/
    │   ├── security-reviewer/
    │   ├── performance-profiler/
    │   ├── doc-writer/
    │   ├── ux-designer/
    │   ├── product-manager/
    │   ├── workflow-orchestrator/
    │   └── skill-generator/
    │
    ├── workflows/
    │   ├── brainstorm.md
    │   ├── execute-plan.md
    │   ├── write-plan.md
    │   ├── debug.md
    │   ├── review.md
    │   └── ship.md
    │
    ├── agents/
    │   ├── code-reviewer.md
    │   ├── tech-lead.md
    │   └── qa-engineer.md
    │
    └── tests/
        └── run-tests.sh

Skill Routing Matrix

The mega-mind orchestrator automatically routes requests to appropriate skills:

Request Type	Primary Skill	Secondary Skills
New feature	tech-lead	brainstorming, writing-plans
Bug fix	systematic-debugging	bug-hunter
Code quality	code-polisher	-
Performance	performance-profiler	-
Security	security-reviewer	-
Testing	test-driven-development	test-genius
Documentation	doc-writer	-
API design	api-designer	backend-architect
Frontend	frontend-architect	ux-designer
Backend	backend-architect	api-designer
DevOps	infra-architect	docker-expert, k8s-orchestrator
Data	data-engineer	data-analyst
ML/AI	ml-engineer	-
Mobile	mobile-architect	-
Legacy code	legacy-archaeologist	-

Workflows

Feature Development

brainstorming → writing-plans → test-driven-development →
executing-plans → verification-before-completion →
requesting-code-review → finishing-a-development-branch

Bug Fix

systematic-debugging → bug-hunter → test-driven-development →
verification-before-completion → finishing-a-development-branch

Code Improvement

code-polisher → test-driven-development → verification-before-completion

Security Audit

security-reviewer → systematic-debugging → test-driven-development →
verification-before-completion

New Project

tech-lead → brainstorming → [architects] → writing-plans →
[docker-expert, k8s-orchestrator, ci-config-helper] → development chains

Key Concepts

Task Tracking

All tasks are tracked in docs/plans/task.md:

Task ID	Description	Status	Priority	Dependencies
1	Example task	pending	high	-

Status values: pending, in_progress, completed, blocked

Verification Before Completion

Never mark a task as complete without:

Running tests
Running linting
Building successfully
Manual verification
Checking for regressions

Execution Model

Session loads .agent/AGENTS.md rules
/mega-mind analyzes and routes requests
Design work flows through brainstorming → planning → execution
All work tracked in task tracker
Nothing marked done without verification

RTK Token Optimization

When RTK is installed, CLI commands are automatically optimized:

Original	RTK-Optimized	Savings
`git log`	`rtk git log`	85%
`cargo test`	`rtk cargo test`	90%
`npm test`	`rtk npm test`	90%
`pytest`	`rtk pytest`	90%

Install RTK:

cargo install rtk
# or
curl -sSL https://github.com/rtk-ai/rtk/releases/latest/download/rtk-$(uname -s)-$(uname -m) -o /usr/local/bin/rtk
chmod +x /usr/local/bin/rtk

Installation

See USAGE.md for the full installation guide.

CLI Reference

# Install skills into current directory
mega-mind init

# Install into a specific path
mega-mind init /path/to/project

# Overwrite existing .agent directory
mega-mind init --force

# Show CLI version
mega-mind --version

Validate Installation

bash .agent/tests/run-tests.sh

Tests verify:

Core workflow skills existence
Domain expert skills existence
Workflows existence
Agent profiles existence
AGENTS.md validation
Skill frontmatter validation

Contributing

To add new skills:

Create a new directory in .agent/skills/

Add a SKILL.md file with proper frontmatter:

---
name: skill-name
description: What this skill does
triggers:
  - "/trigger"
  - "keyword"
---

Include instructions and examples
Run tests to verify

Credits

This project combines and adapts:

Superpowers by obra - Core workflow philosophy
antigravity-superpowers by skainguyen1412 - Antigravity adaptation
virtual-company by k1lgor - Domain expertise skills
RTK - Token optimization CLI

License

MIT License - Free to use and modify.

Project details

Release history Release notifications | RSS feed

0.4.0

Mar 14, 2026

0.3.2

Mar 11, 2026

0.3.1

Mar 11, 2026

0.3.0

Mar 11, 2026

0.2.0

Mar 8, 2026

This version

0.1.1

Mar 8, 2026

0.1.0

Mar 8, 2026

Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

mega_mind_orchestrator-0.1.1.tar.gz (182.8 kB view details)

Uploaded Mar 8, 2026 Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

The dropdown lists show the available interpreters, ABIs, and platforms. Enable javascript to be able to filter the list of wheel files.

mega_mind_orchestrator-0.1.1-py3-none-any.whl (121.7 kB view details)

Uploaded Mar 8, 2026 Python 3

File details

Details for the file mega_mind_orchestrator-0.1.1.tar.gz.

File metadata

Download URL: mega_mind_orchestrator-0.1.1.tar.gz
Upload date: Mar 8, 2026
Size: 182.8 kB
Tags: Source
Uploaded using Trusted Publishing? Yes
Uploaded via: twine/6.1.0 CPython/3.13.7

File hashes

Hashes for mega_mind_orchestrator-0.1.1.tar.gz
Algorithm	Hash digest
SHA256	`f7abd69f12c50d351a091d1a5aaffbee30c44a5909cc9614649a88104def3229`
MD5	`ed8dc94d4c26c67e11a75a2491332636`
BLAKE2b-256	`1932161586631b4ea9539d3c66af843a7e78bcf8668e4388cb95a8388bd54afe`

See more details on using hashes here.

Provenance

The following attestation bundles were made for mega_mind_orchestrator-0.1.1.tar.gz:

Publisher: publish.yml on k1lgor/mega-mind-skills

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

Statement:
- Statement type: https://in-toto.io/Statement/v1
- Predicate type: https://docs.pypi.org/attestations/publish/v1
- Subject name: mega_mind_orchestrator-0.1.1.tar.gz
- Subject digest: f7abd69f12c50d351a091d1a5aaffbee30c44a5909cc9614649a88104def3229
- Sigstore transparency entry: 1059825094
- Sigstore integration time: Mar 8, 2026
Source repository:
- Permalink: k1lgor/mega-mind-skills@4d62625df1e9a898ac74600c739eb7fe12b0a304
- Branch / Tag: refs/tags/v0.1.1
- Owner: https://github.com/k1lgor
- Access: public
Publication detail:
- Token Issuer: https://token.actions.githubusercontent.com
- Runner Environment: github-hosted
- Publication workflow: publish.yml@4d62625df1e9a898ac74600c739eb7fe12b0a304
- Trigger Event: push

File details

Details for the file mega_mind_orchestrator-0.1.1-py3-none-any.whl.

File metadata

Download URL: mega_mind_orchestrator-0.1.1-py3-none-any.whl
Upload date: Mar 8, 2026
Size: 121.7 kB
Tags: Python 3
Uploaded using Trusted Publishing? Yes
Uploaded via: twine/6.1.0 CPython/3.13.7

File hashes

Hashes for mega_mind_orchestrator-0.1.1-py3-none-any.whl
Algorithm	Hash digest
SHA256	`741cbab7d76daa77d5da51021371ea94c2f336aa9e140db9c1a0841a99049cb2`
MD5	`b0dee5ef5c5b1afe7c7bdc423bd7ba8f`
BLAKE2b-256	`2bab457ff3cfd2e2527362207c308954e34b6d1485ad04919c4d5155f92b31d5`

See more details on using hashes here.

Provenance

The following attestation bundles were made for mega_mind_orchestrator-0.1.1-py3-none-any.whl:

Publisher: publish.yml on k1lgor/mega-mind-skills

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

Statement:
- Statement type: https://in-toto.io/Statement/v1
- Predicate type: https://docs.pypi.org/attestations/publish/v1
- Subject name: mega_mind_orchestrator-0.1.1-py3-none-any.whl
- Subject digest: 741cbab7d76daa77d5da51021371ea94c2f336aa9e140db9c1a0841a99049cb2
- Sigstore transparency entry: 1059825097
- Sigstore integration time: Mar 8, 2026
Source repository:
- Permalink: k1lgor/mega-mind-skills@4d62625df1e9a898ac74600c739eb7fe12b0a304
- Branch / Tag: refs/tags/v0.1.1
- Owner: https://github.com/k1lgor
- Access: public
Publication detail:
- Token Issuer: https://token.actions.githubusercontent.com
- Runner Environment: github-hosted
- Publication workflow: publish.yml@4d62625df1e9a898ac74600c739eb7fe12b0a304
- Trigger Event: push

mega-mind-orchestrator 0.1.1

Navigation

Verified details

Maintainers

Unverified details

Meta

Project description

Mega-Mind Skills System

Overview

The Mega-Mind Orchestrator (1 skill)

Core Workflow Skills (13 skills)

Domain Expert Skills (27 skills)

Token Optimization (1 skill)

Quick Start

1. Install the CLI

2. Initialize skills in your project

3. Verify the installation

Using Mega-Mind

The /mega-mind Command

Available Commands

Direct Skill Commands

Example Usage

File Structure

Skill Routing Matrix

Workflows

Feature Development

Bug Fix

Code Improvement

Security Audit

New Project

Key Concepts

Task Tracking

Verification Before Completion

Execution Model

RTK Token Optimization

Installation

CLI Reference

Validate Installation

Contributing

Credits

License

Project details

Verified details

Maintainers

Unverified details

Meta

Release history Release notifications | RSS feed

Download files

Source Distribution

Built Distribution

File details

File metadata

File hashes

Provenance

File details

File metadata

File hashes

Provenance

The `/mega-mind` Command