By mphinance
Portable Claude Code kit that unifies Substack publishing, trading/market analysis, design reviews, code orchestration, and git workflows into a consistent environment across machines. Includes voice-enforced writing, stock research, dashboard generation, parallel subagent builds, and automated commit/push with safety guards.
On-demand cockpit view โ today's calendar, money snapshot, and at-risk code
Quick live money snapshot โ Stripe revenue + brokerage
Pre-push panel review. Fan out 4 read-only reviewers โ each a distinct voice you'd otherwise need a whole team to get โ then synthesize one ranked pick-list. Designed as productive tension (one voice expands, one cuts, one attacks, one verifies), not four flavors of caution.
Run the orchestrator pattern on any codebase โ fan out parallel subagents on waves of work, verify between waves, commit wave-by-wave. Args (optional) describe the goal; with no args, runs in Recon mode and produces a prioritized findings list first.
Sweep every repo under the GitHub folder and safely save anything unsaved
Safely commit and push the current repo with a clean conventional message. Use when Michael says "ship this", "commit and push", or wants working changes saved to GitHub. Runs sanity checks first and never pushes secrets or force-pushes.
Edit and hard-proof a Substack draft against Michael's voice rules before it ships. Use when reviewing or polishing a post for mphinance.substack.com, or when he asks "is this in my voice" / "clean this up for Substack".
Read-only research on a ticker or market theme โ fundamentals, recent price action, news, and brokerage position context. Use when Michael asks "what's the story on X", "should I look at TICKER", or wants a briefing before a trade. NEVER places trades.
A long-form article / blog post โ masthead, hero image placeholder, article body with figures and pull quotes, author byline, related posts. Use when the brief asks for "blog", "article", "post", "essay", or "case study".
Ultra-compressed communication mode. Cuts token usage ~75% by dropping filler, articles, and pleasantries while keeping full technical accuracy. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman.
Run a 5-dimension expert design review on any HTML artifact in the project โ Philosophy / Visual hierarchy / Detail / Functionality / Innovation, each scored 0โ10. Outputs a single self-contained HTML report with a radar chart, evidence-backed scores, and three lists: Keep / Fix / Quick-wins. Use when the brief asks for a "design review", "design critique", "5 ็ปดๅบฆ่ฏๅฎก", "design audit", or "what's wrong with my design".
Admin / analytics dashboard in a single HTML file. Fixed left sidebar, top bar with user/search, main grid of KPI cards and one or two charts. Use when the brief asks for a "dashboard", "admin", "analytics", or "control panel" screen.
Generate multiple radically different interface designs for a module using parallel sub-agents. Use when user wants to design an API, explore interface options, compare module shapes, or mentions "design it twice".
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.
113 Elite AI Agent Skills for Quant Trading, Market Intelligence, and Creative Production
AI agents like Claude Code and Gemini are only as good as the context you provide them. Out of the box, they are brilliant generalists.
This repository gives them a PhD in algorithmic trading and a master's in design.
By dropping these skills/ into your agent's workspace, you inject decades of domain expertise, algorithmic rigor, and aesthetic taste directly into their runtime. You aren't just getting scripts. You are getting autonomous agents capable of identifying market regimes, rewriting PineScript to Python, running full design critiques, and generating Substack-ready financial reports.
On Modularity: A "Full Tower" audit was performed across all 113 directories. Every single skill is structurally unique. Even seemingly overlapping skills (like Breadth vs. Uptrend analyzers) are intentionally decoupled, serving as independent, uncorrelated inputs for the downstream Druckenmiller Strategy Synthesizer.
graph TD
A[AI Agent Core] -->|reads SKILL.md| B(Alpha Skills Suite)
B --> C[Quant Engine]
B --> D[Creative Studio]
B --> E[Agent Infra]
C --> C1[Screeners & Signals]
C --> C2[Regime Detection]
C --> C3[Edge Pipeline]
C1 -->|optional| F[(FMP API)]
C1 -->|optional| G[(Tradier API)]
C2 -->|public CSV| H[(TraderMonty Data)]
E -->|optional| I[(OpenRouter API)]
style A fill:#8a2be2,stroke:#fff,stroke-width:2px,color:#fff
style B fill:#ff007f,stroke:#fff,stroke-width:2px,color:#fff
style C fill:#00e5ff,stroke:#0a0a0c,stroke-width:2px,color:#0a0a0c
style D fill:#00ff88,stroke:#0a0a0c,stroke-width:2px,color:#0a0a0c
style E fill:#b026ff,stroke:#fff,stroke-width:2px,color:#fff
skills/ folder into your agent's skill directory:
~/.gemini/antigravity/skills/Most skills work out of the box with zero configuration. A subset of quant screeners require paid data APIs:
| Key | Service | Used By |
|---|---|---|
FMP_API_KEY | Financial Modeling Prep | 18 screeners/detectors (see tables below) |
TRADIER_API_KEY | Tradier Brokerage | ghost-auto-trader |
OPENROUTER_API_KEY | OpenRouter | urithiru multi-model verification |
Built for traders, by traders. Automates the tedious parts of algorithmic research and protects you from your own biases.
npx claudepluginhub mphinance/alpha-skills --plugin mph-kitComplete collection of 30 Claude Code skills for document processing, development, business productivity, and creative tasks
A comprehensive collection of custom skills for Claude Code covering engineering, product management, design, content, trading, database, QA, and educational domains
Create skills from documentation folders and project codebases. Review, test, and package Anthropic Agent Skills for Claude.ai and Claude Code. 13 commands including from-docs, from-project, beginner tutorial, interactive wizard, templates, quality auditing, and distribution packaging.
Claude Code skill pack for Finta (18 skills)
The Hitchhiker's Guide โ content creation suite with automated pipeline, daily briefs, and blog writing
Comprehensive UI/UX design plugin for mobile (iOS, Android, React Native) and web applications with design systems, accessibility, and modern patterns