alpha-skills

Calculate days, months, and years of sobriety or clean time from a given start date. Shows a recovery milestone card with chip milestones highlighted.

A long-form article / blog post — 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 — Philosophy / Visual hierarchy / Detail / Functionality / Innovation, each scored 0–10. 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 维度评审", "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".

Parse a structured design brief written in I-Lang protocol format into a concrete design spec. Eliminates ambiguity from vague requests like "make it professional" by requiring explicit dimensions: palette, typography, layout, mood, density, and constraints. Trigger keywords: "design brief", "create a design brief", "ilang brief", "structured brief".

Disciplined diagnosis loop for hard bugs and performance regressions. Reproduce → minimise → hypothesise → instrument → fix → regression-test. Use when user says "diagnose this" / "debug this", reports a bug, says something is broken/throwing/failing, or describes a performance regression.

Send messages to and read messages from the TraderDaddy-Pro Discord (#admin-discussion by default) using the alpha-skills bot. Triggers on "post to discord", "send to admin-discussion", "discord post", "read discord", "what's in

A documentation page — left nav, scrollable article body, right-rail table of contents. Use when the brief mentions "docs", "documentation", "guide", "API reference", or "tutorial".

Single-command driver to produce a complete Substack article package in Michael's voice. Given a topic or a pillar, writes docs/articles/<slug>/{README.md, generate_images.py, notes_teaser.md, subject_lines.md, promo_notes.csv}. Use when the user wants a "new Substack post about X", "/draft-article X", "ghost-write the X piece", or says "let's write the post on Y."

Interview the user relentlessly about a plan or design until reaching shared understanding, resolving each branch of the decision tree. Use when user wants to stress-test a plan, get grilled on their design, or mentions "grill me".

Applies multi-disciplinary cognitive frameworks (e.g., Inversion, First Principles, Second-Order Thinking) to user plans and system designs to stress-test decisions.

Render markdown or HTML into a crisp, accurately-rendered PNG — tables, data figures, stat cards — for inlining into Substack posts (where markdown tables render as garbage) or anywhere a real-browser-rendered image beats a hand-drawn one. Use whenever a post or doc needs a table-as-image, or any markdown/HTML turned into a picture.

Build TradingView Pine Script v6 indicators in Michael's house style. Synthwave dashboard, faithful math, v6-compliant, no em dashes. Triggers on "pine script", "tradingview indicator", "write a pine indicator", "/mph-pine".

End-to-end Substack pipeline. Take a subject, produce a draft (or publish it) at mphinance.substack.com. Chains mph-substack-writer (voice) + mph-figure (images) + the local create_draft_from_md.py pusher. Triggers on "write a Substack about X", "draft a post on Y", "publish to Substack", "/dispatch a Substack" or similar.

Write Substack articles in Michael Hanko's exact voice. Enforces strict styling rules (no em dashes, no markdown tables) and captures his irreverent, self-deprecating, recovery-infused tone.

Generates UI components, dashboards, and pages using Michael's signature Synthwave / TraderDaddy / Bloomberg aesthetic.

Mine Claude Code chat transcripts for Michael Hanko's actual phrasing patterns and refresh the VOICE.md corpus. Triggers on "refresh my voice", "update VOICE.md", "mine my chats for voice", "what does my voice sound like lately", "refresh voice corpus", or when mph-substack-writer output has started sounding stale/repetitive.

Run an orchestrator-pattern build on any codebase. Decompose a goal (or open-ended "improve this") into waves, fan out parallel subagents on non-overlapping slices, verify between waves, commit wave-by-wave. Use when the user says "orchestrate", "fan out to agents", "parallel agents", "swarm this", "overnight build", "ship a batch of fixes", "improve this codebase", "find bugs", "what should we fix here", "ideas for this codebase", or any request that's bigger than one agent can comfortably do in one shot.

A meta-skill that establishes a 'One Brain' portable memory folder (.agent/). It persists context, user preferences, identity rules, and execution history across different AI harnesses (Claude Code, Cursor, Windsurf, OpenClaw).

Meta-skill that forges, audits, and refines other skills. Three modes – forge a new skill from a brief, audit recent chat transcripts for new-skill candidates and pain points, or refine an existing skill with additive-only changes. Triggers on "skill-forge a thing that does X", "forge a skill", "skill-forge audit", "skill audit", "refine my skills", "skill-forge refine <name>", or "/skill-forge". Auto-opens a PR against mphinance/alpha-skills (never auto-merges).

Security scanner and health check for your AI agent skills tree. Identifies dead skills, missing documentation, and unsafe shell execution paths.

The deepest single-stock pull we have — everything on ONE ticker in one shot, so when someone asks "do you like PLTR down here?" you can just check instead of looking it all up by hand. Pulls TickerTrace 13F ownership + recent fund changes, full technicals (RSI/ADX/EMA stack/stoch/MACD/fibs/pivots/keltner), complete options positioning (max pain, call/put walls, expected move, IV skew, OI by strike), recent options flow, renders a 90-day chart, and (you) WebSearch recent news/catalysts — then deliver a plain-English verdict. Use when the user asks "do you like X here / down here", "what's the story on X", "should I buy X", "pull everything on X", "deep dive X", "is X a buy", or names a single ticker and wants the full read.

Daily market recap + convergence-ranked stock shortlist for TraderDaddy Pro. Runs ALL screeners at default settings, pulls the biggest options flows / smart money, new CBOE option listings, and hedge-fund (13F) activity, then finds the short list of names that multiple independent sources agree on — with technicals. Use when the user asks to "find good stocks", wants a "market recap", "what's flowing", "what are the funds doing", "run the screeners", "any setups", or "what should I be looking at" for trading ideas.

Show pending Substack drafts and reconcile them against local ~/.mph-substack-cache workspaces. Flags local-only drafts older than 3 days as stale (the "wait did I actually save this on substack" problem). Read-only — never publishes. Triggers on "did I save that draft", "is that saved on substack", "what drafts do I have", "show my substack drafts", "are my drafts pushed", "/substack-status", "/draft-status".

Test-driven development with red-green-refactor loop. Use when user wants to build features or fix bugs using TDD, mentions "red-green-refactor", wants integration tests, or asks for test-first development.

Avantis value-factor tracker — small-cap (AVUV) and large-cap (AVLV) value in one read, straight from TickerTrace's per-fund holdings. Groups by fund tier and by position lifecycle (new/exited, conviction tilt, up-streaks), ranked by weight, and surfaces the sector themes both funds agree on. Use when the user asks "what's the value factor doing", "what did AVUV/AVLV add", "new adds in value", "what are the value funds buying", "value complex", or wants the small-vs-large value read.

Mine Claude Code chat transcripts for Michael Hanko's actual phrasing patterns and refresh the VOICE.md corpus. Triggers on "refresh my voice", "update VOICE.md", "mine my chats for voice", "what does my voice sound like lately", "refresh voice corpus", or when mph-substack-writer output has started sounding stale/repetitive.

Build TradingView Pine Script v6 indicators in Michael's house style. Synthwave dashboard, faithful math, v6-compliant, no em dashes. Triggers on "pine script", "tradingview indicator", "write a pine indicator", "/mph-pine".

Meta-skill that forges, audits, and refines other skills. Three modes – forge a new skill from a brief, audit recent chat transcripts for new-skill candidates and pain points, or refine an existing skill with additive-only changes. Triggers on "skill-forge a thing that does X", "forge a skill", "skill-forge audit", "skill audit", "refine my skills", "skill-forge refine <name>", or "/skill-forge". Auto-opens a PR against mphinance/alpha-skills (never auto-merges).

Audio generation skill — jingles, beds, voiceover, and sound effects. Routes music requests to Suno V5 / Udio / Lyria, speech to MiniMax TTS / FishAudio / ElevenLabs V3, and SFX to ElevenLabs SFX or AudioCraft. Output is one MP3/WAV file saved to the project folder.

Expert guidance for systematic backtesting of trading strategies. Use when developing, testing, stress-testing, or validating quantitative trading strategies. Covers "beating ideas to death" methodology, parameter robustness testing, slippage modeling, bias prevention, and interpreting backtest results. Applicable when user asks about backtesting, strategy validation, robustness testing, avoiding overfitting, or systematic trading development.

This skill should be used when analyzing market breadth charts, specifically the S&P 500 Breadth Index (200-Day MA based) and the US Stock Market Uptrend Stock Ratio charts. Use this skill when the user provides breadth chart images for analysis, requests market breadth assessment, positioning strategy recommendations, or wants to understand medium-term strategic and short-term tactical market outlook based on breadth indicators. Also works WITHOUT chart images by fetching CSV data directly from public sources. All analysis and output are conducted in English.

Generate Minervini-style breakout trade plans from VCP screener output with worst-case risk calculation, portfolio heat management, and Alpaca-compatible order templates (stop-limit bracket for pre-placement, limit bracket for post-confirmation). Use when user has VCP screener results and wants actionable trade plans with entry/stop/target levels and position sizing.

Screen US stocks using William O'Neil's CANSLIM growth stock methodology. Use when user requests CANSLIM stock screening, growth stock analysis, momentum stock identification, or wants to find stocks with strong earnings and price momentum following O'Neil's investment system.

Validate data quality in market analysis documents and blog articles before publication. Use when checking for price scale inconsistencies (ETF vs futures), instrument notation errors, date/day-of-week mismatches, allocation total errors, and unit mismatches. Supports English and Japanese content. Advisory mode -- flags issues as warnings for human review, not as blockers.

A consumer-feeling dating / matchmaking dashboard — left rail navigation, ticker bar of community signals, headline KPIs, a 30-day mutual-matches bar chart, and a match-rate trend block. Editorial typography, restrained accent. Use when the brief asks for a "dating site", "matchmaking", "community dashboard", "social network dashboard", or any consumer product where the data is the story.

A two-spread digital e-guide preview — page 1 is a cover (display title, author, "What's inside" stats, table of contents teaser); page 2 is a spread (lesson body with pull-quote and a step list). Lifestyle / creator brand tone. Use when the brief asks for an "e-guide", "digital guide", "lookbook", "lead magnet", "creator guide", "playbook", "PDF guide", or "电子指南".

Use this skill to find high-quality dividend growth stocks (12%+ annual dividend growth, 1.5%+ yield) that are experiencing temporary pullbacks, identified by RSI oversold conditions (RSI ≤40). This skill combines fundamental dividend analysis with technical timing indicators to identify buying opportunities in strong dividend growers during short-term weakness.