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…
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 createdraftfrommd.py pusher. Triggers on "write a Substack about X", "draft a post on Y", "publish to Substack", "/dispatch a Substack" or…
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.
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…
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"…
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"…
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…
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.…
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…
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…
0DTE day-trading playbook for a small account — Ghost Alpha signals into Tradier XSP (Mini-SPX) same-day options with strict IFTTT entry/exit rules and hard risk guardrails. Use when Michael wants to run a 0DTE session, size a contract, decide whether a signal qualifies, or apply the exit cascade. This is a…
Run the full suite of stock-screening strategies in sequence and export results to Google Sheets (one tab per strategy). Use when Michael wants to run the nightly/weekend scans, refresh the screener tabs, run a specific strategy, or understand which strategies are available and what each surfaces.
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…
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…
Pick a broker MCP server your AI agent can actually execute trades through, and wire it up safely. Use when the user wants to place, submit, or automate real orders; connect an agent to a brokerage account; choose between Alpaca, IBKR, Tradier, Robinhood, Schwab, Kraken and other broker MCP servers; move from analysis…
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.
Daily scanner that finds stocks sitting in the "bottom of the coil" using a dual-timeframe Williams %R Trend Exhaustion indicator, then flags the ones that just triggered out. Silent data feed for Michael — he writes trade posts only when he likes a name. Use when the user asks about "coil scan", "bottom of the coil"…