I've spent years in fitting bays reading Trackman data — this Skill works the way a $200/hour fitting reads: paste your Trackman, GCQuad, Mevo+, R10, or sim numbers and get the one dominant diagnosis, an honest technique-vs-equipment verdict, exact spec directions when equipment is truly the problem, and a practice prescription with a measurable checkpoint. It will tell you NOT to buy a new driver when the data says strike training, which is exactly why you can trust it when it says the opposite
Calculates job costs and margin for HVAC, plumbing, electrical and similar trades. Produces structured cost breakdowns, margin risk flags, and dual internal + client-facing summaries.
Generate a complete EU GPSR-compliant technical file for any physical product in minutes — ready for Amazon, Shopify and EU marketplaces.
Real IV/Greeks-based credit spread analysis: strikes, TP/SL, and risk sizing for small accounts.
Daily scan of ~5,700 US stocks for three publicly-known Qullamaggie chart patterns — Episodic Pivot, Breakout, Parabolic. Interactive bilingual dashboards, per-ticker pattern characteristics, earnings-catalyst checks and a market-regime gauge. Reports objective pattern data and historical statistics only — no entry/stop/target, no position sizing, no "best" pick. Screening & education, not investment advice.
A multi-timeframe market structure tool based on the TWTCI indicator (10/5). Helps interpret uploaded charts, understand historical signal structure, and clarify stop-loss concepts. Educational and research use only — no specific entry, stop-loss, or position-sizing numbers. No order execution; all trading is done manually by the user.
Generate high-quality advertising poster images from natural language descriptions using OpenAI's image generation API (gpt-image-2 / gpt-image-1 / DALL-E 3).
Know if your backtest is a real edge or overfit noise. Runs bar-permutation MCPT, Deflated Sharpe, PBO/CSCV, Hansen SPA, Romano-Wolf StepM, a stationary bootstrap and an out-of-sample split on your own returns — no market feed, no API keys.
GSD is a spec-driven, context-engineering workflow for AI coding agents that prevents context rot & ships via the 5-step Discuss→Plan→Execute→Verify→Ship loop closed by /gsd-ship. Backed by a source-verified surface of 65 concrete commands across 6 namespace routers (/gsd-workflow, /gsd-project, /gsd-quality, /gsd-context, /gsd-manage, /gsd-ideate), with optional OpenGSD companions (gsd-pi, gsd-graph + MCP, gsd-loop, gsd-browser). & a `.planning/` directory that the agent reads across sessions.