Expert AI developer assistant that generates complete, production-ready RAG chatbot code for any stack. Supports: Python, JavaScript. Vector DBs: Pinecone, ChromaDB, pgvector, Qdrant, Weaviate. LLMs: OpenAI, Anthropic, Gemini, Mistral. Outputs: full pipeline code, document ingestion scripts, embedding setup, retrieval logic, system prompts and deployment guide. Paste your requirement — get complete working code instantly.
Un cycle Brainstorm → Spec validée → Plan à cases à cocher → TDD strict → Review de conformité, conçu pour les devs qui construisent des SaaS pilotés par IA (générateurs, agents, outils no-code) en HTML/CSS/JS vanilla ou Node/Express, avec intégrations multi-fournisseurs (Anthropic, OpenAI, Gemini, Mistral). Exemples d'usage : "ajoute une fonctionnalité X à mon générateur", "intègre un nouveau fournisseur IA", "refonds ce module"
A full analysis pipeline that turns a dataset into a finished report, not just charts. Hand it a CSV, Excel, Parquet, or JSON file and it cleans the data, scores its quality, runs EDA, and where the data supports it, trains a prediction model with SHAP attribution and a backtested forecast. You get a trust score, ranked findings, and recommendations as a Word doc, an interactive HTML report, and an optional PowerPoint deck. The numbers come from code, so they stay consistent, never invented.
Spark is easy to get running and hard to get right. I've spent years working specifically with Scala and Spark, so I know where the traps are and how to build things that actually hold up at scale. What I can help with: - Building analytics and ETL pipelines in Scala/Spark from scratch, or cleaning up ones that have gotten messy. - Making slow jobs fast, sorting out shuffles, joins, partitioning, and the memory issues that quietly kill performance.
Turn any public webpage or API response into a clean, validated, deduplicated structured dataset (JSON/CSV/SQLite): schema design with Pydantic, CSS/XPath extraction, cleaning rules, and storage, plus a built-in legal/ethics checklist (robots.txt, ToS, rate limiting). --- 把任何公開網頁或API回應轉成乾淨、已驗證、已去重的結構化資料集（JSON/CSV/SQLite）：Pydantic schema設計、CSS/XPath萃取、清洗規則、儲存，並內建法遵/倫理檢查清單（robots.txt、服務條款、速率限制）。中英文版本皆完整獨立撰寫。
From a local ISSUE file to a verified, committed deliverable — with a fresh-subagent acceptance gate that catches wrong screenshots and leaked logic.
Systematic QA of CLI tools and pipelines across multiple real workspaces using SFDPOT heuristics. Executes structured test flows, evaluates consistency oracles, collects evidence, and produces a structured bug report with P1/P2/P3 priorities and a release readiness verdict.
Serenity-style supply-chain bottleneck research workflow for public-market themes. It maps capex flows, finds overlooked upstream chokepoints, audits public/private/acquired players, separates evidence from inference, scores Bottleneck Strength and Research Priority, writes bear cases first, and outputs Markdown or optional HTML dashboards. Educational research only, not financial advice.
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.