- 📁 assets/
- 📁 references/
- 📄 SKILL.md
Build Cloudflare Workers applications with the Stratal framework. Use when code imports from 'stratal', '@stratal/framework', '@stratal/testing', or '@stratal/inertia', when creating modules, controllers, services, routes, queue consumers, cron jobs, seeders, or CLI commands, or when user mentions Stratal, asks to 'create a module', 'add an endpoint', 'set up auth', 'configure database', 'add error handling', 'set up Inertia', 'write tests', or 'run quarry'. Covers DI, routing with OpenAPI, error handling, i18n, testing, auth, RBAC, Inertia.js SSR, WebSocket, and MCP server. Do NOT use for generic Hono apps, plain Cloudflare Workers, or NestJS.
Administer an Omni Analytics instance — manage connections, users, groups, user attributes, permissions, schedules, and schema refreshes via the Omni CLI. Use this skill whenever someone wants to manage users or groups, set up permissions on a dashboard or folder, configure user attributes, create or modify schedules, manage database connections, refresh a schema, set up access controls, provision users, or any variant of "add a user", "give access to", "set up permissions", "who has access", "configure connection", "refresh the schema", or "schedule a delivery".
· Build, review, or architect AI/ML applications -- LLM integrations, RAG pipelines, agent systems, embeddings, evals, local inference, structured output, and tool use. Triggers: 'llm', 'rag', 'embedding', 'vector store', 'langchain', 'openai sdk', 'anthropic sdk', 'agent loop', 'fine-tune', 'ollama', 'vllm', 'evals', 'guardrails', 'chunking', 'reranking'. Not for MCP servers (use mcp), prompt writing (use prompt-generator), or general DB (use databases).
Backend specialist — builds APIs, database operations, auth, and server-side logic with security and performance focus
- 📁 data/
- 📁 examples/
- 📁 references/
- 📄 LEARNINGS.md
- 📄 SKILL.md
This skill should be used when the user asks about "Ben Gurion airport", "TLV flights", "flight status", "departures from Tel Aviv", "arrivals at TLV", "is my flight on time", "flight to Amsterdam", "airport delays", "cancelled flights", "gate info", "terminal 3", "pickup from airport", "weather at destination", "flight delay history", "נתב״ג", "טיסות", "לוח טיסות", "מצב טיסה". Provides live flight data from Ben Gurion Airport (TLV), destination weather via Open-Meteo, and historical delay analysis via local SQLite database. Do NOT use for booking flights, non-TLV airports, or general travel planning.
Use when generating tests for backend code (Express routes, MongoDB models, Node services) - analyzes file type, detects test framework from package.json, generates comprehensive tests with setup/teardown and edge case coverage
Use this skill whenever working with QuestDB — a high-performance time-series database. Trigger on any mention of QuestDB, time-series SQL with SAMPLE BY, LATEST ON, ASOF JOIN, ILP ingestion, or the questdb Python/Go/Java/Rust/.NET client libraries. Also trigger when writing Grafana queries against QuestDB, creating materialized views for time-series rollups, working with order book or financial market data in QuestDB, or any SQL that involves designated timestamps or time-partitioned tables. QuestDB extends SQL with unique time-series keywords — standard PostgreSQL or MySQL patterns will fail. Always read this skill before writing QuestDB SQL to avoid hallucinating incorrect syntax. --- # QuestDB Skill ## How to Use This Skill **IMPORTANT — MINIMIZE ROUND-TRIPS:** - Do NOT explore library source code (cryptofeed, questdb, etc.) - Do NOT check library versions or verify callback signatures - Do NOT read installed package files to "understand the API" - Do NOT verify infrastructure (Docker containers, Grafana health) is running — trust the user's prompt - Do NOT start `02_ingest.py` separately — `03_dashboard.py` launches it and verifies data automatically - Do NOT read extra reference files for topics already covered in this skill file - DO read reference files when their topic applies (e.g. enterprise.md for auth, grafana-advanced.md for complex panels) - Do NOT use task tracking (TaskCreate/TaskUpdate) for straightforward builds - Do NOT add `sleep` commands to wait for data or check background processes (the deploy script handles this) - Do NOT Ctrl+C, restart, or re-launch the ingestion process once `03_dashboard.py` has started it - Do NOT put VWAP, Bollinger, or RSI in separate timeseries panels — they are refIDs on the OHLC candlestick panel - Do NOT omit or empty `fieldConfig.overrides` — they put RSI on a right Y-axis (0-100%) and spread on a right axis. Without them, different scales crush the chart flat. - Do NOT set dashboard refresh to `"5s"` — the defa
Query and manage Banktivity financial data. Use when the user asks about transactions, accounts, spending, categories, tags, or securities in their Banktivity database.
Baseline de conhecimento para AI/ML engineering moderno em Python. Foco em LLM engineering, RAG systems, agent frameworks (LangChain/LangGraph), multiple LLM providers (Anthropic, OpenAI, Bedrock, Gemini, Meta), vector databases (Qdrant), semantic caching (MongoDB, Redis), testing, observability, security, e production patterns. Complementa arch-py skill com patterns AI-specific.
- 📄 composer.json
- 📄 README.md
- 📄 SKILL.md
Analyze and optimize database schemas, identify performance issues, and suggest improvements. Use when working with database structure, indexes, or query performance.
Scaffold a complete StrataSync app with Next.js client and Fastify server (models, sync, IndexedDB, WebSocket, PostgreSQL)
- 📁 .github/
- 📁 demo/
- 📁 references/
- 📄 .gitignore
- 📄 known-fixes.example.json
- 📄 LICENSE
AI self-healing error handler. Use when a cron job fails, a sub-agent crashes, a deploy breaks, a script errors, or any automated process reports a failure. Also use proactively during heartbeats to scan for recent failures. Detects failures, diagnoses root causes, applies fixes (preferring permanent fixes over band-aids), verifies the fix works, and logs everything to a known-fixes database for faster future resolution. Triggers on error handling, failure recovery, self-healing, diagnose error, fix broken, cron failed, deploy failed, sub-agent crashed, script error.
