This skill should be used when creating, editing, or reviewing inline SVG diagrams for the CocoIndex docs site (anything under docs/src/content/docs/). It encodes the component-based primitive system under docs/src/components/diagrams/, the palette + shape semantics, the preview-and-verify loop using headless Chrome…
This skill should be used when creating a new target connector for CocoIndex to integrate with external systems. It provides guidance on implementing TargetHandler, TargetActionSink, and related types for declarative target state synchronization with change detection and automatic cleanup.
This skill should be used when building data processing pipelines with CocoIndex, a Python library for incremental data transformation. Use when the task involves processing files/data into databases, creating vector embeddings, building knowledge graphs, ETL workflows, or any data pipeline requiring automatic change…
Build and run LLM-powered data processing pipelines with DocETL. Use when users say "docetl", want to analyze unstructured data, process documents, extract information, or run ETL tasks on text. Helps with data collection, pipeline creation, execution, and optimization.
A practical development guide for building JavaScript and React interfaces with Tailwind CSS and shadcn/ui, a collection of reusable interface components.
A tool for generating Markdown data-model documents from Doris, an analytical database. It can pull table metadata and at least 100 sample rows, then fill in field descriptions from database comments or an agent.
Comprehensive toolkit for developing with the CocoIndex library. Use when users need to create data transformation pipelines (flows), write custom functions, or operate flows via CLI or API. Covers building ETL workflows for AI data processing, including embedding documents into vector databases, building knowledge…
A practical extension layer for Guandata BI, a business-intelligence platform used to query data, build charts, and publish dashboards. It covers advanced data-pipeline work and custom HTML, CSS, and JavaScript dashboards beyond the standard tools.
Build, modify, materialize, run, and verify DataCoolie projects. Use for workspace bootstrap, metadata authoring, environment overlays, capability checks, runners, notebooks, custom functions, narrow unsupported adapters, local tests, immutable builds, and project-owned build/CI automation. This is the sole…
Inspect data sources and produce verified source evidence for DataCoolie design or build work. Use for every new DataCoolie project before design, for every declared source type, and when an existing source is new, changed, missing evidence, or contradictory. Discovery is read-only evidence and never creates runtime…
Plan, preflight, deploy, promote, roll back, or author consume-only release automation for an exact verified DataCoolie build. Use for explicit deployment-lifecycle work; read-only planning may precede authorization, while target mutation requires exact authorization. This skill consumes immutable build artifacts and…
A PDF analysis toolset that breaks research papers and other PDF documents into searchable text, sections, images, and tables. It can also connect information across documents in a knowledge graph, a map of related facts.
A skill for creating different kinds of automated tests and checking tools for a codebase. It covers static analysis, which finds code and type problems without running the program, as well as unit, integration, and end-to-end tests.
Build or refresh Foam-compatible LLM wikis from Asset-Aware documents, citation bundles, tables, figures, and local Markdown notes using a multi-tool workflow.
Creates useful Mermaid diagrams for SWE, DevOps, and Platform Engineering work — PRs, ADRs, RFCs, runbooks, incident reviews, roadmaps, system architecture, and more. Use this skill whenever the user wants to visualize a technical initiative, system change, workflow, deployment pipeline, data model, service topology…
Generate a complete, mental-model-first course on any technology — a landing README, a CHEATSHEET, and dependency-ordered numbered course units, each following a fixed learn → why → concepts → exercises → self-checks → takeaways template, grounded in primary sources before any content is written and with the syllabus…
Orient new contributors and developers to a repository or technology through structured, planned exploration. Uses creative-planner to design the tour path, then tree, ls, eza, and cat to map the filesystem landscape live. When unknowns arise, searches the web for current documentation rather than relying on…
Deploy Operator ETL to GCP — Terraform, Docker, Cloud Build, Cloud Run, BigQuery. Use when lifting from local DuckDB MVP to staging/production infrastructure.
Bootstrap and verify Operator ETL in one command — Python check, uv install, sync deps, full proof gate. Use on first clone, "does it work", setup, or before any other operator skill.
Use when the user wants to operate, diagnose, or validate the Mini Data Engine MCP runtime from Codex; prefer the MCP surface over raw shell commands, start with projecttoolcatalog and projectgetdefaults, then use healthcheck, projectrunregression, explainrun, projectcomparebaseline, and related runtime tools.