llm-service-integration
Guide for integrating with LLM providers in the DEVS platform. Use this when asked to add LLM functionality, create AI-powered features, or work with the LLM service.
Discover Documentation skills, compare source repositories and read the instructions for each workflow.
Guide for integrating with LLM providers in the DEVS platform. Use this when asked to add LLM functionality, create AI-powered features, or work with the LLM service.
Guide for developing new features in the DEVS platform following the modular feature architecture. Use this when asked to add a new feature, create a feature module, or understand the feature structure.
Guide for creating and modifying Zustand stores with IndexedDB persistence in the DEVS platform. Use this when asked to create a new store, modify store logic, or work with state management.
Guide for adding internationalization support in the DEVS platform. Use this when asked to add new languages, translate strings, or work with i18n files.
Use when querying GitHub via GraphQL. Provides patterns for PR threads, comments, and mutations.
Use when resolving PR review threads. Enforces that all threads are marked resolved before completion.
Use when working with gh CLI. Provides patterns for PRs, issues, reviews, and repository operations.
Use when managing git worktrees. Provides patterns for creation, cleanup, and branch naming.
Use when checking if PR is ready to merge. Validates merge-readiness and PR status patterns.
Patterns for launching and managing parallel subagents efficiently.
Rules for evaluating, classifying, and deduplicating AI tool permissions
Build a Through-the-Door training set with reject inference using fuzzy augmentation, including PD-based sample weights; pairs with autogluon-tabularpredictor-fit for modeling the augmented data.
Official skill generator for VS Code Agent Skills; scaffolds new skills with correct directory structure and validation, and is the upstream dependency for authoring or modifying any other skill in this reposit...
Presentation creation, editing, and analysis. Use when the assistant needs to work with presentations (.pptx files) for: (1) Creating new presentations, (2) Modifying or editing content, (3) Working with layout...
Suite of tools for creating elaborate, multi-component chat-embedded HTML artifacts using modern frontend web technologies (React, Tailwind CSS, shadcn/ui). Use for complex artifacts requiring state management,...
Create beautiful visual art in .png and .pdf documents using design philosophy. You should use this skill when the user asks to create a poster, piece of art, design, or other static piece. Create original visu...
Render or build or compile Quarto .qmd files from the command line.
Applies a predefined brand color palette and typography rules to artifacts that need a consistent visual identity. Use it when brand colors or style guidelines, visual formatting, or company design standards ap...
Comprehensive spreadsheet creation, editing, and analysis with support for formulas, formatting, data analysis, and visualization. Use when the assistant needs to work with spreadsheets (.xlsx, .xlsm, .csv, .ts...
A set of resources to help me write all kinds of internal communications, using the formats that my company likes to use. Use this skill whenever asked to write internal communications (status reports, leadersh...
Guide users through a structured workflow for co-authoring documentation. Use when user wants to write documentation, proposals, technical specs, decision docs, or similar structured content. This workflow help...
Edit Quarto (.qmd) and Markdown (.md) files with proper nested code block handling to prevent parser errors and truncated output; standalone utility with no skill dependencies.
Creating algorithmic art using p5.js with seeded randomness and interactive parameter exploration. Use this when users request creating art using code, generative art, algorithmic art, flow fields, or particle...
Use DuckDB to query Parquet files, inspect metadata, join tables, and convert results to pandas for analysis; commonly precedes ydata-eda-profiling for EDA on extracted tables.
The default order uses GitHub repository stars from our indexed data. Stars belong to the source repository and may be shared by multiple skills. They indicate repository interest, not skill installs or an independent quality score.