gh-gist
Local-first workflow for iterative document building with GitHub gists
Discover Data & AI skills, compare source repositories and read the instructions for each workflow.
Local-first workflow for iterative document building with GitHub gists
C# 14 and .NET 10 coding patterns, idioms, and conventions
Conventional commit format, type selection, and commit best practices
GitHub PR review operations (inline comments, pending reviews, thread resolution)
GitHub API calls for discussions and draft PRs (non-standard gh CLI patterns)
Best practices for writing AGENTS.md, agent configs, and skill files based on industry research
When writing new code, model state as sum types from the start. Apply when creating entities with distinct modes, phases, or lifecycle states.
Refactor loose state models (optional fields, parallel booleans) into strict sum types. Apply when a field's validity depends on another field's value.
Run Nx generators to scaffold code or transform existing code - for example creating libraries or apps, creating components, or anything else that is boilerplate code or automates repetitive tasks.
Guide structuring new features in Nx workspaces. Use when user asks about creating libraries, organizing code, or where to place new features.
Generate a Product Requirements Document (PRD) for a new feature. Use when planning a feature, starting a new project, or when asked to create a PRD. Triggers on: create a prd, write prd for, plan this feature,...
Facebook automation including posting with privacy settings, interactions, messaging, and navigation workflows
Utilities and patterns for detecting execution environment (CI/CD vs local, network access, available ports, timeouts). Use when you need to adapt scripts or workflows based on where the agent is running, or wh...
Enforce tight coupling between components, tests, and stories with exact naming conventions. Use when creating new components, writing tests, or ensuring test/story files exist for all user-facing components.
Comprehensive testing and verification checklist for agent-created pull requests. Use when preparing to submit a PR, verifying changes work correctly, or ensuring all evidence requirements are met. Covers Docke...
Approved libraries, bundle optimization, and security best practices for dependencies. Use when adding new packages, optimizing bundle size, or ensuring secure dependency management.
Current state of CI/CD automation infrastructure, pre-built Docker images, and performance optimization strategies. Use when dealing with slow builds, container timeouts, yarn install issues, or when you need t...
Coding conventions and best practices for TypeScript, React 19, and Next.js 15. Use when writing new code, reviewing code quality, or ensuring consistency with Airbnb style guides and project-specific patterns.
Guide for migrating from PHP/MySQL to Payload CMS with PostgreSQL. Use when working on migration tasks, understanding data models, or implementing Payload collections. Covers migration strategy, architecture de...
Develop code using Shipbox sandboxes with real Cloudflare containers. Use when the user wants to run code in a sandbox, test in isolation, or deploy workers.
Provide concise project / bead status and run Beads/waif helpers to augment results. Trigger on user queries such as: 'What is the current status?', 'Status of the project?', 'What is the status of ?', 'audit',...
Clean up completed work: inspect branches, update main, remove merged branches (local and optionally remote), reconcile beads, and produce a concise report. Trigger on queries like: 'clean up', 'tidy up', 'prun...
Auhors a brand new OpenCode command following project best practices and conventions. Trigger on user queries such as: 'Create a new command to ', 'Author a command that ', 'I need a command that '.
analyzerアプリケーションのアーキテクチャレビュー。Port&Adapterアーキテクチャ(ヘキサゴナルアーキテクチャ)のルールに従っているかをチェックします。新しいPort/Adapter/Usecase/Model追加時、PRレビュー時、またはアー...
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.