SecondLifes/delphi-expert

An opinionated ecosystem of rules, skills and steerings to elevate Delphi development to state-of-the-art with Artificial Intelligence.

This repository also configures its own agents. See what delphi-expert tells them →

3Stars on the repository
92Mods indexed here, across every type
6d agoLast push, which is what freshness is scored on
MITLicence, which decides whether bodies are shown

powershell-master

25

SecondLifes/delphi-expert

Skill Claude CodeCodex

Complete PowerShell expertise system across ALL platforms (Windows/Linux/macOS). PROACTIVELY activate for: (1) ANY PowerShell task (scripts/modules/cmdlets), (2) CI/CD automation (GitHub Actions/Azure DevOps/Bitbucket), (3) Cross-platform scripting, (4) Module discovery and management (PSGallery), (5)…

not rated 3 6d ago A 166 tokens original MIT

python

26

SecondLifes/delphi-expert

Skill Claude CodeCodex

General-purpose Python engineering skill — profiling/performance optimization, pytest-based testing (fixtures, mocking, async, property-based), and design principles (SRP, composition over inheritance, dependency injection). Use whenever writing, reviewing, testing, or optimizing Python code, including ad-hoc scripts…

not rated 3 6d ago A 67 tokens original MIT

rad-prompt-studio

27

SecondLifes/delphi-expert

Skill Claude CodeCodex

Adopts all five specialist lenses at once (Prompt Engineer & Analyst, Repo Auditor, DevOps/Config Engineer, Systems Forensics Analyst, Context Engineer) to create new prompts, analyze prompts/rules/skills/system architectures (single file or bulk workspace traversal), grade whether existing cross-AI analysis findings…

not rated 3 6d ago A 179 tokens original MIT

rad-repo-scaffold

28

SecondLifes/delphi-expert

Skill Codex

Gather a repository's purpose from a prompt or Markdown specification, resolve missing requirements, and create a minimal, purpose-fit AI-ready structure. Use when asked to initialize, scaffold, organize, or make a new or existing repository ready for Codex, Claude, Cursor, Cline, Roo, or other AI coding agents…

not rated 3 6d ago A 77 tokens original MIT

rad-skill-finder

29

SecondLifes/delphi-expert

Skill Claude CodeCodex

Searches for and recommends AI agent skills, plugins and MCP servers for a task or domain — across this workspace's own skill library, the vendor catalogs (anthropics/skills, openai/skills, microsoft/skills, NVIDIA/skills), the npx skills ecosystem, curated GitHub directories, MCP/plugin registries, and the public web…

not rated 3 6d ago C 179 tokens original MIT

rad-web-scraping

30

SecondLifes/delphi-expert

Skill Claude CodeCodex

General-purpose web scraping / structured data extraction skill — how to discover the most stable data source on a target site (API over DOM), which library to reach for (crawl4AI, ScrapeGraphAI, or plain HTTP), and how to write extraction scripts that survive site redesigns (retries, rate limiting, pagination). Use…

not rated 3 6d ago A 95 tokens original MIT

refactoring

31

SecondLifes/delphi-expert

Skill Claude CodeCodex

Refactoring techniques for Object Pascal focused on improving readability, removing code smells, and preserving behavior through practices like Extract Method, Guard Clauses, and polymorphism. Use when restructuring existing code without changing its behavior, not for a one-off review pass (see code-review) or…

not rated 3 6d ago A 66 tokens original MIT

tdd-dunitx

32

SecondLifes/delphi-expert

Skill Claude CodeCodex

Guidelines on how the AI ​​should act and code when the user requests TDD, unit tests, DUnitX or fakes/mocks using Interfaces in Delphi.

not rated 3 6d ago A 40 tokens copy · 97% MIT

threading

33

SecondLifes/delphi-expert

Skill Claude CodeCodex

Threading patterns in Delphi — TThread, TTask, TParallel, Synchronize, Queue, thread-safety, Producer-Consumer, pools, cancellation and debugging.

not rated 3 6d ago A 36 tokens original MIT

rad-code-fix

34

SecondLifes/delphi-expert

Skill Codex

Audits complete source files and their repository-internal dependencies, then repairs approved findings, implements a requested enhancement, or applies an already-written findings report — always in dependency order, always proven by measurement. Establishes a baseline first, finds correctness, safety, lifecycle…

not rated 3 6d ago A 175 tokens original MIT

At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: