By hpsgd
AI/ML engineer — prompt engineering, model evaluation, RAG pipelines, embeddings, AI feature implementation.
Bootstrap the AI/ML documentation structure for a project. Creates docs/ai/, generates initial templates, and writes domain CLAUDE.md. Idempotent — merges missing sections into existing files without overwriting.
Evaluate and compare models for a use case — quality, latency, cost, reliability, and safety benchmarks on your own data.
Design and document a production prompt — structured template, evaluation criteria, test cases, and version control strategy.
Design a RAG pipeline — chunking strategy, embedding selection, retrieval configuration, and end-to-end evaluation.
Uses power tools
Uses Bash, Write, or Edit tools
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
A plugin marketplace for Claude Code. Agents, skills, rules, and conventions that work together as a virtual team.
/plugin marketplace add hpsgd/turtlestack
Start with the core plugins (rules, thinking skills, and code review), then add agents for your stack:
/plugin install coding-standards@hpsgd
/plugin install writing-style@hpsgd
/plugin install security-compliance@hpsgd
/plugin install thinking@hpsgd
/plugin install tooling@hpsgd
/plugin install code-reviewer@hpsgd
/plugin install ai-engineer@hpsgd
Add a technology stack if relevant:
/plugin install dotnet-stack@hpsgd
/plugin install nextjs-stack@hpsgd
/plugin install python-stack@hpsgd
Then reload:
/reload-plugins
Browse the full plugin list below to see what else is available.
Per-project overrides. Create your own .claude/rules/ files. Project-level rules take precedence over marketplace rules.
Disabling a plugin. Set it to false in .claude/settings.json:
{
"enabledPlugins": {
"writing-style@hpsgd": false
}
}
Local overrides (not committed). Use .claude/settings.local.json for personal preferences that shouldn't affect the team.
{
"enabledPlugins": {
"coding-standards@hpsgd": true,
"writing-style@hpsgd": true,
"security-compliance@hpsgd": true,
"thinking@hpsgd": true,
"tooling@hpsgd": true,
"code-reviewer@hpsgd": true,
"dotnet-stack@hpsgd": true,
"nextjs-stack@hpsgd": true,
"python-stack@hpsgd": true,
"plugin-curator@hpsgd": true,
"coordinator@hpsgd": true,
"cpo@hpsgd": true,
"product-owner@hpsgd": true,
"ui-designer@hpsgd": true,
"ux-researcher@hpsgd": true,
"user-docs-writer@hpsgd": true,
"developer-docs-writer@hpsgd": true,
"internal-docs-writer@hpsgd": true,
"gtm@hpsgd": true,
"support@hpsgd": true,
"customer-success@hpsgd": true,
"grc-lead@hpsgd": true,
"cto@hpsgd": true,
"architect@hpsgd": true,
"react-developer@hpsgd": true,
"dotnet-developer@hpsgd": true,
"python-developer@hpsgd": true,
"ai-engineer@hpsgd": true,
"qa-lead@hpsgd": true,
"qa-engineer@hpsgd": true,
"release-manager@hpsgd": true,
"performance-engineer@hpsgd": true,
"devops@hpsgd": true,
"security-engineer@hpsgd": true,
"data-engineer@hpsgd": true,
"analyst@hpsgd": true,
"investigator@hpsgd": true,
"workflow-tools@hpsgd": true
}
}
After installing plugins, scaffold your project with domain-specific docs:
/coordinator:bootstrap-project my-project
npx claudepluginhub hpsgd/turtlestack --plugin ai-engineerInternal documentation writer — architecture docs, runbooks, changelogs, onboarding guides, ADR documentation. Writes for engineers who know the domain but may be new to the codebase.
Go-to-market specialist — positioning, launch strategy, content marketing, competitive analysis
Customer support — ticket triage, feedback synthesis, knowledge base, bug escalation
Security baseline rules and audit skills for maintaining secure code
Developer documentation writer — API references, SDK guides, integration tutorials, code examples. Writes for developers who are competent but unfamiliar with your codebase.
Agents for data engineering, machine learning, and AI development
Use this agent when implementing AI/ML features, integrating language models, building recommendation systems, or adding intelligent automation to applications. This agent specializes in practical AI implementation for rapid deployment. Examples:\n\n<example>\nContext: Adding AI features to an app\nuser: "We need AI-powered content recommendations"\nassistant: "I'll implement a smart recommendation engine. Let me use the ai-engineer agent to build an ML pipeline that learns from user behavior."\n<commentary>\nRecommendation systems require careful ML implementation and continuous learning capabilities.\n</commentary>\n</example>\n\n<example>\nContext: Integrating language models\nuser: "Add an AI chatbot to help users navigate our app"\nassistant: "I'll integrate a conversational AI assistant. Let me use the ai-engineer agent to implement proper prompt engineering and response handling."\n<commentary>\nLLM integration requires expertise in prompt design, token management, and response streaming.\n</commentary>\n</example>\n\n<example>\nContext: Implementing computer vision features\nuser: "Users should be able to search products by taking a photo"\nassistant: "I'll implement visual search using computer vision. Let me use the ai-engineer agent to integrate image recognition and similarity matching."\n<commentary>\nComputer vision features require efficient processing and accurate model selection.\n</commentary>\n</example>
Professional AI/ML Engineering toolkit: Prompt engineering, LLM integration, RAG systems, AI safety with 12 expert plugins
🤖 AI Engineer — AI Engineer + LLM Systems Specialist
LLM application development with RAG, embeddings, LangChain, and prompt engineering
Editorial "Agent Architect" bundle for Claude Code from Antigravity Awesome Skills.