llm-app-development — Claude Code skill: what it does, how to install
llm-app-development — a skill for Claude Code guides the design of RAG pipelines, autonomous agents, and structured schemas. Triggers when building chatbots, retrieval systems, or LLM-driven tools.
MIT 139 installs ★ 114 updated 2026-11-10
npx skills add travisjneuman/.claude --skill llm-app-development -a claude-codeWhat llm-app-development does
The skill sets architecture patterns and guardrails for software powered by large language models. It enforces grounding via retrieval over raw model memory, strict I/O typing with Zod schemas, and structured error handling for timeouts or hallucinations.
Reference material is split across dedicated documents in references/. They cover vector database selection, streaming responses, tool calling, semantic caching to curb token spend, and evaluation suites for output regressions.
Detailed instructions reside in standalone reference files, so the agent loads only the specific pattern needed for the current prompt.
What it helps with
- build a RAG architecture grounded in external data
- enforce typed LLM outputs using Zod schemas
- implement semantic caching to lower token expenses
- configure automated evaluation for model outputs
Example prompts for the agent
- Design a RAG retrieval pipeline for our documentation search
- Define a Zod schema to parse structured JSON from tool calls
- Help me pick a vector database according to the project reference guide
How to install llm-app-development
1Skills CLI (Vercel)
npx skills add travisjneuman/.claude --skill llm-app-development -a claude-code2Manually: put the files in place
~/.claude/skills/llm-app-development/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/llm-app-development/
1Skills CLI (Vercel)
npx skills add travisjneuman/.claude --skill llm-app-development -a codex2Manually: put the files in place
.agents/skills/llm-app-development/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add travisjneuman/.claude --skill llm-app-development -a cursor2Manually: put the files in place
.cursor/skills/llm-app-development/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install travisjneuman/.claude skills/llm-app-development2Manually: put the files in place
.github/skills/llm-app-development/SKILL.md1Skills CLI (Vercel)
npx skills add travisjneuman/.claude --skill llm-app-development -a gemini-cli2Platform CLI
gemini skills install https://github.com/travisjneuman/.claude --path skills/llm-app-developmentManually: put the files in place
.devin/skills/llm-app-development/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add travisjneuman/.claude --skill llm-app-development -a opencodeClaude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about llm-app-development
How to install llm-app-development in Claude Code?
Run npx skills add travisjneuman/.claude --skill llm-app-development -a claude-code.
What does llm-app-development do?
It provides architecture patterns and reference files for developing LLM software, focusing on RAG, agent tool use, typed outputs, caching, and output evaluation.
Which topics are covered in the reference files?
The files detail six core patterns including streaming and semantic caching, vector database selection, prompt engineering tips, anti-patterns, and a launch checklist.
Source text
SKILL.md · MIT
--- name: llm-app-development description: LLM app development with RAG, prompt engineering, vector databases, and AI agents --- # LLM Application Development ## Overview This skill covers the full spectrum of building applications powered by large language models. It addresses retrieval-augmented generation (RAG) pipelines, vector database integration, prompt engineering techniques, structured output generation, tool use and agentic patterns, evaluation frameworks, cost optimization, and streaming response handling. Use this skill when building chatbots, AI assistants, knowledge retrieval systems, content generation tools, autonomous agents, or any application that integrates LLM capabilities into its core functionality. --- ## Core Principles 1. **Retrieval over memorization** - Use RAG to ground LLM responses in real data rather than relying on model parametric memory. This reduces hallucination and keeps answers current. 2. **Structured I/O boundaries** - Define strict schemas for both inputs (system prompts, context) and outputs (typed responses via function calling or Zod schemas). Never trust raw LLM text for downstream logic. 3. **Evaluate before shipping** - Every LLM feature needs automated evaluation. Model outputs are non-deterministic; without eval, you cannot measure regressions or improvements. 4. **Cost-aware architecture** - Token usage drives cost. Cache aggressively, choose the smallest model that meets quality requirements, and batch where possible. 5. **Fail gracefully** - LLMs can refuse, hallucinate, or timeout. Every call path needs fallback behavior, retry logic, and user-visible error states. --- ## Reference files Detailed material is in separate files so this overview stays short. Read only the file whose topic matches the task; each one is self-contained. Paths are relative to the folder that holds this `SKILL.md` (in the full toolkit install, `~/.claude/skills/llm-app-development/`). | Topic | File | Covers | | --- | --- | --- | | Key Patterns | [`references/key-patterns.md`](references/key-patterns.md) | Pattern 1: RAG Pipeline Architecture; Pattern 2: Structured Output with Zod Schemas; Pattern 3: Tool Use and AI Agents; Pattern 4: Semantic Caching for Cost Optimization; Pattern 5: Streaming Responses; Pattern 6: LLM Output Evaluation | | Vector Database Selection Guide | [`references/vector-database-selection-guide.md`](references/vector-database-selection-guide.md) | 12 lines | | Prompt Engineering Quick Reference | [`references/prompt-engineering-quick-reference.md`](references/prompt-engineering-quick-reference.md) | 12 lines | | Anti-Patterns | [`references/anti-patterns.md`](references/anti-patterns.md) | 15 lines | | Checklist | [`references/checklist.md`](references/checklist.md) | 17 lines | ## Related Resources - **Skills:** `application-security` (prompt injection), `monitoring-observability` (LLM call tracing) - **Rules:** `docs/reference/stacks/react-typescript.md` (frontend patterns for chat UI) - **Rules:** `docs/reference/checklists/verification-template.md` (eval checklist)
© travisjneuman · MIT · travisjneuman/.claude