Home / iuliandita / skills · skills/llm-app-development/SKILL.md · GitHub

llm-app-development skillA

llm-app-development is agent-read markdown (skill) from iuliandita/skills: Build LLM applications: RAG, embeddings, agents, structured outputs, evaluations, fine-tuning, and local inference..

Indexed from public GitHub and served as immutable, content-addressed versions. Install it pinned to an exact SHA-256 with the mdr CLI, and every file is verified against the hash recorded here before it reaches your agent. The deterministic audit below grades the latest version, and the same file always earns the same grade.

What the file says

# LLM Application Development

Build, review, and architect applications that use AI models - from single-API calls to
multi-agent systems with RAG pipelines. The goal is production-grade AI apps that are reliable,
cost-effective, and don't hallucinate their way into an incident.

**Target versions**: September 2026 snapshot. Read `references/target-versions.md` before
pinning model IDs (Claude/OpenAI families), SDKs, runtimes, vector stores, or evaluation tools.

## When to use

- Integrating LLM APIs (Anthropic, OpenAI, etc.) into applications
- Building RAG pipelines (chunking, embedding, retrieval, generation)
- Designing agent systems (tool use, loops, state, multi-agent)
- Choosing between fine-tuning, RAG, and prompt engineering
- Setting up vector stores for semantic search
- Implementing structured output and tool use / function calling
- Building evaluation and testing harnesses for AI features
- Optimizing token costs, latency, and model routing
- Setting up local inference with Ollama or vLLM
- Adding safety guardrails (content filtering, PII handling, output validation)

## When NOT to use

- Building MCP servers or tools (use **mcp** - it handles the protocol layer)
…

Read the whole file at its exact version.

How to install

Latest version
mdr add iuliandita/skills/llm-app-development@git:20260920.ebf9a3d
Exact content
mdr add iuliandita/skills/llm-app-development@sha256:66707cbbea8db2ee

Pin to a label to follow the author's releases, or to a sha256 to freeze the exact bytes forever. Either way the resolved hash is written to mdr.lock, and mdr install reproduces it on any machine.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_552ozi2u7duxa6e7.svg)](https://markdownregistry.com/a/art_552ozi2u7duxa6e7)

1 badge views in 30 days

Versions

versioncommittedcommitsizeaudit
git:20260920.ebf9a3d latest2026-09-20 ebf9a3d 24,754 BA view · diff
git:20260920.ac018532026-09-20 ac01853 24,643 BA view

Audit of the latest version

A  17 of 17 checks passed. Deterministic, no model, same answer every run.
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (24754 bytes)
  • pass: No zero-width or bidi control characters
  • pass: No instruction hidden inside an HTML comment
  • pass: No link to an exfiltration or paste host
  • pass: No credential-shaped string
  • pass: No instruction to send local credentials anywhere
  • pass: No text hidden with inline styles
  • pass: No prompt-injection phrasing
  • pass: No curl or wget piped into a shell
  • pass: No recursive delete of root, home or parent
  • pass: No instruction to read or print local credentials
  • pass: No base64 blob over 200 characters
  • pass: No link to a raw IP address
  • pass: No script tag

Source

GitHub

iuliandita/skills · 7 stars · license MIT · pushed 2026-09-24 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_552ozi2u7duxa6e7
GET https://markdownregistry.com/api/v1/resolve?ref=iuliandita/skills/llm-app-development
GET https://markdownregistry.com/api/v1/blob/66707cbbea8db2ee3de5112dfd194c96140380b5a614b9b1c95aeb770fa9b9d7

Your agent does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.

More from iuliandita/skills

ai-ml skill
iuliandita/skills · skills/ai-ml/SKILL.md · Deprecated name. Use llm-app-development; load this notice only when ai-ml is explicitly requested.
git:20260920.ac01853 · audit A · 7 stars
ansible skill
iuliandita/skills · skills/ansible/SKILL.md · Write, review, and debug Ansible playbooks, roles, inventories, Ansible Vault, Molecule tests, and AWX/AAP.
git:20260920.ac01853 · audit A · 7 stars
anti-ai-prose skill
iuliandita/skills · skills/anti-ai-prose/SKILL.md · Edit prose that sounds AI-written: remove filler and canned phrasing in docs, emails, and replies.
git:20260920.ac01853 · audit A · 7 stars
anti-slop skill
iuliandita/skills · skills/anti-slop/SKILL.md · Deprecated name. Use code-simplification; load this notice only when anti-slop is explicitly requested.
git:20260920.ac01853 · audit A · 7 stars
arch-btw skill
iuliandita/skills · skills/arch-btw/SKILL.md · Deprecated name. Use arch-linux; load this notice only when arch-btw is explicitly requested.
git:20260920.ac01853 · audit A · 7 stars
arch-linux skill
iuliandita/skills · skills/arch-linux/SKILL.md · Administer Arch Linux, CachyOS, EndeavourOS, and Manjaro: pacman, AUR, upgrades, boot, GPU, and desktop issues.
git:20260920.ebf9a3d · audit A · 7 stars
backend-api skill
iuliandita/skills · skills/backend-api/SKILL.md · Design and review REST/HTTP APIs, with bounded GraphQL and gRPC contract guidance: OpenAPI, auth, pagination…
git:20260920.ac01853 · audit A · 7 stars
browse skill
iuliandita/skills · skills/browse/SKILL.md · Deprecated and removed. Load this notice only when browse is explicitly requested; no replacement skill.
git:20260920.ac01853 · audit A · 7 stars
ci-cd skill
iuliandita/skills · skills/ci-cd/SKILL.md · Build, review, and debug CI/CD pipelines and runners: GitHub Actions, GitLab CI, Forgejo/Gitea, and Woodpecker.
git:20260920.ebf9a3d · audit A · 7 stars
cluster-health skill
iuliandita/skills · skills/cluster-health/SKILL.md · Deprecated name. Use kubernetes-health; load this notice only when cluster-health is explicitly requested.
git:20260920.ac01853 · audit A · 7 stars
code-review skill
iuliandita/skills · skills/code-review/SKILL.md · Review code and diffs for correctness: bugs, regressions, edge cases, races, and resource leaks.
git:20260920.ac01853 · audit A · 7 stars
code-simplification skill
iuliandita/skills · skills/code-simplification/SKILL.md · Review code for dead code, duplication, overengineering, invented APIs, and weak tests. Report safe reductions; no…
git:20260920.ebf9a3d · audit A · 7 stars

Every file in iuliandita/skills

Browse by kind, by grade A, or by owner.