Ready to supercharge your AI agents?

Install any skill in seconds. Free to start, no credit card required.

🤖 LLM Application Patterns · dokhacgiakhoa | DecimalAI

ai mlby dokhacgiakhoa

🤖 LLM Application Patterns

dokhacgiakhoa/llm-app-patterns

Source dokhacgiakhoa/agent-skills-4-vibe-coding-cli ↗License NOASSERTION

Production-ready patterns for building LLM applications. Covers RAG pipelines, agent architectures, prompt IDEs, and LLMOps monitoring.

NewMaintained

Automatic

AI Engineer pack

Last verified 8/29/2026

What it changes

Passed 23 of 24 test cases with the skill, and 23 of 24 without it.

Without skill96%

With skill96%

Checks it passed that the model alone missed

Recommends context overlap between adjacent text chunks.

1 fixed22 passed either way0 still failing1 broke

Pass-rate lift: 0 pp
Tokens: +32%
Agent turns: 0%
Response time: +3%

Model gemini-3.6-flashMeasured 8/29/2026v123 of 24 cases passed with skill

Tokens, turns and time describe resource use, not a dollar price.

Use this skill

Save it into your project's skills folder. Claude Code picks it up in its next session.

curl -fsSL --create-dirs -o .claude/skills/dokhacgiakhoa-llm-app-patterns/SKILL.md https://app.decimal.ai/s/dokhacgiakhoa-llm-app-patterns/SKILL.md

Want it pinned and updatable? pip install "decimalai>=0.15", then decimalai skills add dokhacgiakhoa-llm-app-patterns, and start Claude Code with claude --plugin-dir "$(git rev-parse --show-toplevel)/.agents"

1 · One-time — install the CLI (docs ↗)

pip install "decimalai>=0.15"

2 · Get the skill — writes .agents/skills/dokhacgiakhoa-llm-app-patterns/ and pins it in .decimal/skills.lock

decimalai skills add dokhacgiakhoa-llm-app-patterns

No CLI? Get the same file — curl · raw file

curl -fsSL --create-dirs -o .claude/skills/dokhacgiakhoa-llm-app-patterns/SKILL.md https://app.decimal.ai/s/dokhacgiakhoa-llm-app-patterns/SKILL.md

Raw file: /s/dokhacgiakhoa-llm-app-patterns/SKILL.md ↗ · machine-readable summary at /s/dokhacgiakhoa-llm-app-patterns.json ↗

Safety checks: 3 of 3 passed

Code scan CleanIntent PassedContent Clean

See it in action

A test case the skill fixed. Same model, same prompt, with and without the skill.

Prompt

We are building a vector search system over technical PDF manuals. Should we split the documents using strict character-count sliding windows of 500 characters, or is there a better chunking strategy for structured documents? Provide an architectural recommendation.

What was checked, without and with the skill
Checked	Without skill	With skill
Recommends structure-aware chunking based on document headers rather than fixed character lengths.	Passed	Passed
Recommends context overlap between adjacent text chunks.	Missed	Passed

case-02 · gemini-3.6-flash · 8/29/2026 · answers are capped and redacted

What's inside

The instructions your model reads when the skill loads.

SKILL.md38 linessingle file

🤖 LLM Application Patterns

Production-ready patterns for building LLM applications, inspired by Dify and industry best practices.

When to Use This Skill

Use this skill when:

Designing LLM-powered applications
Implementing RAG (Retrieval-Augmented Generation)
Building AI agents with tools
Setting up LLMOps monitoring
Choosing between agent architectures

1. RAG Pipeline Architecture

🧠 Knowledge Modules (Fractal Skills)

1. Overview

2. 1.1 Document Ingestion

3. 1.2 Embedding & Storage

4. 1.3 Retrieval Strategies

5. 1.4 Generation with Context

6. 2.1 ReAct Pattern (Reasoning + Acting)

7. 2.2 Function Calling Pattern

8. 2.3 Plan-and-Execute Pattern

9. 2.4 Multi-Agent Collaboration

10. 3.1 Prompt Templates with Variables

11. 3.2 Prompt Versioning & A/B Testing

12. 3.3 Prompt Chaining

13. 4.1 Metrics to Track

14. 4.2 Logging & Tracing

15. 4.3 Evaluation Framework

16. 5.1 Caching Strategy

17. 5.2 Rate Limiting & Retry

18. 5.3 Fallback Strategy

Track record

Benchmark

23 / 24

test cases passed, vs 23 / 24 without

Adoption

Users: 0
Times used: 0

Safety and source details

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v4 — 8/10/2026

View 15 scanner checks

live_secretremote_code_executionreverse_shelldata_exfiltrationssrf_metadataagent_snoopinganti_refusaldestructive_commandsobfuscated_unicodeunicode_homoglyphopaque_blobsuspicious_urltool_overreachtrigger_abuseprompt_injection_phrasing

IntentSafe

LLM judge · does the skill do what it claims

ContentClean

LLM judge · policy & harmful-content review

Source

Imported

dokhacgiakhoa / agent-skills-4-vibe-coding-cli

.agent/skills/llm-app-patterns/SKILL.md

View on GitHub ↗

License NOASSERTIONImported 8/10/2026Version v1

Other skills for the same job

Published skills whose descriptions closely match this one, with their headline benchmark lift.

More skills from the same source and nearby in the registry, with their headline benchmark lift.

Ready to supercharge your AI agents?

See it in action

What's inside

🤖 LLM Application Patterns

When to Use This Skill

1. RAG Pipeline Architecture

🧠 Knowledge Modules (Fractal Skills)

1. Overview

2. 1.1 Document Ingestion

3. 1.2 Embedding & Storage

4. 1.3 Retrieval Strategies

5. 1.4 Generation with Context

6. 2.1 ReAct Pattern (Reasoning + Acting)

7. 2.2 Function Calling Pattern

8. 2.3 Plan-and-Execute Pattern

9. 2.4 Multi-Agent Collaboration

10. 3.1 Prompt Templates with Variables

11. 3.2 Prompt Versioning & A/B Testing

12. 3.3 Prompt Chaining

13. 4.1 Metrics to Track

14. 4.2 Logging & Tracing

15. 4.3 Evaluation Framework

16. 5.1 Caching Strategy

17. 5.2 Rate Limiting & Retry

18. 5.3 Fallback Strategy

Track record

Benchmark

Adoption

SkillSafety

Source

Other skills for the same job

Related skills