Ready to supercharge your AI agents?

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

Prompt Engineering Patterns · dokhacgiakhoa | DecimalAI

ai mlby dokhacgiakhoa

Prompt Engineering Patterns

dokhacgiakhoa/prompt-engineering-patterns

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

Master advanced prompt engineering techniques to maximize LLM performance, reliability, and controllability in production.

SkillScore82Maintained

Automatic

AI Engineer pack

Last verified 8/29/2026

What it changes

Passed 18 of 22 test cases with the skill, and 17 of 22 without it.

Without skill77%

With skill82%

Checks it passed that the model alone missed

Recommends evaluating each rubric criterion sequentially in separate prompt steps

1 fixed17 passed either way4 still failing0 broke

Pass-rate lift: +5 pp
Tokens: +15%
Agent turns: 0%
Response time: +6%

Model gemini-3.6-flashMeasured 8/29/2026v118 of 22 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-prompt-engineering-patterns/SKILL.md https://app.decimal.ai/s/dokhacgiakhoa-prompt-engineering-patterns/SKILL.md

Want it pinned and updatable? pip install "decimalai>=0.15", then decimalai skills add dokhacgiakhoa-prompt-engineering-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-prompt-engineering-patterns/ and pins it in .decimal/skills.lock

decimalai skills add dokhacgiakhoa-prompt-engineering-patterns

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

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

Raw file: /s/dokhacgiakhoa-prompt-engineering-patterns/SKILL.md ↗ · machine-readable summary at /s/dokhacgiakhoa-prompt-engineering-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 need an LLM workflow to grade student essays against a 5-criterion rubric. Passing the entire essay and all 5 rubrics in one prompt yields inconsistent scores. How can progressive disclosure or multi-step prompting improve grading accuracy?

What was checked, without and with the skill
Checked	Without skill	With skill
Recommends evaluating each rubric criterion sequentially in separate prompt steps	Missed	Passed

case-22 · 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.md42 lines9 filesincludes scripts

Prompt Engineering Patterns

Master advanced prompt engineering techniques to maximize LLM performance, reliability, and controllability.

Do not use this skill when

The task is unrelated to prompt engineering patterns
You need a different domain or tool outside this scope

Instructions

Clarify goals, constraints, and required inputs.
Apply relevant best practices and validate outcomes.
Provide actionable steps and verification.
If detailed examples are required, open resources/implementation-playbook.md.

Use this skill when

Designing complex prompts for production LLM applications
Optimizing prompt performance and consistency
Implementing structured reasoning patterns (chain-of-thought, tree-of-thought)
Building few-shot learning systems with dynamic example selection
Creating reusable prompt templates with variable interpolation
Debugging and refining prompts that produce inconsistent outputs
Implementing system prompts for specialized AI assistants

Core Capabilities

🧠 Knowledge Modules (Fractal Skills)

1. 1. Few-Shot Learning

2. 2. Chain-of-Thought Prompting

3. 3. Prompt Optimization

4. 4. Template Systems

5. 5. System Prompt Design

6. Progressive Disclosure

7. Instruction Hierarchy

8. Error Recovery

9. With RAG Systems

10. With Validation

Track record

Benchmark

18 / 22

test cases passed, vs 17 / 22 without

Adoption

Users: 1
Times used: 17

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/prompt-engineering-patterns/SKILL.md

View on GitHub ↗

License NOASSERTIONImported 8/10/2026Version v1Bundled 8 files · scripts

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

Prompt Engineering Patterns

Do not use this skill when

Instructions

Use this skill when

Core Capabilities

🧠 Knowledge Modules (Fractal Skills)

1. 1. Few-Shot Learning

2. 2. Chain-of-Thought Prompting

3. 3. Prompt Optimization

4. 4. Template Systems

5. 5. System Prompt Design

6. Progressive Disclosure

7. Instruction Hierarchy

8. Error Recovery

9. With RAG Systems

10. With Validation

Track record

Benchmark

Adoption

SkillSafety

Source

Other skills for the same job

Related skills