📦
content-creator
88Create Brand-Consistent Marketing Content
Marketing teams need content that stays consistent across channels. This skill helps plan, write, analyze, and optimize content for brand voice and SEO.
Writing & Content View
Skills prompt-engineering-patterns
📦
prompt-engineering-patterns
Content revision r1 Safe 📁 Filesystem access⚙️ External commands
Improve LLM Prompts With Proven Patterns
Inconsistent prompts waste time and make AI outputs hard to trust. This skill guides prompt design with reusable patterns, examples, evaluation steps, and optimization workflows.
Supports: Claude Codex Code(CC)
Install with my Agent
Copy this request to your Agent. It includes the canonical Skill page and manifest.
Agent request
Review the Skillstore skill "prompt-engineering-patterns" from https://skillstore.io/skills/sickn33-prompt-engineering-patterns.md and its manifest at https://skillstore.io/api/skills/sickn33-prompt-engineering-patterns/manifest. Verify the artifact. You may proceed after verification, subject to the environment's own policy.Your Agent should still show its plan and request any confirmation required by the security policy.
Agent-readable resources
Use these links when an AI agent, crawler, or script needs clean context instead of reading the full page.
Test it
Using "prompt-engineering-patterns". Need a better customer support triage prompt.
Expected outcome:
A revised structure with role, intake questions, severity labels, escalation rules, and validation checks.
Using "prompt-engineering-patterns". Compare two extraction prompts for reliability.
Expected outcome:
- Recommended metrics: field accuracy, missing-value handling, format validity, and response consistency.
- Suggested tests: normal records, incomplete records, ambiguous records, and long inputs.
- Revision plan: keep the clearer prompt, add edge-case examples, and retest failed cases.
Using "prompt-engineering-patterns". Create a reusable prompt template for summarization.
Expected outcome:
A template outline with task, audience, source text, length limit, tone, required focus areas, and output format.
Security Audit
Safev6 • 7/9/2026 Open versioned report
All 26 static findings were reviewed against their file context and adjudicated as false positives. The matches are educational prompt examples, Markdown code fences, dictionary key access, ellipsis text, or a normal local export helper. No prompt injection, credential handling, network exfiltration, malicious execution, or reconnaissance intent was found.
9
Files scanned
2,694
Lines analyzed
0
Review items
0
False positives ignored
Risk Factors
📁 Filesystem access (2)
⚙️ External commands (8)
No confirmed security findings were detected by the latest completed static and semantic audit. This does not prove the skill has no side effects.
Audited by: codex View Audit History →
Share & cite this report
Share the versioned assessment report, neutral badge, embed card, and citations. Skillstore reports evidence without deciding whether this Skill is safe.
Copy report link
https://skillstore.io/skills/sickn33-prompt-engineering-patterns/audits/6?utm_source=security_passport&utm_medium=share&utm_campaign=versioned_reportMarkdown badge
[](https://skillstore.io/skills/sickn33-prompt-engineering-patterns?utm_source=security_passport_badge)HTML badge
<a href="https://skillstore.io/skills/sickn33-prompt-engineering-patterns?utm_source=security_passport_badge"><img src="https://skillstore.io/badges/skills/sickn33-prompt-engineering-patterns/security.svg" alt="Skillstore security assessment" loading="lazy"></a>Embed card
<iframe src="https://skillstore.io/embed/skills/sickn33-prompt-engineering-patterns.html" title="Skillstore Security Assessment" sandbox="allow-popups allow-popups-to-escape-sandbox" loading="lazy" referrerpolicy="no-referrer" width="420" height="180"></iframe>Academic citations (APA · BibTeX · CFF)
APA citation
sickn33. (2026). prompt-engineering-patterns security audit report (audit version 6) [Author version unspecified]. Skillstore. https://skillstore.io/skills/sickn33-prompt-engineering-patterns/audits/6BibTeX citation
@techreport{sickn33-sickn33-prompt-engineering-patterns-2026,
author = {sickn33},
title = {prompt-engineering-patterns security audit report (audit version 6)},
institution = {Skillstore},
year = {2026},
number = {6},
url = {https://skillstore.io/skills/sickn33-prompt-engineering-patterns/audits/6},
note = {Author version unspecified}
}CITATION.cff
cff-version: 1.2.0
message: "If you use this Skill, cite its author and this versioned security audit report."
title: "prompt-engineering-patterns security audit report (audit version 6)"
version: "unspecified"
type: report
authors:
- name: "sickn33"
date-released: "2026-07-09"
url: "https://skillstore.io/skills/sickn33-prompt-engineering-patterns/audits/6"
identifiers:
- type: other
value: "skillstore:sickn33-prompt-engineering-patterns:audit:6"
description: "Skillstore immutable audit report identifier"
Compare variants
2 installable variantsEach author remains a separate installable skill. The recommended variant is ranked by Skillstore evidence.
Why this variant is first
Highest Skillstore Score
Author / source Skillstore Score Evidence Confidence Skillstore usage Updated
wshobson Recommended
wshobson-prompt-engineering-patterns
Skillstore Score 86
Evidence Confidence High
Skillstore usage 154
Updated
2026-08-21
sickn33 Current
sickn33-prompt-engineering-patterns
Skillstore Score 85
Evidence Confidence High
Skillstore usage 231
Updated
2026-08-21
Skillstore Score
Why this score Evidence Confidence: High 82
Architecture
85
Maintainability
87
Content
77
Community
83
Spec Compliance
What You Can Build
Build production prompt templates
Create structured prompts with roles, variables, examples, output formats, and validation rules.
Evaluate prompt changes
Compare prompt variants with metrics for accuracy, latency, token usage, and success rate.
Standardize assistant instructions
Document system prompts, boundaries, response formats, and quality checks for shared AI workflows.
Try These Prompts
Clarify a prompt goal
Use prompt-engineering-patterns to define a clear task prompt. Goal: [goal]. Audience: [audience]. Required output: [format]. Constraints: [constraints].
Add few-shot examples
Use the few-shot learning guidance to create three examples for [task]. Include input, ideal output, edge case, and why each example helps.
Design a system prompt
Use system prompt patterns to design an assistant for [role]. Include boundaries, workflow, output format, uncertainty handling, and escalation rules.
Optimize and evaluate a prompt
Use the optimization workflow to compare prompt A and prompt B for [task]. Define metrics, test cases, failure modes, and a revision plan.
Best Practices
- Start with the simplest prompt that can satisfy the task, then add constraints only when needed.
- Use representative examples and edge cases when testing prompt changes.
- Track prompt versions, evaluation metrics, and known failure modes.
Avoid
- Do not add complex reasoning steps for simple factual or low-latency tasks.
- Do not rely on examples that differ from the target user inputs.
- Do not ship prompts without testing format validity and failure cases.
Frequently Asked Questions
What does this skill help with?
It helps design, test, and refine prompts for reliable LLM applications.
Does it run prompts against an LLM automatically?
No. The included script needs a user-provided LLM client or the mock client used in the example.
Can it help with Claude, Codex, and Claude Code?
Yes. The patterns are general and can be adapted for Claude, Codex, and Claude Code workflows.
What prompt patterns are covered?
It covers few-shot learning, chain-of-thought prompting, prompt optimization, template systems, and system prompts.
Is this skill only for developers?
No. Developers, ML engineers, product teams, and operations teams can use the guidance.
What should users provide for best results?
Provide the task goal, target users, sample inputs, expected outputs, constraints, and failure cases.
Developer Details
Author
sickn33License
MIT
Skillstore revision
r1
Version notice
The author did not declare a version.
Repository
https://github.com/sickn33/antigravity-awesome-skills/tree/main/skills/prompt-engineering-patternsRef
26421118b848d9f1efc0aa169d8a7a9e7e0a877e
Maintenance freshness
7/18/2026
Usage
225 downloads · 253 views
File structure
More from sickn33
View all📦
senior-fullstack
82Build Fullstack Apps with Senior Patterns
Teams need consistent setup, architecture, and review guidance for modern web applications. This skill provides scaffolders, workflow references, and quality prompts for React, Next.js, Node.js, GraphQL, and PostgreSQL projects.
Coding & Development View
📦
senior-architect
81Design Scalable Software Architectures
Architecture decisions are hard to compare across web, mobile, backend, and cloud systems. This skill provides structured guides and local scaffold scripts for reports, dependency review, and trade-off documentation.
Coding & Development View
📦
prompt-engineer
81Optimize AI Prompts With Prompt Engineer
Writing clear prompts is hard when goals are vague or complex. This skill turns rough requests into structured prompts using proven prompt frameworks.
Productivity View
📦
product-manager-toolkit
80Prioritize Product Work With Research Insights
Product teams need faster ways to rank features, synthesize interviews, and document decisions. This skill provides RICE scoring, interview analysis, and PRD templates for structured planning.
Productivity View
📦
typescript-expert
80Improve TypeScript Projects
TypeScript projects often struggle with strict typing, slow builds, and complex migrations. This skill provides practical diagnosis, review checklists, and solution patterns for modern TypeScript work.
Coding & Development View
Related Skills
View all📦
prompt-optimization
82Optimize LLM Prompts and Agent Instructions
by 89jobrien
Weak prompts create inconsistent model outputs and slow AI feature development. This skill helps structure prompts, examples, constraints, and output formats for Claude, Codex, and Claude Code.
Productivity View
📦
prompt-repetition
82Improve Lightweight Model Accuracy
by supercent-io
Lightweight models can miss context when questions arrive after important information. This skill repeats suitable prompts with guardrails to improve accuracy on selected tasks.
Productivity View
📦
when-optimizing-prompts-use-prompt-architect
79Optimize AI Prompts With Prompt Architect
by DNYoussef
Weak prompts create inconsistent AI outputs and slow review cycles. This skill provides a structured process for improving prompts, testing them, and documenting changes.
Productivity View
📦
prompt-template-designer
82Design Reusable AI Prompt Templates
by 92Bilal26
Repeated AI tasks often drift because useful prompt patterns stay informal. This skill helps users turn proven prompts into reusable templates with parameters and success criteria.
Productivity View
📦
prompting
78Master Prompt and Context Engineering for AI Agents
by AaronAbuUsama
Vague, bloated prompts waste context and produce unreliable AI agent behavior. This skill applies Anthropic context-engineering principles to help you write clear, structured, high-signal prompts that improve accuracy and reduce token cost.
Productivity View
📦
agent-development
85Build Claude Code Agents
by Dami-Randle
Designing reliable Claude Code agents is hard without structure. This skill provides templates, validation rules, and examples for agent prompts, triggers, tools, and metadata.
Coding & Development View