Skills prompt-engineering-patterns

📦

prompt-engineering-patterns

Name: prompt-engineering-patterns
Author: wshobson

Content revision r1 Safe 📁 Filesystem access⚙️ External commands

Optimize Prompts With Proven Patterns

LLM prompts can fail through unclear instructions, weak examples, or missing evaluation. This skill provides templates, reasoning patterns, and optimization workflows for Claude, Codex, and Claude Code.

Supports: Claude Codex Code(CC)

💎 86 Featured

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/wshobson-prompt-engineering-patterns.md and its manifest at https://skillstore.io/api/skills/wshobson-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.

Markdown detail GET /skills/wshobson-prompt-engineering-patterns.md Signed manifest GET /api/skills/wshobson-prompt-engineering-patterns/manifest Signed lockfile GET /api/skills/wshobson-prompt-engineering-patterns/lockfile

Test it

Using "prompt-engineering-patterns". Improve a sentiment classification prompt for support tickets.

Expected outcome:

A refined instruction, three labeled examples, validation criteria, and notes on ambiguous tickets.

Using "prompt-engineering-patterns". Create a prompt testing plan for a RAG answer generator.

Expected outcome:

A test matrix covering groundedness, citation quality, refusal behavior, latency, and failure tracking.

Using "prompt-engineering-patterns". Design a system prompt for a data analyst assistant.

Expected outcome:

A role definition, supported tasks, constraints, reporting format, and a checklist for validating responses.

Security Audit

Safe

v7 • 7/8/2026 Open versioned report

The audit found one real medium-risk filesystem issue: scripts/optimize-prompt.py writes optimization results to a caller-provided filename. The remaining static hits are false positives from documentation examples, JSON snippets, Python dictionary key access, and Markdown code fences. No evidence found of malicious prompt injection or data exfiltration intent in the reviewed files.

Files scanned

2,682

Lines analyzed

Review items

False positives ignored

Capability review items (1)

These are real local capabilities that may be expected for this skill, so they require review but are not counted as confirmed malicious behavior.

Medium

scripts/optimize-prompt.py:229

Python file write/append

with open(filename, 'w') as f:

scripts/optimize-prompt.py writes optimization history to a caller-provided filename. If that filename comes from untrusted input, it could overwrite local files.

Risk Factors

📁 Filesystem access (2)

references/prompt-optimization.md:128 scripts/optimize-prompt.py:229

⚙️ External commands (7)

SKILL.md:59-82 SKILL.md:82-102 SKILL.md:102-104 SKILL.md:104-134 SKILL.md:134-144 SKILL.md:144-147 SKILL.md:147-158

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.

Open versioned report

Copy report link

https://skillstore.io/skills/wshobson-prompt-engineering-patterns/audits/7?utm_source=security_passport&utm_medium=share&utm_campaign=versioned_report

Markdown badge

[![Skillstore security assessment](https://skillstore.io/badges/skills/wshobson-prompt-engineering-patterns/security.svg)](https://skillstore.io/skills/wshobson-prompt-engineering-patterns?utm_source=security_passport_badge)

HTML badge

<a href="https://skillstore.io/skills/wshobson-prompt-engineering-patterns?utm_source=security_passport_badge"><img src="https://skillstore.io/badges/skills/wshobson-prompt-engineering-patterns/security.svg" alt="Skillstore security assessment" loading="lazy"></a>

Embed card

<iframe src="https://skillstore.io/embed/skills/wshobson-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

wshobson. (2026). prompt-engineering-patterns security audit report (audit version 7) [Author version unspecified]. Skillstore. https://skillstore.io/skills/wshobson-prompt-engineering-patterns/audits/7

BibTeX citation

@techreport{wshobson-wshobson-prompt-engineering-patterns-2026,
  author = {wshobson},
  title = {prompt-engineering-patterns security audit report (audit version 7)},
  institution = {Skillstore},
  year = {2026},
  number = {7},
  url = {https://skillstore.io/skills/wshobson-prompt-engineering-patterns/audits/7},
  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 7)"
version: "unspecified"
type: report
authors:
  - name: "wshobson"
date-released: "2026-07-08"
url: "https://skillstore.io/skills/wshobson-prompt-engineering-patterns/audits/7"
identifiers:
  - type: other
    value: "skillstore:wshobson-prompt-engineering-patterns:audit:7"
    description: "Skillstore immutable audit report identifier"

Compare variants

2 installable variants

Each 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 Current

wshobson-prompt-engineering-patterns

Skillstore Score 86

Evidence Confidence High

Skillstore usage 154

Updated

2026-08-21

sickn33

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

Architecture

Maintainability

Content

Community

Spec Compliance

What You Can Build

Design reliable LLM workflows

Design reliable prompts for agents, RAG features, classification flows, and structured generation.

Plan prompt quality metrics

Define prompt tests and success metrics before shipping model-backed workflows.

Standardize reusable templates

Turn reusable instructions into clear templates for documentation, support, and analysis tasks.

Try These Prompts

Create a Basic Prompt

Use this skill to improve a prompt for {task}. Keep the output format simple. Explain the revised prompt and why each change helps.

Add Few-Shot Examples

Use this skill to design three few-shot examples for {task}. Include typical inputs, edge cases, and the expected output style.

Build an Evaluation Plan

Use this skill to create an evaluation plan for {prompt_name}. Define metrics, test cases, failure categories, and an iteration process.

Design a Production Prompt System

Use this skill to design a production prompt system for {application}. Include system prompt structure, template variables, validation rules, versioning, and rollback guidance.

Best Practices

Start with the simplest prompt that can meet the task, then add examples or reasoning only when tests show a need.
Version prompts and evaluate changes with stable test cases before production use.
Separate role, task, context, examples, and output format so each part can be reviewed.

Avoid

Adding long reasoning instructions to simple tasks that need direct answers.
Using examples that do not match the input distribution or expected output style.
Treating prompt templates as safe without testing edge cases, policy limits, and failure modes.