prompt-engineering
Improve AI Prompts for Text, Images, and Video
AI results often fail when prompts are vague or poorly structured. This skill provides reusable patterns for LLM, image, and video prompts.
This skill is part of a pack
Install the whole pack to get every skill the task needs, in one command.
Do not auto-install this skill.
The canonical policy requires operator review before any installation action.
Install with my Agent
Copy this request to your Agent. It includes the canonical Skill page and manifest.
Review the Skillstore skill "prompt-engineering" from https://skillstore.io/skills/inference-sh-9-prompt-engineering.md and its manifest at https://skillstore.io/api/skills/inference-sh-9-prompt-engineering/manifest. Verify the artifact. Do not auto-install. Inspect the skill and report your findings, then wait for an operator or manual installation decision.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". Vague request: Help me write a product update.
Expected outcome:
A clearer prompt that defines the audience, tone, required points, length, and acceptance criteria.
Using "prompt-engineering". Need an image prompt for a mountain lodge.
Expected outcome:
A detailed image prompt with subject, setting, lighting, composition, style, and quality terms.
Using "prompt-engineering". Need to analyze why shoppers abandon checkout.
Expected outcome:
A three-step prompt sequence that identifies causes, ranks fixes, and proposes validation tests.
Security Audit
CriticalThe skill is primarily a markdown guide, and most command findings are false positives from fenced examples rather than runnable shell-backtick code. The quick start includes a confirmed critical curl-to-shell installer pattern, and the remote image URL is a low-risk external content fetch. No prompt injection attempt or hidden data-exfiltration instruction was found in SKILL.md.
Confirmed security concerns (1)
Capability review items (2)
These are real local capabilities that may be expected for this skill, so they require review but are not counted as confirmed malicious behavior.
Risk Factors
⚙️ External commands (54)
🌐 Network access (4)
Detected Patterns
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/inference-sh-9-prompt-engineering/audits/4?utm_source=security_passport&utm_medium=share&utm_campaign=versioned_reportMarkdown badge
[](https://skillstore.io/skills/inference-sh-9-prompt-engineering?utm_source=security_passport_badge)HTML badge
<a href="https://skillstore.io/skills/inference-sh-9-prompt-engineering?utm_source=security_passport_badge"><img src="https://skillstore.io/badges/skills/inference-sh-9-prompt-engineering/security.svg" alt="Skillstore security assessment" loading="lazy"></a>Embed card
<iframe src="https://skillstore.io/embed/skills/inference-sh-9-prompt-engineering.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
inference-sh-9. (2026). prompt-engineering security audit report (audit version 4) [Author version unspecified]. Skillstore. https://skillstore.io/skills/inference-sh-9-prompt-engineering/audits/4BibTeX citation
@techreport{inference-sh-9-inference-sh-9-prompt-engineering-2026,
author = {inference-sh-9},
title = {prompt-engineering security audit report (audit version 4)},
institution = {Skillstore},
year = {2026},
number = {4},
url = {https://skillstore.io/skills/inference-sh-9-prompt-engineering/audits/4},
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 security audit report (audit version 4)"
version: "unspecified"
type: report
authors:
- name: "inference-sh-9"
date-released: "2026-07-05"
url: "https://skillstore.io/skills/inference-sh-9-prompt-engineering/audits/4"
identifiers:
- type: other
value: "skillstore:inference-sh-9-prompt-engineering:audit:4"
description: "Skillstore immutable audit report identifier"
Compare variants
4 installable variantsEach author remains a separate installable skill. The recommended variant is ranked by Skillstore evidence.
Why this variant is first
sickn33-prompt-engineering
2026-08-21
doyajin174-prompt-engineering
2026-08-21
inference-sh-9-prompt-engineering
2026-08-21
inference-sh-prompt-engineering
2026-08-21
Skillstore Score
Why this score Evidence Confidence: MediumWhat You Can Build
Create Reliable Work Prompts
Turn vague requests into structured prompts with roles, constraints, and expected formats.
Improve Code Review Requests
Ask AI tools to review code for bugs, security issues, performance, and style.
Draft Media Generation Prompts
Build prompts for image and video models with subject, style, composition, lighting, and motion details.
Try These Prompts
Rewrite this prompt using role, task, constraints, and output format: [draft prompt]. Keep it direct and testable.
Build three examples that teach the model how to complete this task: [task]. Include input, expected output, and one edge case.
Design a prompt that extracts [information type] from [source text]. Define the fields, allowed values, and validation rules in plain language.
Create a three-turn prompting workflow for [business problem]. First diagnose causes, then prioritize options, then propose validation tests.
Best Practices
- State the role, task, constraints, and expected format before examples.
- Use representative examples and include edge cases when accuracy matters.
- Review prompts for sensitive data before using external model providers.
Avoid
- Asking broad questions without success criteria or output format.
- Mixing conflicting style, length, or audience requirements.
- Using private code, customer data, or credentials in third-party prompts.
Frequently Asked Questions
What does this skill help me do?
Does it work with Claude, Codex, and Claude Code?
Does it require the inference.sh CLI?
Can it create prompts for images and video?
Will it guarantee the same output every time?
Should I include private data in prompts?
Developer Details
Author
inference-sh-9License
MIT
Skillstore revision
r1
Version notice
The author did not declare a version.
Ref
a25199bc7d6b82598536822d1738eb5d5f54025b
Maintenance freshness
7/18/2026
Usage
27 downloads · 164 views
File structure
📄 SKILL.md