Marketing PromptsAIMarketing

Prompt Engineer Toolkit

Improve prompts for AI-assisted marketing and content workflows.

$skillfish add ~skills/prompt-engineer-toolkit

Real Examples Get Started Models & Context

Real Conversations

See how the Prompt Engineer Toolkit skill responds to actual requests. These are representative examples of what your AI agent will produce.

You

Our content team uses AI to write blog posts but the output is generic and always needs heavy editing. The prompt is just 'Write a 1000-word blog post about [topic] for B2B SaaS marketers.' How do we improve this?

Agent

Prompt Engineering: Content Brief Upgrade

What's wrong with the current prompt:

No persona (who is writing this?)
No audience specificity ("B2B SaaS marketers" is 2 million people)
No angle or POV (generic = generic output)
No constraints (word count is the only instruction)
No examples or tone reference

Upgraded prompt template:

You are a senior content writer at [Company Name], a [product description] for [specific ICP].

Write a blog post with the following specs:

Topic: [topic]
Angle: [specific POV or contrarian take — not just what, but why it matters]
Target reader: [specific title] at a [company size] [industry] company who is currently [specific situation/pain point]
Tone: [3 adjectives] — write like [comparable publication/author style]
Word count: [X] words
Structure: [H2 headers, bullet points preferred / narrative paragraphs / etc.]

Must include:
- A specific example or case study (can be hypothetical but realistic)
- One stat or data point (cite a real source or label it as industry estimate)
- A clear takeaway the reader can act on this week

Do not:
- Use phrases like "In today's fast-paced world" or "It's no secret that"
- Write a generic introduction — open with a specific scenario or provocative statement
- Use passive voice

Here is a reference post with the tone we're aiming for: [paste 200-word excerpt]

Expected improvement: Prompts with persona + specific reader + angle + negative constraints reduce editing time by 50–70% in most content workflows. The reference excerpt is the single highest-impact addition — it gives the model a concrete tonal target.

You

We're a 6-person marketing team. Everyone is using AI differently and getting inconsistent results. I want to build a shared prompt library. What prompts should we standardize first and how do we structure it?

Agent

Marketing Team Prompt Library: Structure and Priority Prompts

Library structure (Notion or Google Doc):

Marketing Prompt Library
├── 00_CONTEXT_BLOCK.md  ← paste at top of every session
├── Content/
│   ├── blog-post.md
│   ├── linkedin-post.md
│   └── email-newsletter.md
├── Paid Ads/
│   ├── ad-copy-variants.md
│   └── campaign-brief.md
├── Research/
│   ├── competitor-analysis.md
│   └── customer-interview-synthesis.md
└── Ops/
    ├── meeting-summary.md
    └── campaign-brief.md

Priority prompts to build first (highest ROI):

1. Ad copy variants prompt

"Write 3 variants of [ad type] for [platform] targeting [specific persona]. Variant A: pain-led. Variant B: outcome-led. Variant C: social proof-led. Each must have: headline (≤30 chars for Google / ≤150 for LinkedIn), body copy, and CTA. Product context: [paste context block]"

2. LinkedIn post prompt

"Write a LinkedIn post from the perspective of [founder/PMM/specific person]. Topic: [topic]. Format: hook (1 sentence, no question, no 'I'), 4–6 short paragraphs, 1 line CTA. Do not use hashtags. Reference this voice sample: [paste 1 existing post]"

3. Customer interview synthesis

"Here are notes from [N] customer interviews. Extract: top 3 pain points (with exact quotes), top 3 value drivers, and any language patterns that should inform our messaging. Format as a table with quotes."

Governance: Designate one owner per prompt category. Version prompts with dates. Run a 30-min monthly prompt review to update based on what's working.

Expected outcome: Consistent output quality across all 6 team members, 40–60% less time spent on prompt iteration per task.

Get Started

How to install and use this skill in your preferred environment.

Skills are designed for AI coding agents (Claude Code, Cursor, Windsurf) and IDE-based workflows where the agent can read files, run scripts, and act on your codebase. Web-based AI can use the knowledge and frameworks, but won't have tool access.

Models & Context

Which AI models and context windows work best with this skill.

Recommended Models

Best

Claude Opus 4 Claude Sonnet 4 GPT-4.1 Gemini 2.5 Pro Grok 3 Kimi K2

Good

Claude Haiku 4.5 GPT-4.1 mini Gemini 2.5 Flash Grok 3 mini

Larger models produce more detailed, production-ready outputs.

Context Window

This skill's SKILL.md is typically 3–10 KB — fits in any modern context window.

8K Skill only

32K+ Skill + conversation

100K+ Skill + references + codebase

All current frontier models (Claude, GPT, Gemini) support 100K+ context. Use the full window for complex multi-service work.

Pro tips for best results

1

Be specific

Include numbers — users, budget, RPS — so the skill can size the architecture.

2

Share constraints

Compliance needs, team size, and existing stack all improve the output.

3

Iterate

Start with a high-level design, then ask follow-ups for IaC, cost analysis, or security review.

4

Combine skills

Pair with companion skills below for end-to-end coverage.

Ready to try Prompt Engineer Toolkit?

Install the skill and start getting expert-level guidance in your workflow — any agent, any IDE.

$skillfish add ~skills/prompt-engineer-toolkit

← Browse all 169 skills