Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add matteotitta/genesys-skills --skill prompt-designgit clone --depth 1 https://github.com/matteotitta/genesys-skillsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/matteotitta/genesys-skills/prompt-design)<a href="https://agentmods.dev/skills/matteotitta/genesys-skills/prompt-design"><img src="https://agentmods.dev/badge/skills/matteotitta/genesys-skills/prompt-design/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/matteotitta/genesys-skills/prompt-design"><img src="https://agentmods.dev/badge/skills/matteotitta/genesys-skills/prompt-design.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00113 | $0.01335 |
| Opus 5 | $0.00056 | $0.00668 |
| Sonnet 5 | $0.00023 | $0.00267 |
| Haiku 4.5 | $0.00011 | $0.00134 |
Grade A, and why
prompt-design scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 178 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Prompt Design
Generate reusable prompts using the 7-section architecture for B2B SaaS marketing deliverables.
For full process flowchart and step-by-step → the premium reference.
Claude Code Triggers
Invoke this skill when user says:
- "Create a prompt for [deliverable]"
- "Build a prompt template"
- "Generate a prompt for [task]"
- "Prompt template for [use case]"
- "Make me a prompt"
- "Write a prompt for [deliverable]"
Do NOT invoke when:
- User wants a workflow → Use
workflow-designskill - User wants to execute a prompt → Just run it directly
- User wants a specific skill output → Use the relevant skill
Input Requirements
Required
| Input | Description | Source |
|---|---|---|
| Deliverable type | What output the prompt should produce | User specifies |
Optional (improve quality)
| Input | How it helps |
|---|---|
| Target audience | Tailors prompt language |
| Quality criteria | Defines success metrics |
| Existing prompts | Builds on proven patterns |
| Tool context | Adapts for specific AI (Claude, GPT, etc.) |
If deliverable type is missing, ask the user before generating.
Core Framework: 7-Section Prompt Architecture
Every prompt follows this structure:
| Section | Purpose | Content |
|---|---|---|
| ROLE | Sets expertise and context | "You are a [expert type] with [experience]..." |
| GOAL | System-level objective | "Your goal is to [outcome]..." |
| INPUTS | All {{variables}} user provides |
List each variable with description |
| TASK | Step-by-step instructions | Numbered steps with clear actions |
| OUTPUT FORMAT | Structure, length, constraints | Format specification, character limits |
| CONTEXT | Reminder to pull from memory/knowledge | "Use any brand context, previous research..." |
| EXAMPLE | Placeholder for user's example | "Reference this example: {{example}}" |
Prompt template
## ROLE
You are a [EXPERT TYPE] with deep expertise in [DOMAIN]. You have [SPECIFIC EXPERIENCE].
## GOAL
Your goal is to [PRIMARY OBJECTIVE] that [QUALITY CRITERIA].
## INPUTS
The user will provide:
- `{{variable_1}}`: [Description]
- `{{variable_2}}`: [Description]
## TASK
Follow these steps:
1. [First action with specific instruction]
2. [Second action with specific instruction]
3. [Third action with specific instruction]
## OUTPUT FORMAT
Deliver the output as:
- Format: [Markdown/JSON/etc.]
- Length: [Specification]
- Structure: [Description]
Include:
- [Required element 1]
- [Required element 2]
## CONTEXT
Pull from any available context:
- Brand guidelines and voice
- Previous research or deliverables
- Known audience information
## EXAMPLE
Reference this example for quality: {{example}}
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 12d ago First seen · 178 lines · 113 tokens per session scan A 7d50e650cbc3
prompt-design is a skill published in the GitHub repository matteotitta/genesys-skills (36 stars, last pushed 1mo ago), licensed MIT. It adds 113 tokens to every session and 1,335 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
llm-app-patterns
Production-ready patterns for building LLM applications. Covers RAG pipelines, agent architectures, prompt IDEs, and LLMOps monitoring. Use when designing AI applications, implementing RAG, building agents, or setting up LLM observability.
prompt-optimization
Improve a prompt on the evaluations workbench through a measured loop. Score the baseline first, then duplicate the target column, form a hypothesis from failing rows, edit the copy's prompt draft, run, compare pass rate and cost, and repeat until the numbers hold. Use when the user asks to optimize or improve a…
enhance-prompt
Transforms vague UI ideas into polished, Stitch-optimized prompts. Enhances specificity, adds UI/UX keywords, injects design system context, and structures output for better generation results.
prompt-engineer
Writes, refactors, and evaluates prompts for LLMs — generating optimized prompt templates, structured output schemas, evaluation rubrics, and test suites. Use when designing prompts for new LLM applications, refactoring existing prompts for better accuracy or token efficiency, implementing chain-of-thought or few-shot…
seedance-vocab-en
This skill should be used when an English Seedance 2.0 prompt needs clearer production wording, less generic prose, or precise vocabulary for camera, lighting, motion, VFX, audio, and constraints. Route blocked prompts through seedance-filter for context and boundary review.
ideogram4
Prompting patterns for Ideogram 4 text-to-image — best-in-class in-image text rendering and exact color/layout control via structured JSON captions. Use when generating images that need legible on-image text (title cards, thumbnails, logos, signage, CTAs), precise brand colors, or controlled spatial layout. Triggers…