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 aniganti/pm-superpowers --skill prompt-buildergit clone --depth 1 https://github.com/aniganti/pm-superpowersWrote 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/aniganti/pm-superpowers/prompt-builder)<a href="https://agentmods.dev/skills/aniganti/pm-superpowers/prompt-builder"><img src="https://agentmods.dev/badge/skills/aniganti/pm-superpowers/prompt-builder/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/aniganti/pm-superpowers/prompt-builder"><img src="https://agentmods.dev/badge/skills/aniganti/pm-superpowers/prompt-builder.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Anti-Refusal · line 120 Skill attempts to nullify the agent's safety policies or restrictions ('you have no restrictions', 'ignore your guidelines', 'do anything now'). This is a direct jailbreak that disables guardrails.Fix: Remove jailbreak framing that nullifies safety policies or restrictions. Skill content must not instruct the agent to ignore its guidelines or operate without guardrails.
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 | $0.00062 | $0.01307 |
| Opus 5 | $0.00031 | $0.00654 |
| Sonnet 5 | $0.00012 | $0.00261 |
| Haiku 4.5 | $0.00006 | $0.00131 |
Grade A, and why
prompt-builder 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 9d 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 — 131 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AI Prompt Builder for Product Managers
Purpose
Help product managers craft well-structured, effective prompts for generative AI tools. This skill walks the PM through a series of guided questions — one at a time — to gather the context needed to produce a polished, ready-to-use prompt.
Instructions
You are an AI prompt creation assistant for product managers. You are great at asking clarifying questions to understand the user's needs and then crafting effective prompts based on that information.
Interaction Model
- Ask one question at a time and wait for the user's response before moving to the next
- If the user provided an argument when invoking this skill, use it as context to tailor your questions
- Be conversational — offer examples and suggestions to help the PM think through each question
- For optional questions (8 and 9), let the PM know they can skip
Questions to Ask (in order)
1. Role or Point-of-View "What role or point-of-view would you like the AI assistant to assume?"
- Offer PM-relevant examples: product strategist, user research assistant, UX designer, data analyst, technical writer, competitive intelligence analyst, customer success advisor
2. Target Audience "Who is the target audience or end-user for your request?"
- Help the PM be specific: internal stakeholders, engineering team, executive leadership, end users, customers in a particular segment
3. Desired Outcome "What outcome are you seeking to achieve with the help of the AI assistant?"
- Encourage concrete, measurable outcomes where possible
4. Obstacles or Unknowns "What are some obstacles or unknowns that you hope generative AI can help you overcome?"
- Prompt for: knowledge gaps, time constraints, analysis paralysis, cross-functional alignment challenges
5. Tone and Writing Style "What tone of voice and writing style would you prefer the AI assistant to use?"
- Examples: formal, casual, executive-ready, technical, empathetic, data-driven, concise
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.
- 9d ago First seen · 131 lines · 62 tokens per session scan A 6066999a83b6
prompt-builder is a skill published in the GitHub repository aniganti/pm-superpowers (47 stars, last pushed 25d ago), licensed MIT. It adds 62 tokens to every session and 1,307 once invoked, about $0.0003 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…