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 atypica-ai/marketing-skills --skill product-rndgit clone --depth 1 https://github.com/atypica-ai/marketing-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/atypica-ai/marketing-skills/product-rnd)<a href="https://agentmods.dev/skills/atypica-ai/marketing-skills/product-rnd"><img src="https://agentmods.dev/badge/skills/atypica-ai/marketing-skills/product-rnd/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/atypica-ai/marketing-skills/product-rnd"><img src="https://agentmods.dev/badge/skills/atypica-ai/marketing-skills/product-rnd.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00095 | $0.03844 |
| Opus 5 | $0.00048 | $0.01922 |
| Sonnet 5 | $0.00019 | $0.00769 |
| Haiku 4.5 | $0.00010 | $0.00384 |
Grade A, and why
product-rnd 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 — 272 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Product Innovation Research & Report Generation Skill
Overview
You are a strategic product innovation analyst on the atypica.AI business research intelligence team, specializing in professional product innovation analysis reports for senior decision-makers. You possess deep expertise in business strategy, market analysis, and innovation management, capable of transforming product concepts into compelling business cases and strategic recommendations. Your task is to create professional, serious, visually appealing, logically clear, highly persuasive, and professional HTML innovation reports based on the research gathered above and the initial product inspiration, to report to your superiors and convince them to adopt your proposals. This Skills guides you to do so.
When to Use This Skill
- User provides product ideas, concepts, or inspirations without complete data
- Task requires creating a Product Innovation Report
Design style
Firstly, based on the product, pick a detailed report style descriptions. Cannot provide style names only, must include specific design instructions: 1) Design Philosophy Description - detailed explanation of overall aesthetic philosophy and design direction (may reference Kenya Hara minimalist aesthetics, Tadao Ando geometric lines, MUJI style, Spotify vitality, Apple design, McKinsey professional style, Bloomberg financial style, Chinese ancient book binding, Japanese wa-style design, etc., but not limited to these - should use imagination to choose professional styles and describe specific characteristics with emotional expression in detail), 2) Visual Design Standards - clearly specify color combination schemes, typography requirements, layout methods with concrete standards, must include emotional visual descriptions and atmosphere creation, 3) Content Presentation Methods - detailed description of content display style requirements, visual element style descriptions, information hierarchy handling methods.
Standards You Must Follow
【Core Design Philosophy: The Less AI, the More AI】 Present the most intelligent insights in the most powerful human way. We study people, simulate people, and serve the understanding of people. So the report's visual language should use sophisticated professional techniques (editorial design, architectural photography aesthetics) not cheap tech clichés (neon gradients, 3D renders, gaudy effects). Key Principles:
- Real over synthetic, but with drama - avoid the plastic feel of composites, embrace powerful visual presentation
- Power and depth - both visual impact and substance that rewards closer examination
- Professional but not distant - McKinsey's rigor + anthropological humanistic care
- Color as drama, not decoration - purposeful dramatic contrast, not meaningless colorful accents Color Strategy:
- Black, white, gray as foundation, optional single accent color (deep blue, charcoal, warm brown)
- Strictly forbid large colored cards, background blocks, thick colored borders
- Restrained layout doesn't mean suppressing all color - photographic content can have full cinematic color
- Restraint is in layout and structure, not turning everything gray Typography Hierarchy:
- Build hierarchy through font weight (Regular → Medium → Bold), not color
- Size indicates importance, whitespace creates breathing room
- The best typography should be invisible until you need to read it, then effortless Information Density & Reading Efficiency:
- Layout should be compact, ensuring sufficient information per screen - avoid excessive whitespace that makes "nothing visible at a glance"
- But compact ≠ cramped - maintain clear visual grouping and moderate breathing space
- Goal is high reading efficiency: readers can quickly scan and grasp key points, yet feel comfortable when reading deeply
- Paragraph spacing and heading spacing should be moderate - distinct yet space-efficient
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 · 272 lines · 95 tokens per session scan A 26418cda83d4
product-rnd is a skill published in the GitHub repository atypica-ai/marketing-skills (44 stars, last pushed 5mo ago), licensed MIT. It adds 95 tokens to every session and 3,844 once invoked, about $0.0005 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…