Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add Kaminoikari/product-playbook/plugin install product-playbookWrote 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/kaminoikari/product-playbook/document-export)<a href="https://agentmods.dev/skills/kaminoikari/product-playbook/document-export"><img src="https://agentmods.dev/badge/skills/kaminoikari/product-playbook/document-export/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/kaminoikari/product-playbook/document-export"><img src="https://agentmods.dev/badge/skills/kaminoikari/product-playbook/document-export.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 | $0.00065 | $0.04543 |
| Opus 5 | $0.00032 | $0.02271 |
| Sonnet 5 | $0.00013 | $0.00909 |
| Haiku 4.5 | $0.00006 | $0.00454 |
Grade A, and why
document-export 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 — 491 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Document Export
Detect the user's language and reply in it; the framework below is authored in English.
Provenance: when you produce an HTML report or a PDF/DOCX/PPTX export, contribute the framework tags HTML Report and PDF Export to the meta-skill's provenance line (— Frameworks: … · HTML Report · PDF Export · …).
Framework
HTML Product Planning Report Output
Triggered when the user says "produce a report" or confirms the last stage content is correct.
Design Specifications
Use a modern design style: a single HTML file (CSS and JS fully inlined), ensuring it's readable offline.
Overall Style:
- Gradient background Hero section (with mode, audience, date labels)
- Card-based layout (rounded corners + shadows), each section like an independent information card
- Clear typography hierarchy and comfortable reading spacing
- Responsive design, smooth reading on mobile
Color Scheme:
- Primary: Deep blue
#1a1a2e→#16213e→#0f3460 - Accent:
#e94560or#533483 - Content area background:
#f8f9fa, cards: white withbox-shadow
Font: Load Inter from Google Fonts CDN first, fall back to system fonts:
/* In <head> */
<link href="https://fonts.googleapis.com/css2?family=Inter:wght@400;500;700&display=swap" rel="stylesheet">
/* In CSS */
font-family: "Inter", system-ui, -apple-system, "Segoe UI", Roboto, sans-serif;
This is the only permitted external CDN dependency. If Google Fonts is unavailable, the page will still render correctly.
Page Structure (Dynamically rendered based on completed stages)
┌──────────────────────────────────────────────────────────────┐
│ Hero Section (Product name, one-liner, mode, audience, date)│
├──────────────────────────────────────────────────────────────┤
│ Table of Contents Navigation (Sticky, only shows completed) │
├──────────────────────────────────────────────────────────────┤
│ 🧭 Strategy Section (if completed) │
│ ├─ Strategy Blocks hierarchy diagram │
│ ├─ Rumelt's Kernel of Good Strategy (Diagnosis/Policy/ │
│ │ Actions) │
│ └─ Shreyas' Three Levels of Product Work │
│ ✅ Opportunity Check Section (if completed) │
│ 🔍 Discovery Section (if completed) │
│ ├─ Persona Table (card-style table) │
│ ├─ Persona Cards (one per persona) │
│ ├─ JTBD Analysis Table (four types) │
│ ├─ Opportunity Solution Tree (visual tree) │
│ └─ User Journey Map (overview + accordion detail) │
│ 🎯 Define Section (if completed) │
│ ├─ Pain Point Summary Table │
│ ├─ April Dunford Positioning Framework Card │
│ ├─ HMW Question Cards (with JTBD type tags) │
│ └─ Opportunity Assessment Table (opportunity cost view) │
│ 💡 Develop Section (if completed) │
│ ├─ PR-FAQ Card (simulated press release format) │
│ ├─ Solution Ideation (three-column parallel cards) │
│ ├─ Pre-mortem Risk Table (color-coded High/Med risk) │
│ ├─ GEM Matrix + Impact/Effort Quadrant Chart │
│ ├─ RICE Prioritization Table (if completed) │
│ ├─ User Story Table (if completed) │
│ └─ MVP Scope (three-column cards + Not Doing List) │
│ 🚀 Deliver Section (if completed) │
│ ├─ Aha Moment Definition Card (prominently displayed) │
│ ├─ North Star Metric Card │
│ ├─ Three-Layer Signal Metrics Table │
│ ├─ PMF Level Assessment (four-level visual + current │
│ │ position marker) │
│ ├─ GTM Strategy (channel selection + first 100 users │
│ │ plan, if completed) │
│ ├─ Business Model & Pricing (revenue model + pricing │
│ │ strategy, if completed) │
│ ├─ Hypothesis Validation Plan Table (if completed) │
│ └─ Product Spec Summary (three-section structure: │
│ Decision Summary / Execution Boundaries / Deep Ref) │
│ ⭐ Best Entry Point Analysis (full logic chain visual) │
├──────────────────────────────────────────────────────────────┤
│ Footer: Output date + mode + framework attribution │
└──────────────────────────────────────────────────────────────┘
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 491 lines · 65 tokens per session scan A d324eb7f0cdf
document-export is a skill published in the GitHub repository Kaminoikari/product-playbook (24 stars, last pushed 1mo ago), licensed MIT. It adds 65 tokens to every session and 4,543 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
utility-slideshow-creator
Generates professional presentations from a JSON deck specification using 18 slide types with dark/light variants, content-to-layout decision logic, and calibrated character limits. Ships with a default professional theme.
scan-to-practice
A complete methodology for turning scanned or image-based learning materials into high-quality desktop, web, or mobile practice products. Covers visual transcription, data assembly, answer-key-driven controls and grading, product design, animation, validation, and long-term maintenance. Use when a user wants to…
paper-fetch
Use whenever the user wants to obtain, download, or fetch a paper's PDF — given a DOI, an arXiv id, a paper title, a citation, or a list of DOIs. Trigger on phrases like "download this paper", "find the PDF for [DOI]", "grab me the [Nature/bioRxiv/arXiv] paper on X", "get the open-access version", "I need this…
mineru
An AI-Native skill for parsing PDF / Office / image files into clean Markdown with MinerU — a fast, zero-config document parser for AI agents. Works with NO token via the lightweight Agent API and auto-upgrades to the Standard API (token) for large files, batches, and DOCX/HTML/LaTeX export. Use when: (1) Converting…
pro-report-builder
Create polished HTML technical reports and multi-page documents for consulting deliverables. Includes a customizable design system with dark cover page, warm cream content pages (8.5x11 portrait), professional typography, and a curated component library (KPI cards, data tables with severity coloring, callout boxes…
html-report-builder
Create polished HTML technical reports and multi-page documents for consulting deliverables. Features a professional design system with dark cover pages, warm cream content pages, Switzer + Cartograph CF typography, and a curated component library (KPI cards, data tables, callout boxes, recommendation cards, priority…