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 Mintii-Labs/ozor-skills --skill ozor-document-videogit clone --depth 1 https://github.com/Mintii-Labs/ozor-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/mintii-labs/ozor-skills/ozor-document-video)<a href="https://agentmods.dev/skills/mintii-labs/ozor-skills/ozor-document-video"><img src="https://agentmods.dev/badge/skills/mintii-labs/ozor-skills/ozor-document-video/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/mintii-labs/ozor-skills/ozor-document-video"><img src="https://agentmods.dev/badge/skills/mintii-labs/ozor-skills/ozor-document-video.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 | $0.00204 | $0.02226 |
| Opus 5 | $0.00102 | $0.01113 |
| Sonnet 5 | $0.00041 | $0.00445 |
| Haiku 4.5 | $0.00020 | $0.00223 |
Grade A, and why
ozor-document-video scanned grade A with 1 finding 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 11d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- `mcp__ozor__prepare_document_upload` — gets a curl-uploadable URL for local files with no public URL (the common path) How it starts
The opening of the file, as written. The whole thing — 179 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Ozor Document-to-Video
End-to-end document-to-video on Ozor.ai. Takes a real file (PDF, PPTX, DOCX, etc.), analyzes it on Ozor's side to produce a structured plan, lets the user approve/edit the plan, then generates and exports a finished video — preserving slide visuals along the way.
When to use
Use this skill when the input is a document/file. Signals:
- User attached or referenced a PDF, PPTX, DOCX, Keynote export, slide deck, proposal, whitepaper, report, one-pager
- "Turn this deck into a video"
- "Make a video from this PDF"
- "Video from my pitch / proposal / report"
Do NOT use this skill when:
- Input is a short creative text brief →
ozor-generate - Input is a URL or landing page →
ozor-url-to-video - User only wants a written Ozor prompt →
ozor-doc-to-video(prompt-only skill) - User wants to manage existing videos →
ozor-video-library
Required MCP tools
mcp__ozor__analyze_document— analyzes the doc, returns aplanIdplus the structured planmcp__ozor__prepare_document_upload— gets a curl-uploadable URL for local files with no public URL (the common path)mcp__ozor__get_plan— fetches the latest plan statemcp__ozor__update_plan— applies user edits to the plan before generationmcp__ozor__generate_from_plan— kicks off the video build from the approved plan, returnsprojectIdmcp__ozor__export_video— starts the render (use theprojectIdasvideoId)mcp__ozor__wait_for_export— blocks until the render is readymcp__ozor__get_embed_code— returns the<iframe>HTML
If the Ozor MCP isn't connected, tell the user and stop. Do not extract content yourself and fall back to generate_video with a hand-written script — that loses the slide visuals and overflows the 2000-char prompt limit. The plan-based flow is mandatory for documents.
Workflow
Step 1 — Get the document to Ozor
Pick the best source, in priority order:
- Public URL → pass
urldirectly toanalyze_document. No size limit, no token cost. Best whenever available. - Local file (the common case) → call
mcp__ozor__prepare_document_upload, then run the returned curl command to push the bytes directly to Ozor's storage. Bytes never traverse a tool call, so files up to ~50 MB work. Use this for any multi-MB PDF/PPTX/DOCX the user has uploaded into the conversation. fileBase64+fileNameonanalyze_document→ only for small files (≲ a few hundred KB). Avoid for big decks — it burns tokens.
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.
- 11d ago First seen · 179 lines · 204 tokens per session scan A 9a8c42fe237f
ozor-document-video is a skill published in the GitHub repository Mintii-Labs/ozor-skills (6 stars, last pushed 3mo ago), licensed MIT. It adds 204 tokens to every session and 2,226 once invoked, about $0.0010 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
ozor-doc-to-video
Convert any document into a production-ready Ozor.ai video prompt. Use this skill whenever the user uploads a document (PDF, PowerPoint, Google Doc, Markdown, text file, or URL) and wants to turn it into a video. Also trigger when the user mentions 'turn this doc into a video', 'make a video from this PDF', 'video…
ozor-landing-page-to-video
Convert any landing page or website into an Ozor.ai video prompt. Use this skill whenever the user provides a URL, landing page content, or website copy and wants to turn it into a video. Trigger on phrases like 'make a video from my website', 'video from this landing page', 'turn my homepage into a video', 'video…
ozor-prompt-optimizer
Analyze and improve existing Ozor.ai video prompts for better output quality. Use this skill whenever the user has an Ozor prompt that produced mediocre results, wants to improve a video prompt, needs help debugging why a video didn't turn out well, or wants expert feedback on their prompt before running it. Trigger…
ozor-video-best-practices
Expert guide for crafting high-quality video prompts for Ozor.ai, the AI video generation platform. Use this skill whenever the user mentions Ozor, wants to create a launch video, product demo, feature announcement, explainer video, social ad, release notes video, investor update, tutorial, or any marketing video.…
ozor-changelog-to-video
Convert changelogs, release notes, and version updates into Ozor.ai video prompts. Use this skill whenever the user has a CHANGELOG.md, release notes, GitHub release, version bump summary, or any list of product changes and wants to turn them into a video. Trigger on phrases like 'video from my changelog', 'release…
ozor-social-batch
Generate a batch of social media video prompts for multiple platforms from a single input. Use this skill whenever the user wants to create videos for multiple social platforms at once, repurpose one video across platforms, or create a social media video campaign. Trigger on phrases like 'social media videos', 'videos…