What is prepare-video-publish?

A video-publishing preparation workflow reads a local video or subtitle file and creates draft publishing text plus complete cover-image options in several aspect ratios, such as widescreen and vertical.

Use it to transcribe or summarize a video, draft its title and description, and create covers for different publishing platforms and screen shapes.

It prepares the materials needed for publishing while keeping review and approval in the current task.

prepare-video-publish — Skill for Codex by sunshineLixun

Install

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.

Any agent

npx skills add sunshineLixun/video-publish-skill --skill prepare-video-publish

Clone the repo

git clone --depth 1 https://github.com/sunshineLixun/video-publish-skill

Made for: Codex.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/sunshinelixun/video-publish-skill/prepare-video-publish/github.svg)](https://agentmods.dev/skills/sunshinelixun/video-publish-skill/prepare-video-publish)

Your own site

<a href="https://agentmods.dev/skills/sunshinelixun/video-publish-skill/prepare-video-publish"><img src="https://agentmods.dev/badge/skills/sunshinelixun/video-publish-skill/prepare-video-publish/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/sunshinelixun/video-publish-skill/prepare-video-publish"><img src="https://agentmods.dev/badge/skills/sunshinelixun/video-publish-skill/prepare-video-publish.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 118 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,836 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits

NVIDIA SkillSpector warn 7 Sept 2026

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 Data Exfiltration · line 148
Code or instructions that leak agent conversation context to external services, potentially exposing sensitive user interactions.

Fix: Remove any code that sends prompts, responses, or session data externally. Preserve user privacy; never exfiltrate conversation content.

How audits are shown

Origin original No closer match found in the catalogue.

Token cost

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	$0.00118	$0.01836
Opus 5	$0.00059	$0.00918
Sonnet 5	$0.00024	$0.00367
Haiku 4.5	$0.00012	$0.00184

Measured 12d ago against content hash f5285b68ec3a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

prepare-video-publish 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.

The scan reads SKILL.md. This mod also ships 24 executable files (scripts/ego-publisher/scripts/check-package.mjs, scripts/ego-publisher/scripts/config.mjs, scripts/ego-publisher/scripts/find-video.mjs, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

skills/prepare-video-publish/SKILL.md · 185 lines

How it starts

The opening of the file, as written. The whole thing — 185 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Prepare Video Publish

Complete the entire workflow in the current Codex task. Never start a review website, local HTTP server, background Agent, app-server, or separate Codex task.

Initial Workflow

Resolve the attached video and/or subtitle to absolute local paths.
Run scripts/video-publish.mjs prepare and retain the returned sessionPath in this task.
Read the complete transcript.
Read content-contract.md, write content.json beside the session, and run finalize until validation passes.
Add any user-supplied style or person images with references add.
Read cover-workflow.md, update the cover spec when references or user instructions require it, and generate four complete covers with Codex built-in ImageGen.
Register the generated files with covers add.
Present the publishing draft and all four local cover images directly in this task, then stop and wait for user feedback or explicit publishing confirmation.

Do not open publishing pages during the initial workflow.

Prepare Input

Replace $SKILL_DIR with the absolute directory containing this SKILL.md.

Video or subtitle:

node "$SKILL_DIR/scripts/video-publish.mjs" prepare --input "/path/input"

Video with a preferred subtitle:

node "$SKILL_DIR/scripts/video-publish.mjs" prepare \
  --input "/path/video.mp4" \
  --subtitle "/path/subtitle.srt"

Subtitle with a separately supplied video:

node "$SKILL_DIR/scripts/video-publish.mjs" prepare \
  --input "/path/subtitle.srt" \
  --video "/path/video.mp4"

The command returns sessionPath and transcriptPath as JSON.

Finalize Content

Ground every factual claim in the complete transcript. Never infer visual details from video frames.

node "$SKILL_DIR/scripts/video-publish.mjs" finalize \
  --session "/path/session.json" \
  --content "/path/content.json"

Conversation Checkpoint

After registering covers, respond in the current task with:

Read the full file on GitHub · 185 lines

Files

What ships with it

30 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.

Changes

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 · 185 lines · 118 tokens per session scan A f5285b68ec3a

Subscribe to this mod's changes

prepare-video-publish is a skill published in the GitHub repository sunshineLixun/video-publish-skill (22 stars, last pushed 8d ago), licensed Apache-2.0. It adds 118 tokens to every session and 1,836 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.

Creative and media agent-skill automation codex local-first video-publishing

algorithmic-art

Creating algorithmic art using p5.js with seeded randomness and interactive parameter exploration. Use this when users request creating art using code, generative art, algorithmic art, flow fields, or particle systems. Create original algorithmic art rather than copying existing artists' work to avoid copyright…

PM-Shawn/Abu-Cowork · 62 tokens

canvas-design

Create beautiful visual art in .png and .pdf documents using design philosophy. You should use this skill when the user asks to create a poster, piece of art, design, or other static piece. Create original visual designs, never copying existing artists' work to avoid copyright violations.

PM-Shawn/Abu-Cowork · 59 tokens

prepare-video-publish