agentmods.dev

creator-flow: Skill for Claude Code

.agents/skills/zimeiti-video-workflow/SKILL.md

zimeiti-video-workflow is a skill for Claude Code, Codex from Damonhhh/creator-flow. It costs 35 tokens per session (1,869 once invoked), scanned A, original, MIT.

A project-level workflow guide for making videos, from choosing a topic and writing a script to creating audio, subtitles, visuals, assembly, quality checks, and publishing materials. It routes each task to the relevant production stage and tool.

In plain words
What is it for?
Use it to plan, script, narrate, subtitle, assemble, check, publish, and wrap up video projects, including deciding which editing tool to use.
Why use it?
It helps keep video work in the correct order and identifies which project instructions and references are needed at each stage. It also guides the choice between HyperFrames and another compatible video editor.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: installed under .agents/ (shared by several agents); mentions AGENTS.md.

This is Damonhhh/creator-flow's own configuration. It tells Claude Code and Codex how to work on creator-flow itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything creator-flow configures →

not rated 272repo +1 2mo ago A scan SkillSpector: warn 35 tokens original MIT
View source ↗ Damonhhh/creator-flow
Reuse

Borrowing it

Nothing to install: this file belongs to Damonhhh/creator-flow. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/Damonhhh/creator-flow/main/.agents/skills/zimeiti-video-workflow/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/Damonhhh/creator-flow

Made for: Claude Code, 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.

agentmods badge for zimeiti-video-workflow

README.md
[![agentmods](https://agentmods.dev/badge/skills/damonhhh/creator-flow/zimeiti-video-workflow/github.svg)](https://agentmods.dev/skills/damonhhh/creator-flow/zimeiti-video-workflow)
Your own site
<a href="https://agentmods.dev/skills/damonhhh/creator-flow/zimeiti-video-workflow"><img src="https://agentmods.dev/badge/skills/damonhhh/creator-flow/zimeiti-video-workflow/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.

agentmods 80×15 button for zimeiti-video-workflow

Your own site · 80×15
<a href="https://agentmods.dev/skills/damonhhh/creator-flow/zimeiti-video-workflow"><img src="https://agentmods.dev/badge/skills/damonhhh/creator-flow/zimeiti-video-workflow.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 35 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,869 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: 2 findings, up to medium

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 →

  • medium Excessive Agency · line 73
    Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.
    Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
  • medium Excessive Agency · line 79
    Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.
    Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00035 $0.01869
Opus 5.5 $0.00014 $0.00748
Sonnet 5.5 $0.00007 $0.00374
Haiku 4.5 $0.00003 $0.00187

Measured 2mo ago against content hash 2c1424e5b111, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

zimeiti-video-workflow 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 2mo 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.

.agents/skills/zimeiti-video-workflow/SKILL.md · 156 lines

How it starts

The opening of the file, as written. The whole thing — 156 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CreatorFlow Video Workflow

Purpose

This is CreatorFlow's project-level router. Use it whenever the task involves topic planning, scripting, TTS/subtitles, materials, assembly, QA, publishing packages, wrap-up, or choosing between HyperFrames and another compatible renderer.

This skill decides the production stage and the smallest reference slice needed for that stage. references\pipeline.md is the execution map.

Read Order

Before real video work, read:

  1. AGENTS.md when the host project provides one.
  2. docs\video-workflow-current-state.md when changing the workflow itself.
  3. references\pipeline.md.
  4. docs\failure-pattern-index.md; open only matching sections from docs\failure-patterns.md.
  5. The matching references\stage-*.md file.

For external editing tools, also read:

  1. docs\video-editing-skill-integration.md

For scripts, titles, captions, covers, publishing copy, or other reader-facing text, also read:

  1. The active project's writing-style.md and account-profile.md.
  2. A final human-readable editing pass that removes formulaic AI phrasing without changing facts or locked wording.

Stage Router

When a video project already exists, read project-state.json first when present. It is the machine-readable current-stage authority; status.md is supporting context. Then choose the smallest current stage and read that reference file completely before acting.

Stage Use When Reference
Topic choosing, scoring, reframing, or rejecting a topic references\stage-topic.md
Script TTS writing spoken narration, public copy, TTS, SRT, or orientation decision references\stage-script-tts.md
Material sourcing proof/texture/explain assets, beat maps, motion jobs, tool handoffs references\stage-material.md
Assembly HyperFrames composition, captions, timeline, animation, render candidate references\stage-assembly.md
QA draft QA, frame inspection, subtitle/evidence/readability checks references\stage-qa.md
Publish Wrap Up covers, publish copy, final package, sync, 收尾, 可以发, 准备发布 references\stage-publish-wrap-up.md

Read the full file on GitHub · 156 lines

Files

What ships with it

11 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.

  1. 2mo ago First seen · 156 lines · 35 tokens per session scan A 2c1424e5b111

Subscribe to this mod's changes

zimeiti-video-workflow is a skill published in the GitHub repository Damonhhh/creator-flow (272 stars, last pushed 2mo ago), licensed MIT. It adds 35 tokens to every session and 1,869 once invoked, about $0.0001 per session on Opus 5.5. 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
Related

zimeiti-video-workflow compared with skills from other repositories

zimeiti-video-workflow next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
zimeiti-video-workflowDamonhhh/creator-flowSkill2722mo agoMITA35Claude Code, Codex
imagegenopenai/codexSkill134ktodayApache-2.0A113Codex
playwright-climicrosoft/playwrightSkill99ktodayApache-2.0A19Claude Code
local-ai-agentsmicrosoft/ai-agents-for-beginnersSkill79ktodayMITA200Claude Code, Codex
systematic-debuggingobra/superpowersSkill314k3d agoMITA21Claude Code
next-cache-components-adoptionvercel/next.jsSkill143kyesterdayMITA95Claude Code
next-partial-prefetching-adoptionvercel/next.jsSkill143kyesterdayMITA103Claude Code