Agent skill · Data & Analytics

minimax-hailuo-video

Use MiniMax's first-party Hailuo video API safely and reproducibly across global and mainland-China platforms. Covers current text-to-video, image-to-video, first/last-frame, and subject-reference models; prompt and camera craft; region/account routing; exact cost approval; asynchronous jobs and callbacks; artifact provenance; and rights, likeness, disclosure, and data-governance review. Use when designing, implementing, debugging, or evaluating direct MiniMax/Hailuo video-generation API workflows. Do not use for the consumer Hailuo site, Video Agent templates, gateways, or unrelated MiniMax m

Calesthio43,316★ · +2,384/wk · 2 repos on radarProfile →
claude-codecodexcopilotcursorMIT
Install
npx skills add calesthio/generative-media-skills --skill minimax-hailuo-video --agent claude-code

Same command for any agent — swap --agent for codex, cursor, copilot.

Facts
Files in the skill folder: 2
SKILL.md size: 50 KB
Bundled scripts: none
Path: skills/providers/video-generation/minimax-hailuo-video/SKILL.md
Open the folder on GitHub →
Where it comes from
Stars: 112 · +8 this week
Language: Python
Read our review of the source →

Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.

Review
written from the skill's own SKILL.md · Aug 5, 2026

What it does

Build a reviewed request, obtain exact cost approval, create at most one paid task, then preserve the result and its evidence. Treat documentation gaps as unknowns, not defaults.

How it works

  • Start with a boundary by selecting one service region and keeping account details, key, billing, host, and terms together for Global or Mainland China.
  • Route by mode using POST /v1/video_generation for four modes (Text-to-video, Image-to-video, First/last frame, Subject reference) with specified required media and models.
  • Build a request dossier before calling create, recording region, account identifiers, key type, model, mode, resolution, duration, currency, unit price, pricing-page retrieval time, exact prompt and parameters, source file metadata, audience, jurisdiction, disclosure plan, retention class, and attempt ID.
  • Use specific image input constraints for first/last-frame and I2V modes; ensure aspect/resolution rules match mode requirements.
  • Write prompts for the motion system following a defined compact order and ensure prompts respect mode constraints and optional fields like prompt_optimizer and fast_pretreatment.
  • Make the paid boundary explicit: perform a dry-run, show redacted request, exact one-video cost, pricing timestamp, hashes, and host policy; require human digest approval and a positive maximum in the same currency.
  • Before POSTing, acquire an exclusive ledger entry; after a response, keep an allowlisted summary only (task ID, provider code, status digest, timestamps).
  • Follow retry and polling guidance, with explicit handling for various error codes and 5xx cases; do not assume success from HTTP alone.
  • The Python 3.11+ client hailuo_generate.py is provided for dry-run behavior, detailing hosts, prices, models, and payment rules.

When to use it

Use when designing, implementing, debugging, or evaluating direct MiniMax/Hailuo video-generation API workflows. Do not use for consumer Hailuo site or unrelated MiniMax modalities.

What it can touch

  • Tools declared: claude-code, codex, copilot, cursor. (Only listed tools are allowed.)

Caveats

  • License: MIT
  • Regions have separate service endpoints and currencies; a key/plan may not work across regions; do not translate prices between currencies.
  • Restrictions on models and modes; some inputs and outputs are region/model dependent; verify availability and price in the correct console before paid use.
  • Documentation gaps should be treated as unknowns, not defaults; no guarantees on endpoints beyond documented behavior.
From the SKILL.md

# MiniMax Hailuo video Build a reviewed request, obtain exact cost approval, create at most one paid task, then preserve the result and its evidence. Treat documentation gaps as unknowns, not defaults. ## Start with the boundary Choose one service region and keep its account, key, billing, host, and terms together: | Region | Console/docs | API host | Billing currency | |---|---|---|---| | Global

More from generative-media-skills
All skills →
About this skill
What does the minimax-hailuo-video skill do?

Use MiniMax's first-party Hailuo video API safely and reproducibly across global and mainland-China platforms. Covers current text-to-video, image-to-video, first/last-frame, and subject-reference models; prompt and camera craft; region/account routing; exact cost approval; asynchronous jobs and callbacks; artifact provenance; and rights, likeness, disclosure, and data-governance review. Use when designing, implementing, debugging, or evaluating direct MiniMax/Hailuo video-generation API workflows. Do not use for the consumer Hailuo site, Video Agent templates, gateways, or unrelated MiniMax m

How do I install it?

Run `npx skills add calesthio/generative-media-skills --skill minimax-hailuo-video --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.

Where does this skill come from?

From calesthio/generative-media-skills, a repository with 112 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.

Is a popular skill a good skill?

Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.

Keep going