New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Dark Rescue H3 External Camera

by karuvanan in karuvanan/MiniMax-H3-Director-Cut-Studio

Writes fictional, non-graphic rescue scenes for MiniMax H3 with an external cinematic camera, a visible rescuer, Mandarin dialogue and shot-by-shot direction.

Custom licenceAuto-check passedMedia & Creative

Install Dark Rescue H3 External Camera

skills CLI
$ npx skills add karuvanan/MiniMax-H3-Director-Cut-Studio --skill dark-rescue-h3-no-pov -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install karuvanan/MiniMax-H3-Director-Cut-Studio dark-rescue-h3-no-pov --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/karuvanan/MiniMax-H3-Director-Cut-Studio.git skills-src && mkdir -p .claude/skills && cp -r skills-src/'skill special/dark-rescue-h3-no-pov' .claude/skills/dark-rescue-h3-no-pov && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
dark-rescue-h3-no-pov
GitHub stars
132
Token cost
~1.7k tokens
SKILL.md length
890 words
Files
3
Skills in repo
13
Repo updated
First seen
Licence
Custom licence

At a glance

Writes fictional, non-graphic rescue scenes for MiniMax H3 with an external cinematic camera, a visible rescuer, Mandarin dialogue and shot-by-shot direction.

  • Works in 9 steps: exterior hook: show the damaged… → entry: S2 crosses or opens one obstacle… → route discovery: S2 follows one clue… → …
  • Planning a fictional rescue scene for MiniMax H3 shown from an outside camera
  • SKILL.md covers Interpret a Short Request, External-camera Contract, Build a Causal Rescue and Character and Reference…, plus 4 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

This special skill for MiniMax H3 turns a short request, a place, a duration and a rescue goal, into one self-contained fictional rescue story, and it is paired with a default H3 prompt writing skill. Unless you specify otherwise it infers a visible police officer or firefighter as rescuer, one stable adult trapped person, one obstruction, one traversable route and one credible exit, with non-graphic danger and practical light sources.

Its distinguishing rule is the external camera: the rescuer is a visible character and the camera never sits in their eyes. Each Shot spells out framing, camera angle, camera movement, subject action, continuity state and an explicit no-POV direction, and helmet-cam, body-cam, security-camera and drone viewpoints are banned unless you ask for them. A 45-second request defaults to nine chronological five-second Shots, opening with an exterior hook and an entry beat. Real landmarks are described as fictional reconstructions.

When your agent uses it

  • Planning a fictional rescue scene for MiniMax H3 shown from an outside camera
  • Avoiding first-person camera contracts in a rescue story
  • Writing editable Mandarin dialogue and location sound notes for a short rescue clip

Example prompts

  • “Design a 45-second H3 rescue story in a collapsed school corridor, filmed from an external camera.”
  • “Write a dark rescue scene in a narrow alley with a firefighter and a trapped adult, with no rescuer-eye POV.”
  • “Draft the shot list and Mandarin dialogue for a non-graphic building rescue and keep both characters visible.”

Requirements

  • MiniMax H3 with its default H3 prompt writing skill

Workflow steps

9 steps, taken from the first numbered list in SKILL.md.

  1. exterior hook: show the damaged location, visible rescuer and evidence of a trapped person;
  2. entry: S2 crosses or opens one obstacle and exterior sound becomes muffled;
  3. route discovery: S2 follows one clue through plausible geography;
  4. obstruction contact: the trapped person's position and blocking object become clear;
  5. extraction: S2 completes one decisive physical rescue action;
  6. consequence: the environment reacts and closes the original route;
  7. reroute: radio information motivates a specific alternate path;
  8. ascent or exit: both characters travel in one continuous screen direction;
  9. release and Final Hold: reach a safe open space and introduce no new danger.

What it can do on your machine

Read from SKILL.md and the folder at commit 9bdc33d. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Dark Rescue H3 External Camera loads about 1.7k tokens when it runs. Until then it costs about 97 tokens; SKILL.md has 890 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~97
When it runs · the whole SKILL.md, loaded when a task matches
~1.7k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

Its licence (Custom licence) doesn't allow us to republish the file, so here is its outline and opening line. It has 890 words (~1,699 tokens).

“Apply this Special Skill with the bound Default H3 Prompt Writing Skill. This is the deliberate no-POV variant: the rescuer is a visible on-screen character and the camera is an external cinematic observer. Never copy the first-person camera contract from…”

— opening of SKILL.md by karuvanan, Custom licence
name
dark-rescue-h3-no-pov

Read the full SKILL.md on GitHub

Files

SKILL.md and 2 other files in skill special/dark-rescue-h3-no-pov of karuvanan/MiniMax-H3-Director-Cut-Studio.

  • SKILL.md
  • DESIGN_REQUIREMENT.txt
  • SKILL.cn.md

Open the folder on GitHubat commit 9bdc33d

Compare with similar skills

Dark Rescue H3 External Camera next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Dark Rescue H3 External Camera compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Dark Rescue H3 External Camera this skillkaruvanan/MiniMax-H3-Director-Cut-Studio132—~1.7kAutomated safety check: PassCustom licence
MiniMax H3 Video DirectorTFboy1/oh-my-minimaxh3-director143—~2.4kAutomated safety check: PassMIT
MiniMax H3 Video PromptingSlavaSexton/ComfyUI-Agent-Kit105—~2.5kAutomated safety check: PassApache-2.0
Hailuo Promptingnodetool-ai/nodetool560—~1.3kAutomated safety check: PassAGPL-3.0
Video Cover Imageitwanger/toBeBetterJavaer18k—~3.3kAutomated safety check: PassNone
Seedance 2.0 Video PromptingEmily2040/seedance-2.07.6k1 repos~7.4kAutomated safety check: PassMIT

Similar skills

  • MiniMax H3 Video Director

    TFboy1/oh-my-minimaxh3-director

    Turns a script into a storyboard, assigns MiniMax H3 workflows in ComfyUI, monitors batch generation and builds a Jianying draft of the finished video.

    143 GitHub stars~2.4k tokensUpdated 1 mo ago
    Media & CreativeAuto-check passed

  • MiniMax H3 Video Prompting

    SlavaSexton/ComfyUI-Agent-Kit

    Guides prompting and local ComfyUI use of MiniMax H3 (Hailuo 3), which generates video with synchronized audio, including prompt format, quants and troubleshooting.

    105 GitHub stars~2.5k tokensUpdated 1 mo ago
    Media & CreativeAuto-check passed

  • Hailuo Prompting

    nodetool-ai/nodetool

    Prompt MiniMax's Hailuo video line — the chronological beat order it animates from, the fifteen bracketed camera commands the Director endpoints accept and the three-per-bracket rule, when to switch…

    560 GitHub stars~1.3k tokensUpdated today
    Media & CreativeAuto-check passed

  • Video Cover Image

    itwanger/toBeBetterJavaer

    Generate matched 3:4, 16:9, and 4:3 short-video cover images from toBeBetterJavaer video scripts or AI/Java technical topics.

    18k GitHub stars~3.3k tokensUpdated yesterday
    Media & CreativeAuto-check passed

  • Seedance 2.0 Video Prompting

    Emily2040/seedance-2.0

    Routes Seedance 2.0 video work across Dreamina, API and router surfaces, covering prompts, reference handling, audio and lip-sync, pricing and model-ID questions.

    7.6k GitHub starsUsed in 1 repo~7.4k tokens
    Media & CreativeAuto-check passed

  • Seedance IP-Safe Prompt Rewriter

    Emily2040/seedance-2.0

    Rewrites Seedance 2.0 video prompts that name characters, brands, celebrities, songs or real people into original, rights-safe versions that keep the creative intent.

    7.6k GitHub starsUsed in 1 repo~930 tokens
    Media & CreativeAuto-check passed

More from karuvanan/MiniMax-H3-Director-Cut-Studio

All 14 skills in this repo

  • Hong Kong Comic Fighter for H3

    karuvanan/MiniMax-H3-Director-Cut-Studio

    Special skill that turns loaded Hong Kong comic panels into photoreal MiniMax H3 martial-arts sequences with readable attack and defence action.

    132 GitHub stars~4.4k tokensUpdated today
    Auto-check passed

  • 60-Second Cinematic Story Director

    karuvanan/MiniMax-H3-Director-Cut-Studio

    Adapts prose or rough story material into a roughly 60-second MiniMax H3 short with shot planning, Mandarin dialogue and voice-over, and a strong ending.

    132 GitHub stars~1.8k tokensUpdated today
    Auto-check passed

  • Comic Talk Show H3

    karuvanan/MiniMax-H3-Director-Cut-Studio

    Turn one loaded P1 group image into a duration-aware ensemble comedy in which every complete foreground person is detected dynamically, assigned a stable left-to-right speaker identity, given one…

    132 GitHub stars~2.3k tokensUpdated today
    Auto-check passed

  • Long-Form H3 Director

    karuvanan/MiniMax-H3-Director-Cut-Studio

    Plans long-form MiniMax H3 video productions as Sequence, Shot, and Segment contracts that stay continuous across generation windows.

    132 GitHub stars~1.5k tokensUpdated today
    Auto-check passed

  • MiniMax H3 Singing Music Video

    karuvanan/MiniMax-H3-Director-Cut-Studio

    Directs a lip-synced singing music video in the MiniMax H3 studio, locking the lead singer's identity, a scene master and exact audio references so the final track stays untouched.

    132 GitHub stars~1.8k tokensUpdated today
    Auto-check passed

  • Short Drama H3 Director

    karuvanan/MiniMax-H3-Director-Cut-Studio

    Develops vertical and short-form drama episodes for MiniMax H3 into causal stories, timed Shot Blocks, exact dialogue and Director Design JSON for an editable Timeline.

    132 GitHub stars~2.3k tokensUpdated today
    Auto-check passed

Works with

Categories

Questions about Dark Rescue H3 External Camera

What does Dark Rescue H3 External Camera do?

Writes fictional, non-graphic rescue scenes for MiniMax H3 with an external cinematic camera, a visible rescuer, Mandarin dialogue and shot-by-shot direction. This special skill for MiniMax H3 turns a short request, a place, a duration and a rescue goal, into one self-contained fictional rescue story, and it is paired with a default H3 prompt writing skill. Unless you specify otherwise it infers a visible police officer or firefighter as rescuer, one stable adult trapped person, one obstruction, one traversable route and one credible exit, with non-graphic danger and practical light sources.

When should I use Dark Rescue H3 External Camera?

Dark Rescue H3 External Camera fits situations like: planning a fictional rescue scene for MiniMax H3 shown from an outside camera; avoiding first-person camera contracts in a rescue story; writing editable Mandarin dialogue and location sound notes for a short rescue clip.

How do I install Dark Rescue H3 External Camera in Claude Code?

Run `npx skills add karuvanan/MiniMax-H3-Director-Cut-Studio --skill dark-rescue-h3-no-pov -a claude-code`. Or copy the skill folder (skill special/dark-rescue-h3-no-pov in karuvanan/MiniMax-H3-Director-Cut-Studio) into .claude/skills/dark-rescue-h3-no-pov in your project. Claude Code loads it when a task matches its description.

How do I install Dark Rescue H3 External Camera in Codex?

Run `npx skills add karuvanan/MiniMax-H3-Director-Cut-Studio --skill dark-rescue-h3-no-pov -a codex`. Or copy the skill folder (skill special/dark-rescue-h3-no-pov in karuvanan/MiniMax-H3-Director-Cut-Studio) into .agents/skills/dark-rescue-h3-no-pov in your project. Codex loads it when a task matches its description.

Can I use Dark Rescue H3 External Camera in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add karuvanan/MiniMax-H3-Director-Cut-Studio --skill dark-rescue-h3-no-pov -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/dark-rescue-h3-no-pov, .gemini/skills/dark-rescue-h3-no-pov, .github/skills/dark-rescue-h3-no-pov and .opencode/skills/dark-rescue-h3-no-pov in your project.

What does Dark Rescue H3 External Camera need to run?

SKILL.md names no scripts, command-line tools or credentials: Dark Rescue H3 External Camera is instructions for the agent only. Our summary lists: MiniMax H3 with its default H3 prompt writing skill.

Does Dark Rescue H3 External Camera access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Dark Rescue H3 External Camera safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Dark Rescue H3 External Camera use?

Dark Rescue H3 External Camera has a licence file (the repository's licence) that doesn't match a standard licence. Read it on GitHub before reusing the skill.

How many tokens does Dark Rescue H3 External Camera use?

About 1.7k tokens (SKILL.md is roughly 6.8k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Dark Rescue H3 External Camera?

Skills that share tags, products or a category with Dark Rescue H3 External Camera: MiniMax H3 Video Director (TFboy1/oh-my-minimaxh3-director, 143 stars), MiniMax H3 Video Prompting (SlavaSexton/ComfyUI-Agent-Kit, 105 stars), Hailuo Prompting (nodetool-ai/nodetool, 560 stars) and Video Cover Image (itwanger/toBeBetterJavaer, 18k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Dark Rescue H3 External Camera?

karuvanan (a GitHub user) maintains it in karuvanan/MiniMax-H3-Director-Cut-Studio, which has 132 GitHub stars. The repository holds 13 skills in this directory. The repository was last updated on October 11, 2026.

Source: karuvanan/MiniMax-H3-Director-Cut-Studio on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.