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

AIGC Video Production Workflow

by renmu2017 in renmu2017/Hell-Grind-AIGC-Skill

Model-agnostic workflow for AI image and video projects: prompt writing, tracking of assets and shots, continuity checks and diagnosis of failed generations.

MITAuto-check passedMedia & Creative

Install AIGC Video Production Workflow

skills CLI
$ npx skills add renmu2017/Hell-Grind-AIGC-Skill --skill hell-grind-aigc-skill -a claude-code

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

GitHub CLI
$ gh skill install renmu2017/Hell-Grind-AIGC-Skill hell-grind-aigc-skill --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/renmu2017/Hell-Grind-AIGC-Skill.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skill/hell-grind-aigc-skill .claude/skills/hell-grind-aigc-skill && 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
hell-grind-aigc-skill
GitHub stars
230
Token cost
~1.8k tokens
SKILL.md length
772 words
Files
56 (incl. scripts, references, assets)
Skills in repo
1
Repo updated
First seen
Licence
MIT

At a glance

Model-agnostic workflow for AI image and video projects: prompt writing, tracking of assets and shots, continuity checks and diagnosis of failed generations.

  • Works in 6 steps: Extract intent, hard constraints,… → Preserve explicit counts, duration,… → Ask only when a missing fact would… → …
  • Setting up folders and trackers for an AI video project
  • SKILL.md covers Classify the request, Route to the minimum references, Work in this order and Choose richness deliberately, plus 3 more sections
  • Calls python3

What it does

Each request is classified first: the workflow (production management, prompt writing or failure diagnosis), the medium (image, video or mixed), the operation (create, polish, initialize, audit or diagnose), the richness level, whether it is a standalone prompt or part of a project, the provider, and what authority the agent has (text only, local files, generating or publishing media). Only the reference files that route needs are then read, such as prompt architecture, image and video prompt contracts, camera language, spatial blocking and a quality rubric.

Approved project facts, creative instructions, provider settings, generation attempts and review decisions are kept separate, and identity, counts, spatial relationships, timing and continuity are preserved while the visual style changes. A project template provides folders and CSV files for the brief, story bible, assets, scenes and shots. Local scripts need Python 3.10 or newer, while prompt writing needs no shell or generation API.

When your agent uses it

  • Setting up folders and trackers for an AI video project
  • Writing or polishing an image or video prompt without losing hard constraints
  • Diagnosing why a generated shot broke continuity
  • Auditing a project before delivery

Example prompts

  • “Initialize a project for a short product video, with my brief in ./brief.md.”
  • “Polish this video prompt for a rainy street chase without changing the main character's look.”
  • “Audit my shot list for continuity problems before I generate anything.”

Requirements

  • Python 3.10 or newer for the local scripts

Workflow steps

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

  1. Extract intent, hard constraints, reference scope, output use, and authority.
  2. Preserve explicit counts, duration, exact text/dialogue, identity, state, rights, and prohibited content.
  3. Ask only when a missing fact would materially change the result; otherwise state a conservative assumption.
  4. Build a model-independent artifact, then place provider-specific settings in a separate platform adapter.
  5. Check IDs, references, timing, spatial logic, continuity, contradictions, and current quality gates.
  6. Return the artifact with the fixed output required by its reference.

What it can do on your machine

Read from SKILL.md and the folder at commit 742cb1f. 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

    Ships 1 file in scripts/, which the agent can run.

    Shell commands in SKILL.md call:

    • python3

    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

AIGC Video Production Workflow loads about 1.8k tokens when it runs, and up to ~34k if it reads all its reference files. Until then it costs about 68 tokens; SKILL.md has 772 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~68
When it runs · the whole SKILL.md, loaded when a task matches
~1.8k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~34k

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); the scripts in this folder are not scanned.

SKILL.md

The full file from renmu2017/Hell-Grind-AIGC-Skill at commit 742cb1f, republished under its MIT licence (© renmu2017). 772 words, ~1,770 tokens.

Download SKILL.mdSave it as .claude/skills/hell-grind-aigc-skill/SKILL.md (or your agent's skills folder). This skill also uses 55 other files; get the full folder from GitHub.
name
hell-grind-aigc-skill
description
Use when structuring, managing, auditing, or diagnosing an AIGC video project; creating or polishing model-agnostic image and video prompts; or tracking assets, shots, generations, and continuity while preserving creative intent and hard constraints.

Hell Grind AIGC Skill

Use this Skill as a model-agnostic AIGC production workflow in an AI assistant or agent that can read its instructions and supporting files. Keep approved project facts, creative instructions, provider settings, generation attempts, and review decisions separate. Local scripts require Python 3.10+; prompt writing itself does not require a shell or a generation API.

Adapt the visual language to the user's brief: live-action realism, stylized animation, illustration, product imagery, or another explicitly chosen medium. Preserve identity, counts, spatial relationships, timing, and continuity while changing rendering, materials, lighting, and motion conventions. Do not carry photorealistic skin, natural-light rules, or physical-camera language into a style where they conflict with the brief.

Use the user's requested output language. References contain Chinese and English production terminology; client-specific UI metadata is optional and does not change the core workflow.

Classify the request

Determine these dimensions before writing:

  • Workflow: 生产管理 / 提示词创作 / 失败诊断.
  • Medium: image / video / mixed project.
  • Operation: create / polish / initialize / audit / diagnose.
  • Richness: 精简版 / 标准版 / 导演版.
  • Context: standalone prompt / existing project.
  • Provider: unspecified / named without adaptation / explicit adaptation requested.
  • Authority: text only / local files / media generation / upload or publication.

Route to the minimum references

For any non-trivial prompt, first read references/prompt-architecture.md. Read references/methodology-evidence.md when explaining why the workflow uses assets, versions, iteration, or risk gates.

生产管理工作流

For project setup, tracking, continuity, review, or delivery, read:

  • references/production-workflow.md
  • references/project-schemas.md
  • references/project-qa-gates.md for audit or delivery
提示词创作工作流：图片从零生成 / 图片润色扩写

Read:

  • references/image-prompt-crafting.md
  • references/reference-asset-control.md for asset sheets, identity/state versions, or reference inheritance
  • references/spatial-blocking.md for multiple subjects, exact placement, screen direction, or unique props
  • references/prompt-preservation.md
  • references/prompt-quality-rubric.md
视频从零生成 / 视频润色扩写

Read:

  • references/video-prompt-contract.md
  • references/camera-editing-language.md for framing, lens effect, movement, focus, cuts, or camera failures
  • references/performance-direction.md for acting, eyelines, breath, dialogue performance, or stillness
  • references/action-physics-vfx.md for movement, impact, fights, throws, destruction, creatures, or effects
  • references/spatial-blocking.md for exact placement, direction, axis, and unique objects
  • references/lighting-color-material.md for motivated light, exposure, palette, surfaces, or weather
  • references/dialogue-audio.md for exact dialogue, lips, ambience, foley, silence, or mix
  • references/continuity-control.md for cross-shot identity, state, axis, action, environment, or sound
  • references/negative-constraints.md when selecting and compressing failure-specific avoid rules
  • references/multi-shot-sequences.md for cuts, dialogue coverage, action sequences, or montage
  • references/prompt-preservation.md
  • references/prompt-quality-rubric.md
失败诊断

Read references/failure-diagnosis.md, then the affected layer guide. Start with the relevant quality gate and production record. Identify whether the defect belongs to the asset, scene/shot contract, prompt, provider adapter, generation attempt, or edit. Do not default to adding more negative words.

For identity drift, inspect the approved asset state and reference scope first; do not begin by expanding negative constraints.

For repeated generations, candidate comparison, version changes, or budget/stop decisions, read references/iteration-selection.md.

Read references/prompt-examples.md only when an example materially helps. For work inside an existing project, first load its approved asset, scene, shot, prompt version, generation, selection, and continuity records.

Show full SKILL.md (323 more words)Show less

Work in this order

  1. Extract intent, hard constraints, reference scope, output use, and authority.
  2. Preserve explicit counts, duration, exact text/dialogue, identity, state, rights, and prohibited content.
  3. Ask only when a missing fact would materially change the result; otherwise state a conservative assumption.
  4. Build a model-independent artifact, then place provider-specific settings in a separate platform adapter.
  5. Check IDs, references, timing, spatial logic, continuity, contradictions, and current quality gates.
  6. Return the artifact with the fixed output required by its reference.

Choose richness deliberately

  • 精简版: low-complexity exploration; keep only result-determining facts.
  • 标准版: default production form; cover the complete image or shot contract without repeating approved facts.
  • 导演版: complex action, dialogue, multi-character, multi-shot, or strict-continuity work; expose timing, performance, camera endpoints, audio, continuity, and risk locks.

Richness changes detail, never the user's intent or hard constraints.

Initialize or audit a project

Run the bundled scripts when local file creation is requested:

bash
python3 scripts/init_project.py --name "Project name" --output /absolute/project/path
python3 scripts/validate_project.py /absolute/project/path --strict-v2
python3 scripts/audit_prompt.py /absolute/prompt.md --medium video

The initializer must refuse a non-empty target. The validator must remain read-only. Do not replace these safety behaviors with ad hoc file operations.

Fixed prompt output

Unless the user asks for a narrower artifact, return:

  1. Mode and richness.
  2. Intent and hard-constraint snapshot.
  3. Model-independent master prompt.
  4. Separate platform adapter; write unspecified when unknown.
  5. Design summary for new prompts or modification summary for polishing.
  6. Assumptions and unresolved choices.
  7. Quality score with concrete deductions.
  8. Risks and first-test recommendation.

Preserve boundaries

  • 默认不调用付费模型，不上传、不发布、不部署。
  • Do not treat prompt writing as authorization to generate media.
  • Do not invent an authorization, budget, provider, reference right, or delivery approval.
  • Do not copy project-specific Hell Grind characters, assets, or long source prompts into a new project unless the user separately supplies rights and requests reuse.
  • Keep each local initialize/validate/audit operation at 0 network requests and 0 database operations.

If the user explicitly requests generation or publication, treat it as a separate action and follow the active tool's confirmation, cost, and safety rules.

© renmu2017, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 55 other files (scripts, references, assets) in skill/hell-grind-aigc-skill of renmu2017/Hell-Grind-AIGC-Skill.

  • SKILL.md
  • VERSION
  • agents/openai.yaml
  • assets/project-template/00_brief/brief.md
  • assets/project-template/00_brief/project.yaml
  • assets/project-template/01_story/story-bible.md
  • assets/project-template/02_assets/asset-state-matrix.csv
  • assets/project-template/02_assets/assets.csv
  • assets/project-template/02_assets/reference-scope.csv
  • assets/project-template/03_scenes/scenes.csv
  • assets/project-template/03_scenes/spatial-map.csv
  • assets/project-template/04_shots/audio-cues.csv
  • assets/project-template/04_shots/beat-sheet.csv
  • … and 43 more

Open the folder on GitHubat commit 742cb1f

Compare with similar skills

AIGC Video Production Workflow 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.

AIGC Video Production Workflow compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
AIGC Video Production Workflow this skillrenmu2017/Hell-Grind-AIGC-Skill230—~1.8kAutomated safety check: PassMIT
Cinematic Video Prompt GuideRylaispirit/cinematic-video-prompt-skill147—~5kAutomated safety check: PassMIT
Prompt EngineAgriciDaniel/claude-prompts111—~1.2kAutomated safety check: PassMIT
Seedance 2.0 Video PromptingEmily2040/seedance-2.07.6k1 repos~7.4kAutomated safety check: PassMIT
SN Motion HTMLOpenSenseNova/SenseNova-Skills5.7k—~2.2kAutomated safety check: NotesMIT
Seedance IP-Safe Prompt RewriterEmily2040/seedance-2.07.6k1 repos~930Automated safety check: PassMIT

Similar skills

  • Cinematic Video Prompt Guide

    Rylaispirit/cinematic-video-prompt-skill

    Acts as a cinematography dictionary and prompt formula for writing AI video and image prompts about camera angles, movement, lighting and mood.

    147 GitHub stars~5k tokensUpdated 13 days ago
    Media & CreativeAuto-check passed

  • Prompt Engine

    AgriciDaniel/claude-prompts

    Ultimate AI prompt database and builder with 2,500+ curated prompts across 19 categories and 17 AI models (Midjourney, Flux, Leonardo AI, DALL-E, Sora, Imagen, Mystic, Stable Diffusion, Ideogram…

    111 GitHub stars~1.2k tokensUpdated 6 mo ago
    AI & LLM EngineeringAuto-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

  • SN Motion HTML

    OpenSenseNova/SenseNova-Skills

    Builds HTML stories where one continuous camera journey advances with page progress, using researched structure, AI stills, Seedance video clips and browser QA.

    5.7k GitHub stars~2.2k tokensUpdated 2 days ago
    Media & CreativeAuto-check: notes

  • 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

  • Seedance Storyboard Generator

    liangdabiao/Seedance2-Storyboard-Generator

    专业的Seedance 2.0平台AI视频脚本和分镜生成器。当用户要求：(1) 将文章/故事转换为视频脚本，(2) 生成Seedance 2.0分镜提示词，(3) 规划多集AI视频系列，(4) 为GPT-Image-2、Seedream、Nano Banana…

    2.6k GitHub stars~2.2k tokensUpdated 20 days ago
    Media & CreativeAuto-check passed

Categories

Questions about AIGC Video Production Workflow

What does AIGC Video Production Workflow do?

Model-agnostic workflow for AI image and video projects: prompt writing, tracking of assets and shots, continuity checks and diagnosis of failed generations. Each request is classified first: the workflow (production management, prompt writing or failure diagnosis), the medium (image, video or mixed), the operation (create, polish, initialize, audit or diagnose), the richness level, whether it is a standalone prompt or part of a project, the provider, and what authority the agent has (text only, local files, generating or publishing media). Only the reference files that route needs are then read, such as prompt architecture, image and video prompt contracts, camera language, spatial blocking and a quality rubric.

When should I use AIGC Video Production Workflow?

AIGC Video Production Workflow fits situations like: setting up folders and trackers for an AI video project; writing or polishing an image or video prompt without losing hard constraints; diagnosing why a generated shot broke continuity; auditing a project before delivery.

How do I install AIGC Video Production Workflow in Claude Code?

Run `npx skills add renmu2017/Hell-Grind-AIGC-Skill --skill hell-grind-aigc-skill -a claude-code`. Or copy the skill folder (skill/hell-grind-aigc-skill in renmu2017/Hell-Grind-AIGC-Skill) into .claude/skills/hell-grind-aigc-skill in your project. Claude Code loads it when a task matches its description.

How do I install AIGC Video Production Workflow in Codex?

Run `npx skills add renmu2017/Hell-Grind-AIGC-Skill --skill hell-grind-aigc-skill -a codex`. Or copy the skill folder (skill/hell-grind-aigc-skill in renmu2017/Hell-Grind-AIGC-Skill) into .agents/skills/hell-grind-aigc-skill in your project. Codex loads it when a task matches its description.

Can I use AIGC Video Production Workflow 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 renmu2017/Hell-Grind-AIGC-Skill --skill hell-grind-aigc-skill -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/hell-grind-aigc-skill, .gemini/skills/hell-grind-aigc-skill, .github/skills/hell-grind-aigc-skill and .opencode/skills/hell-grind-aigc-skill in your project.

What does AIGC Video Production Workflow need to run?

Going by SKILL.md and its folder, AIGC Video Production Workflow needs the command-line tools its instructions call (python3). Our summary lists: Python 3.10 or newer for the local scripts.

Does AIGC Video Production Workflow 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 AIGC Video Production Workflow 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. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.

What licence does AIGC Video Production Workflow use?

AIGC Video Production Workflow is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does AIGC Video Production Workflow use?

About 1.8k tokens (SKILL.md is roughly 7.1k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 33k tokens, read only when the agent opens those files.

What are the alternatives to AIGC Video Production Workflow?

Skills that share tags, products or a category with AIGC Video Production Workflow: Cinematic Video Prompt Guide (Rylaispirit/cinematic-video-prompt-skill, 147 stars), Prompt Engine (AgriciDaniel/claude-prompts, 111 stars), Seedance 2.0 Video Prompting (Emily2040/seedance-2.0, 7.6k stars) and SN Motion HTML (OpenSenseNova/SenseNova-Skills, 5.7k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains AIGC Video Production Workflow?

renmu2017 (a GitHub user) maintains it in renmu2017/Hell-Grind-AIGC-Skill, which has 230 GitHub stars. The repository was last updated on September 24, 2026.

Source: renmu2017/Hell-Grind-AIGC-Skill on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.