agentleFS
thoitiettxl-cyberthoitiettxl-cyber/Claw-II/skills/video-generation/SKILL.md

video-generation

Skill2 starsChanged 7 months agoMITView on GitHub

Build structured video-generation prompts, handle optional reference-image inputs, and optionally invoke an imported helper that calls an external video API. Use when the user explicitly wants a generated video concept, prompt package, or video artifact.

22 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use surprise-me, ppt-generation and 6 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • stophobiaSkill

    surprise-me

    Create a delightful, unexpected "wow" experience for the user by dynamically discovering and creatively combining other enabled skills. Triggers when the user says "surprise me" or any request expressing a desire for an unexpected creative showcase. Also triggers when the user is bored, wants inspiration, or asks for "something interesting".

    Also in 3 projects that use this

  • HK-hubSkill

    ppt-generation

    Use this skill when the user requests to generate, create, or make presentations (PPT/PPTX). Creates visually rich slides by generating images for each slide and composing them into a PowerPoint file.

    Also in 3 projects that use this

  • stophobiaSkill

    github-deep-research

    Conduct multi-round deep research on any GitHub Repo. Use when users request comprehensive analysis, timeline reconstruction, competitive analysis, or in-depth investigation of GitHub. Produces structured markdown reports with executive summaries, chronological timelines, metrics analysis, and Mermaid diagrams. Triggers on Github repository URL or open source projects.

    Also in 3 projects that use this

  • MicrosoftSkill

    podcast-generation

    Generate AI-powered podcast-style audio narratives using Azure OpenAI's GPT Realtime Mini model via WebSocket. Use when building text-to-speech features, audio narrative generation, podcast creation from content, or integrating with Azure OpenAI Realtime API for real audio output. Covers full-stack implementation from React frontend to Python FastAPI backend with WebSocket streaming.

    Also in 3 projects that use this

  • HK-hubSkill

    chart-visualization

    This skill should be used when the user wants to visualize data. It intelligently selects the most suitable chart type from 26 available options, extracts parameters based on detailed specifications, and generates a chart image using a JavaScript script.

    Also in 3 projects that use this

  • VercelSkill

    vercel-deploy

    Deploy applications and websites to Vercel with a claimable preview. Use when the user requests deployment actions like "deploy my app", "deploy and give me the link", "push this live", or "create a preview deployment". No authentication required - returns preview URL and claimable deployment link.

    Also in 3 projects that use this

The file

We split this skill into the rules it gives an agent

6 rules. 0 are common, 6 are distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 19 edited versions we read keep these.

  • 6

    Distinctive

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    If execution would upload prompt/reference content to an external API or download generated media, obtain approval first.

    line 62
  2. Distinctive:

    If approved and prerequisites exist, invoke the helper.

    line 70
  3. Distinctive:

    ask for minimum missing details or provide a bounded prompt draft with assumptions labeled.

    line 76
  4. Distinctive:

    stop at prompt-package output.

    line 80
  5. Distinctive:

    no fabricated generated artifact

    line 90
  6. Distinctive:

    no silent external upload/download

    line 91

“Common” is measured: kept by at least 6 in 10 of the 19 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Video Generation

Indexed Reference Map

  • @[SKILL.md#L1-L92] Frontmatter, scope, KB notes, trigger rules, SOP, error handling, output contract.
  • @[references/INDEX.md#L1-L11] Reading order and file map.
  • @[references/QUICK_REFERENCE.md#L1-L20] Trigger boundary, approval split, and stop conditions.
  • @[references/CORE_API.md#L1-L40] Prompt package contract, helper/API behavior, polling, and privacy boundary.
  • @[references/PATTERNS.md#L1-L13] Prompt-shaping and reference-image handling patterns.
  • @[references/EXAMPLES.md#L1-L15] Representative video requests and handling.
  • @[references/AI_WORKFLOW.md#L1-L14] Bounded orchestration flow.
  • @[scripts/generate.py#L1-L94] Imported external video-generation helper.

Scope

  • In-scope:
    • structure video-generation prompts from user intent
    • organize optional reference-image inputs
    • prepare prompt files/specs for later generation
    • execute the imported helper only when external API use is approved
  • Out-of-scope:
    • blind execution of upstream helper without review/approval
    • pretending a video was generated when only a prompt draft exists
    • downloading/searching reference media unless separately requested and approved

KB Mode Notes

  • Reading order:
    1. references/INDEX.md
    2. references/QUICK_REFERENCE.md
    3. references/CORE_API.md
    4. references/PATTERNS.md
    5. references/EXAMPLES.md
    6. references/AI_WORKFLOW.md
    7. scripts/generate.py
  • Coverage Matrix:
    • trigger boundary + approval split -> QUICK_REFERENCE.md
    • prompt package + helper/API/polling contract -> CORE_API.md
    • prompt engineering and reference handling -> PATTERNS.md
    • representative use cases -> EXAMPLES.md
    • orchestration order -> AI_WORKFLOW.md
  • Portability note:
    • Local governance treats the helper as an external API adapter with long-running polling; re-check endpoint, auth, timeout, and download policy before porting.

Trigger Rules

  • Positive:
    • The user explicitly wants a video clip, short scene, animated sequence, or generation-ready video prompt package.
    • A structured prompt package is needed for later video generation.
  • Negative:
    • The task is only ideation without any prompt/package need.
    • The request is primarily about local video editing rather than AI video generation.
    • External API upload/generation is disallowed and prompt-only output would not satisfy the request.
  • Escalation:
    • If execution would upload prompt/reference content to an external API or download generated media, obtain approval first.
    • Without approval, return the structured prompt package and execution notes only.

SOP

  1. Confirm the user wants AI video generation or a generation-ready prompt package.
  2. Extract subject, scene progression, camera, style, lighting, duration cues, and optional reference-image role.
  3. Build a structured prompt/package in English unless the target workflow explicitly requires otherwise.
  4. Validate that prompt details are traceable to user instructions; do not invent hidden story beats.
  5. If approved and prerequisites exist, invoke the helper.
  6. Otherwise, return the prompt/spec package and state that execution was deferred.
  7. Report actual output artifact path or explicit deferral.

Error Handling

  • Missing creative requirements:
    • ask for minimum missing details or provide a bounded prompt draft with assumptions labeled.
  • Missing/invalid reference image:
    • exclude it and state the effect on generation.
  • Missing API credential/runtime dependency:
    • stop at prompt-package output; do not fake execution.
  • API/polling/download failure:
    • report the real failure and keep the prompt package for retry.

Output Contract

  • Deliverables:
    • structured prompt/package
    • reference-image usage or deferral note
    • actual output path only if video generation succeeded
  • Validation:
    • no fabricated generated artifact
    • no silent external upload/download
    • prompt details remain faithful to user intent
  • Compliance Verdict:
    • PASS when prompt structure is sound and execution/deferral is reported truthfully.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.