Slopcamera logo

Slopcamera

Organization
hraness
slopcamera

Create, inspect, edit and render visual media with the SlopCamera CLI and SDK. Use for diagrams, raster-to-SVG conversion, existing screen or camera recordings, video editing and captions, social collage banners, music videos from authored scenes and local tracks, AI images/video/speech/transcription, Three.js scenes and world-space media, Blender rigs and simulation, CadQuery models, parametric architectural designs, Manim educational films, HTML/WGSL motion graphics, and durable agent workflows.

Overview

Publisherhraness
Repositoryslopcamera
Skill nameslopcamera
Stars
7
Forks
1
Bundled files
39
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 39 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by hraness on GitHub. Read the source before you install it.

Installation

Install the Slopcamera AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/hraness/slopcamera/tree/main/skills/slopcamera
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/hraness/slopcamera.git /tmp/slopcamera
mkdir -p .claude/skills
cp -r /tmp/slopcamera/skills/slopcamera .claude/skills/slopcamera
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Slopcamera in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Slopcamera on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Slopcamera is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Create visual media with SlopCamera

Start from the requested result and existing source. Use the installed slopcamera CLI, inspect its real capabilities and retain the authored source beside its derived media. Read only the references needed by the task.

For creative film and animation, choose coherent art direction before rendering. Use creative direction to turn a brief into staging, a hardest-shot test, deliberate sound, and a visible source revision. Use visual style direction for historical footage, animation families, resolution, and visual review. Default to native 4K for an unspecified creative master when the renderer and source support it; preserve deliberate pixel grids, period aspect ratios, source limits, and the user's explicit settings. Treat quality as staging, materials, movement, and finishing together.

For every 3D brief, apply the 3D quality bar, "accurate physics, AAA graphics, VFX", unless the user overrides it, and review the render against all three parts before handing it back.

Establish the host

Run slopcamera --help and use slopcamera doctor --json for the selected local tools. slopcamera status --json reports what is running, credits and the newest outputs; slopcamera commands --json lists every command with what it may change. If installation or a version mismatch blocks the task, read installation and readiness. A skill installation does not install the CLI or native engines.

SlopCamera installs from its verified release archive or from source. Historical Atet archives contain the old package and executable, not these renamed commands. Discover IDs and options through help, operations, workflows, ai models and html catalog; never invent them or silently switch to historical paid-world commands.

Choose the workflow

Requested resultRead
Creative brief, polished showcase, or a meaningful visual revisionCreative direction
Historical film, cel animation, pixel art, classic animation styles, or a demo portfolioVisual style direction
Editable diagram, flowchart or visual explanationDiagrams and visual communication
Patent-style drawing sheets, physical margins, monochrome SVGs or a drawing PDFDrawing sheets
Custom diagram themes, fonts or icon packagesCustomization
Raster artwork converted to SVGVectorization
Deterministic oil-paint study from named tubes and replayable bristle strokesOil paint
Deterministic vector icon, icon scene or construction program, no modelIcon scenes
Tempo, meter and section cues from a Soundfish score or MIDI fileSoundtracks
Clean up, caption, frame, or deliver existing recordings and footageVideo projects
Music video, dancing mascot or timed HTML scene with a local soundtrackMusic videos
Product launch film, UI mockup motion, kinetic type, or coming from HyperFrames or RemotionLaunch films; for a whole Hraness product launch, the product-launch agent skill
Authorized YouTube or other public web-media excerpt (yt-dlp / youtube-dl)Web-media excerpts
Generate images, clips, narration or transcriptsGateway media
Product mark, marketing illustration or topic iconBrand illustrations
Compose an editorial or social banner from generated layers, local type and diagramsSocial collage banners
Review alternative textures, skyboxes, backdrops, design candidates or whole-scene variantsImage galleries
Tall scrolling pixel landscapes, linked generated sections, palette-safe alpha artPixel landscapes
Budgeted short clips, reviewed takes and continuityDirecting video
Editable Three/Spark scene, saved world, named-part edits or shared cameraDirected scenes
Semantic direction, galleries, bounded effects, temporal audit or the cinematic-world recipe packDirected scenes
Author a scene from code, generate procedural entities, or audit framingScene building
Refine an existing scene, organic interactions, contact, staging, or final movie qualityScene refinement
Parametric architecture, furniture, dimensions, repeated structures or editable design variantsParametric design
Blender, rigs, bakes, CAD, shared native assets or production framesNative studio
Any 3D brief: physics, PBR, color management, anti-aliasing, VFX and the review checklist3D quality bar
Blender model for the web: high-to-low baking, texture budgets, LODs, GLB export and runtime checksWeb-ready 3D assets
Manim lesson, narrated explanation or mathematical animationEducational video
Typed Bun SDK, built-in workflow, durable resume or MCPWorkflows and SDK
Reference-led Three scene, transparent 3D loop or metallic logoReference-led 3D
Travel-photo rubber-stamp field-note posterRubber-stamp field notes

Combine workflows when the result needs them. Inspect generated media before choosing it, retain asset and runtime receipts, then compose and render the selected sources. Follow existing user selection criteria and authorization; ask only for a material missing decision or authority.

Preserve source and execution boundaries

Keep originals, explicit timing, stable IDs and returned lineage. Authoring a creative scene may require visual invention; literal diagram facts, supplied copy and identity constraints must stay literal in their respective modes.

Credentials and upload/native-code acknowledgements belong to the invocation, not authored source or project state. A native import does not authorize execution. A local render does not authorize a model upload. Never automatically retry an ambiguous paid or native attempt; inspect and reconcile its retained state first.

Verify the intended result

Use each workflow's relevant checks. Inspect actual image pixels or video frames, including cuts, first/last frames, captions, color and alpha when applicable. Review sound when the environment supports playback; report signal-only checks honestly when it does not. A receipt proves a recorded operation and identities, not visual quality or that a simulation is physically valid.

Deliver the useful artifact paths, source/receipt locations and meaningful limitations. Keep rejected attempts as evidence when they explain a recovery or selection. Do not run diagram checks for an unrelated media task.

Optional support at closeout

After delivering useful work with the already available CLI, read optional support for one brief invitation. Skip this for unattended/subagent work, failures, repeated repair loops, a prior conversation invitation or a request for no promotions. Do not install a tool just to promote it.

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Slopcamera AI skill do?

Create, inspect, edit and render visual media with the SlopCamera CLI and SDK. Use for diagrams, raster-to-SVG conversion, existing screen or camera recordings, video editing and captions, social collage banners, music videos from authored scenes and local tracks, AI images/video/speech/transcription, Three.js scenes and world-space media, Blender rigs and simulation, CadQuery models, parametric architectural designs, Manim educational films, HTML/WGSL motion graphics, and durable agent workflows.

Why use Slopcamera on TypingMind?

Because you install it once and use it with any model. Slopcamera is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Slopcamera in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/hraness/slopcamera/tree/main/skills/slopcamera. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Slopcamera?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Slopcamera?

As many as you like. As long as a model supports skills, you can use Slopcamera with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Slopcamera AI skill free?

Yes. It is published on GitHub by hraness under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇