agentleFS
rakaarwakyrakaarwaky/agents-arwaky/skills/media-content/ascii-video/SKILL.md

ascii-video

Skill0 starsChanged 7 days agoMITView on GitHub

ASCII video: convert video/audio to colored ASCII MP4/GIF.

17 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use songwriting-and-ai-music, teams-meeting-pipeline and 2 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.
  • Tommy-ywSkill

    songwriting-and-ai-music

    Songwriting craft, AI music generation prompts (Suno focus), parody/adaptation techniques, phonetic tricks, and lessons learned. These are tools and ideas, not rules. Break any of them when the art calls for it.

    Also in 6 projects that use this

  • john-data-chenSkill

    teams-meeting-pipeline

    Operate the Teams meeting summary pipeline via Hermes CLI — summarize meetings, inspect pipeline status, replay jobs, manage Microsoft Graph subscriptions.

    Also in 4 projects that use this

  • Tommy-ywSkill

    maps

    Location intelligence — geocode a place, reverse-geocode coordinates, find nearby places (46 POI categories), driving/walking/cycling distance + time, turn-by-turn directions, timezone lookup, bounding box + area for a named place, and POI search within a rectangle. Uses OpenStreetMap + Overpass + OSRM. Free, no API key.

    Also in 5 projects that use this

  • browser-useSkill

    manim-video

    Production pipeline for mathematical and technical animations using Manim Community Edition. Creates 3Blue1Brown-style explainer videos, algorithm visualizations, equation derivations, architecture diagrams, and data stories. Use when users request: animated explanations, math animations, concept visualizations, algorithm walkthroughs, technical explainers, 3Blue1Brown style videos, or any programmatic animation with geometric/mathematical content.

    Also in 5 projects that use this

The file

We split this skill into the rules it gives an agent

2 rules. 0 are common, 1 is distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 17 edited versions we read keep these.

  • 1

    Distinctive

    This author's own choices. Worth a look.

  • 1

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Per-section variation: Never use one config for the whole video — vary background effect, character palette, color strategy, and shader …

    line 16
  2. Very specific:

    Completion: Test frames at key timestamps pass the brightness check (canvas.mean() > 8) and the creative vision check against …

    line 19

“Common” is measured: kept by at least 6 in 10 of the 17 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

ASCII Video Production Pipeline

You build a single self-contained Python renderer per project and pipe it through the 6-stage pipeline INPUT → ANALYZE → SCENE_FN → TONEMAP → SHADE → ENCODE to produce colored ASCII character video (MP4, GIF, image sequence). No GPU required. Six input modes (video-to-ASCII, audio-reactive, generative, hybrid, lyrics/text, TTS narration) route to references/inputs.md and references/effects.md; the 4-step build sequence is in references/workflow.md.

Global rules

  • Creative standard. This is visual art — ASCII characters are the medium, cinema is the standard. Articulate the creative concept before writing code; the output must be visually striking on the first render (full rubric in references/creative-standard.md).
  • Adaptive tonemap only. ASCII on black is inherently dark — use adaptive tonemap(), never canvas * N multipliers (implementation notes in references/implementation-notes.md).
  • Per-section variation. Never use one config for the whole video — vary background effect, character palette, color strategy, and shader intensity per scene/section.
  • Invent, don't just pick. The effect, shader, and palette catalogs are a starting vocabulary; every project includes at least one custom palette, effect, or visual moment.
  • Single-file renderer. One self-contained Python script per project: NumPy + Pillow + ffmpeg CLI, with SciPy for audio modes; hardware-detect a quality profile before building.
  • Completion. Test frames at key timestamps pass the brightness check (canvas.mean() > 8) and the creative vision check against references/creative-standard.md; output matches the selected mode's shape (MP4, GIF, or image sequence).

Routing

StepReferencePurpose
Workflowreferences/workflow.md4-step build sequence: creative vision, technical design, script component order, quality verification.
Creative standardreferences/creative-standard.mdCreative rubric: first-render excellence, proactively creative, cohesive aesthetic, dense/layered, per-section variation, project-specific invention.
Pipeline architecturereferences/architecture.md6-stage pipeline, grid system, resolution presets, font selection, character palettes, color system (HSV + OKLAB + discrete RGB + harmony), _render_vf(), GridLayer.
Compositionreferences/composition.md20 pixel blend modes, blend_canvas(), multi-grid composition, adaptive tonemap(), FeedbackBuffer, PixelBlendStack, masking/stencil system.
Effectsreferences/effects.mdEffect building blocks: value field generators, hue fields, noise/fBM/domain warp, voronoi, reaction-diffusion, cellular automata, SDFs, strange attractors, particle systems, coordinate transforms, temporal coherence.
Shadersreferences/shaders.mdShaderChain, _apply_shader_step() dispatch, 38-shader catalog, audio-reactive scaling, transitions, tint presets, output format encoding, terminal rendering.
Scenesreferences/scenes.mdScene protocol, Renderer class, SCENES table, render_clip(), beat-synced cutting, parallel rendering, scene design patterns, worked examples, design checklist.
Inputs (all 6 modes)references/inputs.mdMode table + audio analysis (FFT, bands, beats), video sampling, image conversion, text/lyrics, TTS integration (ElevenLabs, voice assignment, audio mixing).
Optimizationreferences/optimization.mdHardware detection, quality profiles, vectorized patterns, parallel rendering, memory management, performance budgets.
Troubleshootingreferences/troubleshooting.mdNumPy broadcasting traps, blend mode pitfalls, multiprocessing/pickling, brightness diagnostics, ffmpeg issues, font problems, common mistakes.
Critical notesreferences/implementation-notes.mdtonemap() code, font cell height (macOS), ffmpeg pipe deadlock, font compatibility, per-clip architecture, performance budgets.
Creative divergencereferences/creative-divergence.mdUse only when the user requests experimental/creative/unique output: Forced Connections, Conceptual Blending, Oblique Strategies.

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.