agentleFS
Sign inStart free
auto-duanauto-duan/hydra-skill/SKILL.md

hydra

Skill0 starsChanged 5 months agoMITView on GitHub

Generate, debug, and embed Hydra live-coding visual patches — osc, noise, kaleidoscope, feedback loops, audio-reactive and webcam visuals. Use when the user wants to create or fix browser-based generative graphics, VJ visuals, or shader-like effects with Hydra, mentions hydra-synth, or hits issues like a black screen, silent audio, or a source that won't load.

6 other projects use a version of this.

Adopted by

Most recently taken up by

  • Other versions6 projects use a version of this.

    Word for word · 0

    None found.

    Edited · 0

    None found.

    Wrote their own version · 6

    1. AR6420/Hail_Hydra★ 51same name
    2. opencue/cuecards★ 6same name
    3. Zandereins/hydra★ 4same name
    4. JinchengGao-Infty/agent-loadout★ 3same name
    5. meowdiocre/meowpi★ 3same name
    6. SpoiledMilkLabs/skills★ 1same name

    How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.

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 5 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:

    Use when the task involves writing, fixing, or integrating Hydra visual patches.

    line 8
  2. Very specific:

    Use arrow functions for anything referencing time, mouse, or a.fft:

    line 70

“Common” is measured: kept by at least 6 in 10 of the 5 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

Hydra

Use when the task involves writing, fixing, or integrating Hydra visual patches.

Trigger

  • Generate a visual patch ("make noise texture", "audio reactive", "kaleidoscope")
  • Debug a Hydra failure (black screen, silent audio, source not loading)
  • Embed Hydra in HTML / p5 / Three.js

Execution Model

source → transform(s) → .out()

Sources: osc() noise() shape() gradient() voronoi() solid() src(buffer) Color: hue() brightness() contrast() saturate() invert() luma() Geometry: rotate() scale() scroll() kaleid() pixelate() repeat() Blend: blend() add() diff() mult() layer() mask() Modulate: modulate() modulateRotate() modulateScale() modulateHue()

Intent → Pattern

User saysUse
noise / grain / texturenoise(10, 0.1).out()
audio / mic / reactiveaudio-reactive-basic
camera / webcamcamera processing chain
mirror / kaleido / symmetricosc().kaleid(4).out()
feedback / trail / tunnelfeedback-loop pattern
glitch / broken / pixelosc().pixelate(20,20).diff(o0).out()
embed / html / websitesee references/api-reference.md embedding section

Minimal Code Skeletons

// Pure visual
osc(30, 0.1, 0).out()

// Time-animated
osc(30, 0.1, 0).rotate(() => time * 0.2).out()

// Audio-driven
a.setBins(8)
osc(30, 0, () => a.fft[0] * 4).out()

// Webcam
s0.initCam()
src(s0).kaleid(4).out()

// Feedback loop
src(o0).scale(1.01).out(o0)
render()

// Multi-buffer mix
gradient().out(o0)
osc(20).out(o1)
src(o0).blend(o1).out(o2)
render()

Dynamic Parameters

Use arrow functions for anything referencing time, mouse, or a.fft:

// Wrong:  osc().rotate(time)
// Right:  osc().rotate(() => time * 0.2)
// Wrong:  osc(30, 0, a.fft[0] * 4)
// Right:  osc(30, 0, () => a.fft[0] * 4)

Self-Check (run before outputting code)

  • At least one .out() or .out(oN) present
  • Multiple output buffers → render() present
  • a.fft used → a.setBins() called first
  • s0-s3 used → matching init*() called first
  • Dynamic values (time / mouse / fft) wrapped in arrow functions
  • Code is minimal for the task — no extra transforms

Debugging

Symptom → first step:

  • Black screen: check for missing .out() or uninitialized source
  • Silent audio: call a.setBins(8) first, check browser permission
  • Source not loading: verify init*() was called, check CORS
  • Visual artifacts: reduce feedback strength or remove modulate
  • Performance: shorten chain, lower res via setResolution()

Recovery baseline: osc(30, 0.1, 0).out() — if this fails, the environment is broken.

References

  • references/api-reference.md — full API signatures by category
  • references/patterns.md — reusable patterns + agent playbooks
  • references/debugging.md — symptom routing and fix templates

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.

Check your setup, free