mirror of
https://github.com/NousResearch/hermes-agent.git
synced 2026-05-10 03:22:05 +00:00
98db898c0b
Completes the Windows-gating coverage for the built-in skills/ tree. Every
bundled SKILL.md now carries an explicit platforms: declaration so the
loader (agent.skill_utils.skill_matches_platform) can skip-load skills
that don't fit the current OS.
74 skills declared cross-platform (platforms: [linux, macos, windows]):
Creative (16): ascii-art, ascii-video, architecture-diagram, baoyu-comic,
baoyu-infographic, claude-design, creative-ideation, design-md,
excalidraw, humanizer, manim-video, p5js, pixel-art,
popular-web-designs, pretext, sketch, songwriting-and-ai-music,
touchdesigner-mcp
Autonomous agents: claude-code, codex, hermes-agent, opencode
Data/devops: jupyter-live-kernel, kanban-orchestrator, kanban-worker,
webhook-subscriptions, dogfood, codebase-inspection
GitHub: github-auth, github-code-review, github-issues,
github-pr-workflow, github-repo-management
Media: gif-search, heartmula, songsee, spotify, youtube-content
MCP / email / gaming / notes / smart-home: native-mcp, himalaya,
pokemon-player, obsidian, openhue
mlops (non-broken): weights-and-biases, huggingface-hub, llama-cpp,
outlines, segment-anything-model, dspy, trl-fine-tuning
Productivity: airtable, google-workspace, linear, maps, nano-pdf,
notion, ocr-and-documents, powerpoint
Red-teaming / research: godmode, arxiv, blogwatcher, llm-wiki,
polymarket
Software-dev: debugging-hermes-tui-commands, hermes-agent-skill-authoring,
node-inspect-debugger, plan, requesting-code-review, spike,
subagent-driven-development, systematic-debugging,
test-driven-development, writing-plans
Misc: yuanbao
5 skills gated from Windows (platforms: [linux, macos]):
mlops/inference/vllm (serving-llms-vllm)
vLLM is officially Linux-only; Windows requires WSL.
mlops/training/axolotl
Axolotl's flash-attn + deepspeed + bitsandbytes stack is Linux-first.
mlops/training/unsloth
Requires Triton + xformers + flash-attn — Linux only in practice.
mlops/models/audiocraft (audiocraft-audio-generation)
torchaudio ffmpeg backend + encodec dependencies are Linux-first.
mlops/inference/obliteratus
Research abliteration workflow; relies on Linux-focused pytorch
kernels and MLX — no first-class Windows path.
Same strict-over-lenient policy as the optional-skills sweep: when the
underlying tool's Windows support is rough, missing, or WSL-only, gate the
skill. Easier to un-gate after verified Windows support lands than to leak
partial support that manifests as mid-task failures.
Combined with prior commits in this branch, every bundled SKILL.md
(skills/ + optional-skills/) now has a platforms: declaration.
|
||
|---|---|---|
| .. | ||
| references | ||
| scripts | ||
| templates | ||
| README.md | ||
| SKILL.md | ||
p5.js Skill
Production pipeline for interactive and generative visual art using p5.js.
What it does
Creates browser-based visual art from text prompts. The agent handles the full pipeline: creative concept, code generation, preview, export, and iterative refinement. Output is a single self-contained HTML file that runs in any browser — no build step, no server, no dependencies beyond a CDN script tag.
The output is real interactive art. Not tutorial exercises. Generative systems, particle physics, noise fields, shader effects, kinetic typography — composed with intentional color palettes, layered composition, and visual hierarchy.
Modes
| Mode | Input | Output |
|---|---|---|
| Generative art | Seed / parameters | Procedural visual composition |
| Data visualization | Dataset / API | Interactive charts, custom data displays |
| Interactive experience | None (user drives) | Mouse/keyboard/touch-driven sketch |
| Animation / motion graphics | Timeline / storyboard | Timed sequences, kinetic typography |
| 3D scene | Concept description | WebGL geometry, lighting, shaders |
| Image processing | Image file(s) | Pixel manipulation, filters, pointillism |
| Audio-reactive | Audio file / mic | Sound-driven generative visuals |
Export Formats
| Format | Method |
|---|---|
| HTML | Self-contained file, opens in any browser |
| PNG | saveCanvas() — press 's' to capture |
| GIF | saveGif() — press 'g' to capture |
| MP4 | Frame sequence + ffmpeg via scripts/render.sh |
| SVG | p5.js-svg renderer for vector output |
Prerequisites
A modern browser. That's it for basic use.
For headless export: Node.js, Puppeteer, ffmpeg.
bash skills/creative/p5js/scripts/setup.sh
File Structure
├── SKILL.md # Modes, workflow, creative direction, critical notes
├── README.md # This file
├── references/
│ ├── core-api.md # Canvas, draw loop, transforms, offscreen buffers, math
│ ├── shapes-and-geometry.md # Primitives, vertices, curves, vectors, SDFs, clipping
│ ├── visual-effects.md # Noise, flow fields, particles, pixels, textures, feedback
│ ├── animation.md # Easing, springs, state machines, timelines, transitions
│ ├── typography.md # Fonts, textToPoints, kinetic text, text masks
│ ├── color-systems.md # HSB/RGB, palettes, gradients, blend modes, curated colors
│ ├── webgl-and-3d.md # 3D primitives, camera, lighting, shaders, framebuffers
│ ├── interaction.md # Mouse, keyboard, touch, DOM, audio, scroll
│ ├── export-pipeline.md # PNG, GIF, MP4, SVG, headless, tiling, batch export
│ └── troubleshooting.md # Performance, common mistakes, browser issues, debugging
└── scripts/
├── setup.sh # Dependency verification
├── serve.sh # Local dev server (for loading local assets)
├── render.sh # Headless render pipeline (HTML → frames → MP4)
└── export-frames.js # Puppeteer frame capture (Node.js)