Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add skills/mxslr/mlcraft/domain-generativenpx skills add mxslr/mlcraft --skill domain-generativegit clone --depth 1 https://github.com/mxslr/mlcraftWhat it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00131 | $0.00492 |
| Opus 5 | $0.00066 | $0.00246 |
| Sonnet 5 | $0.00026 | $0.00098 |
| Haiku 4.5 | $0.00013 | $0.00049 |
Grade A, and why
domain-generative scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
Generative Models - Method Selection
Prefer fine-tuning a strong pretrained base over training from scratch. Use classifier-free guidance for text alignment.
Decision table
| Sub-task | Recommended | Notes |
|---|---|---|
| Text-to-image or general image generation | latent diffusion (Stable Diffusion family, SDXL) | diffusion now beats GANs on quality and diversity. |
| Personalize or customize on a few images | LoRA, DreamBooth, or textual inversion on a diffusion base | parameter-efficient, small data. |
| Fast or real-time, or paired image-to-image | GAN (pix2pix, StyleGAN) or a distilled diffusion model | GANs are faster at inference. |
| Inpainting or super-resolution | diffusion inpainting, Real-ESRGAN | |
| Audio or music generation | diffusion, or a transformer LM over audio tokens |
Cross-cutting practice
- Metrics: FID and KID (fidelity and diversity versus real data), CLIP score (text-image alignment), IS. For personalization, measure subject fidelity and prompt fidelity separately. Automatic metrics are weak proxies, so human evaluation remains essential. Do not judge on a single number.
- Caveats: generated data can carry artifacts, so training a downstream model on synthetic data can hurt. Watch for training-data memorization, plus licensing and safety.
- Explainability: cross-attention maps (which words drove which region) and guidance-scale sweeps.
- Recent bases (2024): SD3 and FLUX text-to-image, plus consistency and distilled models for fast few-step sampling.
- Improve results: use
accuracy-improvement-loop; evaluate withrigorous-evaluation(generation metrics plus human review).
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 2d ago First seen · 25 lines · 131 tokens per session scan A 5c2a52da9270
domain-generative is a skill published in the GitHub repository mxslr/mlcraft (8 stars, last pushed 1mo ago), licensed MIT. It adds 131 tokens to every session and 492 once invoked, about $0.0007 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
albucore-benchmarks
Running Albucore micro-benchmarks under benchmarks/, synthetic router timings, and comparing PyPI releases with uv --no-project. Use when adding benchmarks, comparing performance across versions, or documenting benchmark workflow.
albucore-conventions
Albucore image processing conventions - shapes (H,W,C), dtypes (uint8/float32), benchmark-driven backend routing (OpenCV, NumPy, Torch CPU, LUT, NumKong), tests, and lockfile discipline. Use when implementing or modifying albucore modules, writing tests, or reviewing image-processing code.
performance-optimization
Systematic performance audit for Albucore runtime code. Use whenever implementing, reviewing, profiling, or optimizing atomic image operations, backend routing, reductions, label maps, LUTs, random generation, dtype conversions, allocation-heavy paths, batch or volume kernels, or in-place behavior.
torch-performance-optimization
Optimize or review eager CPU-only Albucore PyTorch runtime paths with benchmark-backed decisions. Use when adding or changing Torch CPU kernels, Tensor/NumPy bridges, Torch backend routing, tensor layouts, allocations, threading, profiling, memory-format candidates, or Torch performance benchmarks.
albucore-public-api
Albucore star-exported API (all), routers vs albucore.functions shims, and dependents such as Albumentations. Use when changing exports, documenting API, or deciding what belongs in package all.
ml-for-aec
Computer vision for buildings, image-to-floorplan, generative ML models, performance prediction, structural analysis ML, energy prediction, natural language to design, and point cloud ML for AEC computational design.