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 skills add roedyrustam/vibes-plug --skill synthetic-data-finetuning-expertgit clone --depth 1 https://github.com/roedyrustam/vibes-plugWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/roedyrustam/vibes-plug/synthetic-data-finetuning-expert)<a href="https://agentmods.dev/skills/roedyrustam/vibes-plug/synthetic-data-finetuning-expert"><img src="https://agentmods.dev/badge/skills/roedyrustam/vibes-plug/synthetic-data-finetuning-expert/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/roedyrustam/vibes-plug/synthetic-data-finetuning-expert"><img src="https://agentmods.dev/badge/skills/roedyrustam/vibes-plug/synthetic-data-finetuning-expert.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What 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 5.1 | $0.00080 | $0.02334 |
| Opus 5.5 | $0.00032 | $0.00934 |
| Sonnet 5.5 | $0.00016 | $0.00467 |
| Haiku 4.5 | $0.00008 | $0.00233 |
Grade A, and why
synthetic-data-finetuning-expert 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 6d 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.
How it starts
The opening of the file, as written. The whole thing — 198 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Synthetic Data & Fine-Tuning Expert (Custom Domain SLMs)
English
Orchestration & Integration
- Local SLM & Quantization:
local-slm-edge-ai-expert,wasm-edge-computing-expert - FinOps & Cost Optimization:
llm-finops-router,adaptive-model-cascade,ai-llm-integration-expert - Prompting & Evals:
ai-prompt-engineering-expert,structured-output-contracts,ai-safety-governance-expert - Python Pipelines & Tools:
python-programming-expert,data-pipeline-etl-expert - Lifecycle & Governance:
zero-to-prod-orchestrator,session-memory-manager,anti-slop
Description
Production-grade guide for generating synthetic training datasets, curating high-signal instruction pairs, executing Parameter-Efficient Fine-Tuning (QLoRA / LoRA) with Unsloth and Hugging Face TRL, performing Direct Preference Optimization (DPO), and quantizing custom Small Language Models (SLMs) to GGUF for edge or on-premise execution.
Swarm Synergy: Within the AI Engineering Swarm, this skill serves as the Model Specialization Lead. When frontier API costs or latency become prohibitive, it trains, aligns, and deploys hyper-efficient domain SLMs (1B–8B parameters) in Phase 4.
Trigger Conditions
- Generating domain-specific synthetic training data from seed documents, codebases, or APIs.
- Filtering low-quality or hallucinated synthetic data using LLM-as-a-judge curation pipelines.
- Fine-tuning open-weights models (Llama 3.3, Qwen 2.5, Mistral) on custom tasks using 4-bit QLoRA.
- Aligning model outputs using Direct Preference Optimization (DPO) to enforce specific response styles.
- Quantizing fine-tuned models to GGUF (q4_k_m, q8_0) for zero-latency local inference with Ollama or llama.cpp.
Synthetic Data & Fine-Tuning Lifecycle
1. SEED EXTRACTION & SYNTHESIS
[Raw Docs / Codebase] ──► [Frontier LLM / Distilabel] ──► Raw Instruction Pairs (10k+)
2. QUALITY FILTERING (LLM-AS-A-JUDGE)
Raw Instruction Pairs ──► [Rubric Scorer / De-duplication] ──► Curated Gold Dataset (2k-5k)
3. 4-BIT QLORA FINE-TUNING (UNSLOTH)
Base Model (e.g. Qwen 2.5-Coder) + LoRA Adapters ──► SFT / DPO Training Loop
4. QUANTIZATION & LOCAL DEPLOYMENT
Merged 16-bit Weights ──► [llama.cpp GGUF Export] ──► Local Ollama Service (<50ms latency)
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.
- 6d ago Changed · +8 lines bf9b32a779c9
- 7d ago Changed · +1 lines c8f7aab2894c
- 10d ago Changed · +33 lines fc54c2dc7b34
- 19d ago Changed e5275a2226ee
- 24d ago Changed cdb6583aa6ea
- 25d ago Changed b7faddff8575
- 27d ago Changed · -6 lines · +62 tokens per session 2d5e8e55f400
- 29d ago Changed · +6 lines · -62 tokens per session 5022ed4ef7d4
- 1mo ago Changed e102e2bc17d8
- 1mo ago First seen · 156 lines · 80 tokens per session scan A 6d3badcde398
synthetic-data-finetuning-expert is a skill published in the GitHub repository roedyrustam/vibes-plug (115 stars, last pushed yesterday), licensed MIT. It adds 80 tokens to every session and 2,334 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-09-12.
Other skills, from other repositories
pytorch
Expert PyTorch deep learning assistance covering dynamic tensors, autograd, torch.compile, distributed training (DDP), and GPU acceleration. Use when training neural networks and deploying AI research.
scikit-learn
Expert Scikit-Learn assistance covering classification, regression, clustering, pipelines, cross-validation, and preprocessing. Use when building classical machine learning models and feature engineering pipelines.
dask
Expert Dask distributed computing assistance covering Dask DataFrames, Arrays, Futures, and cluster scaling. Use when analyzing datasets too large for pandas on a single machine or multi-node cluster.
pytorch-patterns
PyTorch deep learning patterns and best practices for building robust, efficient, and reproducible training pipelines, model architectures, and data loading.
pytorch-patterns
PyTorch deep learning patterns and best practices for building robust, efficient, and reproducible training pipelines, model architectures, and data loading.
accelerate
Run PyTorch training across GPUs with minimal changes.