A standalone skill for training language models to write in any author's style. This is a separate plugin from the main Context Engineering collection.
# Add the marketplace first
/plugin marketplace add muratcankoylan/Agent-Skills-for-Context-Engineering
# Install the book-sft-pipeline plugin
/plugin install book-sft-pipeline@context-engineering-marketplaceCopy SKILL.md to your .rules or project skills folder.
Reference the SKILL.md file directly in your agent's context.
book-sft-pipeline/
├── README.md # This file
├── SKILL.md # Complete skill documentation (standalone)
├── examples/
│ └── gertrude-stein/ # Complete case study with real outputs
│ ├── README.md # Results and analysis
│ ├── sample_outputs.md # Raw model outputs
│ ├── training_config.json
│ ├── dataset_sample.jsonl
│ └── pangram/ # AI detector screenshots
├── scripts/
│ └── pipeline_example.py # Conceptual implementation
└── references/
├── segmentation-strategies.md
├── tinker-format.md
└── tinker.txt
Trained Qwen3-8B-Base on Gertrude Stein's "Three Lives" (1909):
| Metric | Value |
|---|---|
| Training examples | 592 |
| Loss reduction | 97% |
| Pangram AI detector | 70% Human |
| Training time | 15 minutes |
| Total cost | $2 |
This skill applies patterns from the Agent Skills for Context Engineering collection:
| Skill | Application |
|---|---|
| project-development | Staged pipeline architecture |
| context-compression | Segmentation strategy |
| multi-agent-patterns | Orchestrator pattern |
| evaluation | Modern scenario testing |
| context-fundamentals | Prompt diversity |
- Dataset on Hugging Face
- Research Paper (Chakrabarty et al. 2025)
MIT