drost-ai/tinker-ai-skill
Agent Skill for fine-tuning an agentic model on your own Claude Code sessions with Tinker. Works in Claude Code, Codex and OpenCode.
From the publisher
README & documentation
Source previewRead the project’s overview, installation instructions and usage examples. The original README is the source of truth.
Turn your own coding-agent sessions into a fine-tuned model you can run locally. This is the recipe behind Tess-4 and Tess-4.5. [](LICENSE) [](https://agentskills.io) [](#install-the-skill) [](https://thinkingmachines.ai/tinker) Every session you run with a coding agent is a worked example of how you want a model to behave: your repositories, your conventions, your tools, your way of debugging. This skill hands your agent the complete, production-tested pipeline to turn those sessions into a supervised fine-tuning dataset, train a LoRA on Tinker, merge it, and ship a GGUF that runs in llama.cpp on your own machine. One afternoon, a few dollars to a few hundred, and a model that works the way you do. Install it once and say: "fine-tune Qwen3.6-35B-A3B on my Claude Code sessions from the last three months." The agent takes it from there and stops before anything that costs money. We built the Tess family of agentic coding models from…
Read the full README ↗ · Preview checked 2026-11-14T15:16:53.876Z
Inside the original README — Document outline
- tinker-ai-skill
- Proven on real releases
- What you get
- The method, from transcripts to a local model
- Why this and not a generic SFT tutorial
- Quick start: five minutes on synthetic data
- Then on your own sessions
- Install the skill
- What it costs
- Requirements
- Layout
- Data safety
Headings are captured from the source. Links open the publisher’s document, not a locally hosted copy.
Links from the README
References supplied by the publisher, not independently verified endorsements. Check the destination before downloading files or entering credentials.
Documentation belongs to its respective authors. Reported project/model license: MIT. A listing is not a grant of reuse or training rights. Confirm the document’s own terms at the source.
What this repository does
Agent Skill for fine-tuning an agentic model on your own Claude Code sessions with Tinker. Works in Claude Code, Codex and OpenCode.
Repository facts
- Owner
- drost-ai
- Primary language
- Python
- Stars
- 323
- Forks
- 39
- Open issues + pull requests
- 0
- License
- MIT
- Archived
- No
- Default branch
- main
- Created
- 2026-11-07T16:50:04.000Z
- Last push
- 2026-11-07T17:15:54.000Z
Topics and intended use
No topics were included in the latest source metadata.
Review the README for scope, installation, examples and limitations. We do not run repository code or certify it.
Evaluate before installing
Review licensing and dependencies, inspect recent commits and unresolved issues, and test in an isolated environment before production use. Stars and forks alone cannot answer these questions.
Source and freshness
Source: GitHub. Metadata observed 2026-11-14T12:24:55.365Z. Daily imports are snapshots, not real-time monitoring.
Popularity and source listings do not establish security, suitability, licensing rights or benchmark performance.
Related repositories
EbookFoundation/free-programming-books
donnemartin/system-design-primer