Tinker AI Skill

Turn your own coding-agent session transcripts (Claude Code JSONL) into a supervised fine-tuning dataset and train a LoRA on Tinker with the tinker-cookbook. Use when the user wants to fine-tune a model on their agent sessions, build an SFT dataset from transcripts, anonymize or de-identify transcripts, slice long sessions to a context length with compaction context, or train and evaluate on Tinker. Covers collection, cleaning (secrets, PII, paths), chunking, train/val splits, training, sampling, and the pitfalls that cost us runs.

325 stars 39 forksAI, LLMs & Agents

Install

skills CLI (Claude Code, Cursor, Codex and more)
npx skills add drost-ai/tinker-ai-skill --skill tinker-ai-skill
Manual install
git clone --depth 1 https://github.com/drost-ai/tinker-ai-skill.git /tmp/tinker-ai-skill
mkdir -p ~/.claude/skills
cp -r /tmp/tinker-ai-skill/. ~/.claude/skills/tinker-ai-skill

Personal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.

From the SKILL.md

# Fine-tune a coding model on your own agent transcripts (Tinker)

You are helping someone turn the sessions they already ran with a coding agent into
training data, and fine-tune an open model on it with [Tinker](https://thinkingmachines.ai/tinker).
This skill distils a pipeline that shipped several public models. Follow the steps
in order; each script is small, offline unless stated, and prints what it did.

All commands below run from this skill's directory (`tinker-ai-skill`). Read `references/` when a step
needs judgement; the scripts' docstrings (`python scripts/<name>.py --help`) explain
every flag.

## Before you start

1. **Keep the transcripts.** Claude Code deletes transcripts after 30 days by default.
   Tell the user to add `"cleanupPeriodDays": 3650` to `~/.claude/settings.json` now.
2. **Keys.** Copy `.env.example` to `.env` and fill in `TINKER_API_KEY`
   (console at tinker.thinkingmachines.ai) and `WANDB_API_KEY` (wandb.ai/authorize).
   Never print, commit, or paste these values anywhere; the scripts read `.env`.
3. **Environment.** `uv venv && uv pip install -r requirements.txt` (or `pip install -r requirements.txt`).
   Python 3.11+. Use that interpreter for every script.
4. **Budget.** Training costs tokens x price. Always run a script's default (offline)
   mode first; only `--train`, `sample_checkpoint.py` and `export_checkpoint.py` touch
   the service. Confirm the estimated cost with the user before launching.
Read the full skill on GitHub

Details

Skill name
tinker-ai-skill
License
MIT
Repo updated
7 November 2026

FAQ

What does the Tinker AI Skill skill do?

Turn your own coding-agent session transcripts (Claude Code JSONL) into a supervised fine-tuning dataset and train a LoRA on Tinker with the tinker-cookbook. Use when the user wants to fine-tune a model on their agent sessions, build an SFT dataset from transcripts, anonymize or de-identify transcripts, slice long sessions to a context length with compaction context, or train and evaluate on Tinker. Covers collection, cleaning (secrets, PII, paths), chunking, train/val splits, training, sampling, and the pitfalls that cost us runs.

How do I install the Tinker AI Skill skill?

skills CLI (Claude Code, Cursor, Codex and more): npx skills add drost-ai/tinker-ai-skill --skill tinker-ai-skill. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.

Is Tinker AI Skill popular?

It lives in drost-ai/tinker-ai-skill, which has 325 GitHub stars and 39 forks.

Related skills

Writing for Agents

559

KunoLu/640-skills

Writing documents for agents. Use when creating or editing skills, or modifying AGENTS.md or CLAUDE.md.

AI, LLMs & Agents13

On Device Verification

499

google-ai-edge/litert-samples

Prove a converted or quantized LiteRT model on the actual device via the CompiledModel API - confirm GPU residency, compare device output against the source model, and diagnose device-only failures such as silent CPU fallback, whole-graph compile ceilings, and fp16 range breaks. Use after conversion or quantization, when device output is wrong or NaN, when a clean graph fails to compile only on device, or when GPU and CPU outputs are suspiciously identical.

AI, LLMs & Agents134

China 3 Statement Model

896

jwangkun/claude-for-financial-services-cn

Three-statement financial model for A-share stocks. Adapts the standard 3-statement-model methodology for Chinese accounting standards (CAS), Chinese GAAP differences, and AkShare-sourced financials. Use instead of the original 3-statement-model skill when building integrated IS/BS/CF models for Chinese listed companies.

AI, LLMs & Agents143

Litert Google Tensor

499

google-ai-edge/litert-samples

Compiles LiteRT (.tflite) models ahead-of-time for Google Tensor TPUs (Tensor G5 on Pixel 10, Tensor G6 on Pixel 11) locally on Linux x86_64 or remotely via Google Colab (--colab on macOS, Windows, or ARM hosts), benchmarks them on a USB-attached Pixel with LiteRT's benchmark_model (NPU latency, peak memory, TPU tile time, TPU energy, optional CPU baseline), and packages compiled models for an Android Gradle app as a Google Play AI pack with the Tensor NPU runtime module and a Kotlin loader, applies it to the app and verifies it on a Pixel. Use when the user asks to compile, AOT-compile, or pr

AI, LLMs & Agents134

China AI Readiness

896

jwangkun/claude-for-financial-services-cn

Assess an A-share portfolio company's AI readiness for China-focused private equity investments. Evaluates data infrastructure, technology stack, talent, and AI adoption opportunities in the Chinese market context. Triggers on "A股公司AI评估", "AI readiness China", "AI assessment portfolio company", "AI转型评估", or "artificial intelligence readiness [company]".

AI, LLMs & Agents143

Litert Compiled Model Migration

499

google-ai-edge/litert-samples

Rapidly migrate an Android application from legacy TensorFlow Lite (TFLite) to the modern LiteRT CompiledModel API (2.x) in Open Source GitHub repositories, keeping the TensorFlow Lite Support Library as LiteRT Support (litert-support 2.3.0). Covers buffer reuse, NPU JIT compilation, a reference implementation, and a two-stage verification gate (compile check, then an on-device parity test against a golden output).

AI, LLMs & Agents134

Browse the most popular Claude skills, all ai, llms & agents skills, or write your own with the skills generator.