tinker
Skills for fine-tuning language models with the Tinker API — research, debugging, and more.
Plugin bundle · by Thinking Machines Lab
About
tinker is a plugin bundle for AI coding tools published by Thinking Machines Lab. Marketplaces we read that list it: 1 (Community GitHub marketplaces). The last change we recorded was on 2026-11-12. As of our marketplace pass on 2026-11-13.
What it asks for
- Installs as a plugin bundle
None of the marketplaces we read publishes its tools or the settings it asks for.
What it declares, asks for and runs, in full
Only install plugins from developers you trust. We list what marketplaces publish and do not test plugins.
Works with
- Claude Code
From the marketplaces that list it and the MCP transport it declares, as each client documents them. We do not test plugins.
Connect
Commands and configs built only from what its marketplaces declare. We do not run them for you and do not test plugins.
As a Claude Code plugin
Built from what Community GitHub marketplaces declares.
/plugin marketplace add thinking-machines-lab/tinker-cookbook
/plugin install tinker@tinker-skillsWhere it is published
| Marketplace | Status | Version | Figures | Verified | First seen |
|---|---|---|---|---|---|
| Community marketplace thinking-machines-lab/tinker-cookbook (Open the source on GitHub) | Listed | 0.3.0 | Forks (GitHub): 557 Stars (GitHub): 4 253 |
Not marked |
Each figure is the marketplace's own and is never added up across marketplaces. A marketplace that publishes no figure shows none: no number is not zero.
Listed in one community marketplace
| Marketplace | Repository | Stars (GitHub) |
|---|---|---|
| tinker-skills | thinking-machines-lab/tinker-cookbook | 4 253 |
How its figures have moved
- 2026-11-10557
- 2026-11-13557
- 2026-11-104.2k
- 2026-11-124.3k
- 2026-11-134.3k
Each dot is a day we read a different number; flat stretches are days the number did not move. Figures of different marketplaces are never added up.
What the bundle contains
As published on Community GitHub marketplaces.
Skills: 4
debuginklingresearchrollout-ui
What changed
- Became a product we track
- Community GitHub marketplaces: appeared
Similar plugins
Products whose own names, descriptions, tools and skills are closest in meaning to this one, on every marketplace we read. Closeness is ranked within this list only.
-
LLM Fine-tuning Engineer — LLM fine-tuning — PEFT/LoRA, RLHF, instruction tuning, prompt optimization
-
prompt-engineering
Agents specialized in prompt engineering and AI interaction. Focuses on effective prompt design and AI model optimization.
-
evaluation
LLM benchmarking and evaluation including lm-evaluation-harness, BigCode Evaluation Harness, and NeMo Evaluator. Use when benchmarking models or measuring performance.
-
Connect to Hugging Face Hub and thousands of Gradio AI Applications
-
Claude model selection advisor — recommends optimal model for each task via shell hook. Zero attack surface.
-
Tools, skills, and CLI extensions for designing and productionizing LLM inference pipelines. Pattern-guided, slim by default, eval-first.
-
dspy
Optimize and build programmatic prompt systems with Stanford DSPy. Signatures, modules (Predict, ChainOfThought, ReAct), optimizer/teleprompter selection, compilation, caching…
-
unsloth
Install, operate, and troubleshoot Unsloth Core, Studio, and Desktop for local inference and model training. Use for Unsloth environment setup, LoRA/QLoRA supervised fine-tuning…
-
Agents specialized in prompt engineering and AI interaction. Focuses on effective prompt design and AI model optimization.
-
LLM application development, prompt engineering, and AI assistant optimization
Similar plugins by marketplace
The same question asked of one marketplace at a time: is there an analog of this plugin there?
Has a listing on Claude Code: claude-plugins-community (5)
-
Claude model selection advisor — recommends optimal model for each task via shell hook. Zero attack surface.
-
together-ai-skills
A collection of skills that teach coding agents how to use the Together AI platform, including chat completions, image generation, video, audio, embeddings, fine-tuning, batch…
-
Plan tasks with optimal model routing to minimize token usage. Breaks work into steps, assigns each the right model (Haiku/Sonnet/Opus), adds quality gates between stages…
-
Build, train, evaluate, and use open source AI models, datasets, and spaces.
-
Autonomous experiment loop for Claude Code. Run an endless optimize-measure-keep/discard cycle on any optimization target: LLM training loss, test speed, bundle size, build time…
Has a listing on Claude Code: claude-plugins-official (5)
-
Build, train, evaluate, and use open source AI models, datasets, and spaces.
-
Agent Skills for Together AI platform — inference, training, embeddings, audio, video, images, function calling, and infrastructure. Covers serverless chat completions…
-
Output.ai workflow development toolkit for Claude Code. Adds 5 specialist agents (planner, builder, debugger, prompt writer, quality reviewer), 40+ slash-command skills covering…
-
Skills for adding DeepEval evaluations, tracing, datasets, Confident AI reports, and iterative improvement loops to AI applications.
-
Build, train, and deploy AI models with deep AWS AI/ML expertise brought directly into your coding assistants, covering the surface area of Amazon SageMaker AI.
Has a listing on Claude: knowledge-work-plugins (5)
-
Skills for working with Langfuse, the open-source LLM engineering platform for tracing, prompt management, and evaluation.
-
DataRobot skills for AI/ML workflows — model training, deployment, predictions, feature engineering, monitoring, explainability, data preparation, App Framework CI/CD, and…
-
AI-first project auditor and re-engineer based on the 9 design principles and 7 design patterns from the TechWolf AI-First Bootcamp
-
Build multimodal AI applications with Pixeltable -- tables, computed columns, embedding search, UDFs, tool-calling agents, and 25+ AI provider integrations.
-
MCP server for terminal commands, file operations, and process management
Has a listing on Codex: openai-curated (openai/plugins) (5)
-
Build with OpenAI APIs, Agents SDK, and ChatGPT Apps, and create and save OpenAI API keys from Codex.
-
Evaluate Codex skills and plugins from chat with a beginner-friendly start command, local-first reports, token budget explanations, and guided benchmarking.
-
Skills for NVIDIAs ecosystem spans GPU acceleration, CUDA, AI agents, inference, robotics, Physical AI, Omniverse, and simulation. This plugin helps you understand the pieces…
-
AI-powered code review in Codex, powered by CodeRabbit.
-
An agentic skills framework & software development methodology that works: planning, TDD, debugging, and collaboration workflows.
Has a listing on Community GitHub marketplaces (5)
-
LLM Fine-tuning Engineer — LLM fine-tuning — PEFT/LoRA, RLHF, instruction tuning, prompt optimization
-
prompt-engineering
Agents specialized in prompt engineering and AI interaction. Focuses on effective prompt design and AI model optimization.
-
evaluation
LLM benchmarking and evaluation including lm-evaluation-harness, BigCode Evaluation Harness, and NeMo Evaluator. Use when benchmarking models or measuring performance.
-
Tools, skills, and CLI extensions for designing and productionizing LLM inference pipelines. Pattern-guided, slim by default, eval-first.
-
dspy
Optimize and build programmatic prompt systems with Stanford DSPy. Signatures, modules (Predict, ChainOfThought, ReAct), optimizer/teleprompter selection, compilation, caching…
Has a listing on Copilot CLI: github/awesome-copilot (5)
-
Run a lightweight, role-separated AI development team with flexible tools, developer-selected models, proportionate planning, and optional QA.
-
Multi-model council for Copilot CLI: three subagents on different model families (Anthropic, OpenAI, Google) answer independently, then build on each other or attack the leading…
-
Task Researcher and Task Planner for intermediate to expert users and large codebases - Brought to you by microsoft/edge-ai
-
Plain-English translation layer for non-technical Copilot CLI users. Translates every approval prompt, error message, and technical output into clear, jargon-free English with…
-
Meta prompts that help you discover and generate curated GitHub Copilot agents, instructions, prompts, and skills.
Has a listing on Copilot CLI: github/copilot-plugins (5)
-
Toolkit for building Microsoft 365 Copilot declarative agents — scaffolding, JSON manifest development, and capability configuration.
-
Bring Azure DevOps work-item, repository, and pull-request workflows into GitHub Copilot.
-
model-apps
Build and deploy Power Apps generative pages for model-driven apps with specialist agents for planning, entity creation, and parallel code generation. Requires PAC CLI >= 2.7.0…
-
Advanced Security plugin for GitHub Copilot.
-
workiq
Query Microsoft 365 data with natural language — emails, meetings, documents, Teams messages, and more.
Has a listing on Cursor: cursor/plugins (5)
-
Iterative self-referential AI loops using the Ralph Wiggum technique.
-
Incremental transcript-driven memory updates for AGENTS.md using high-signal bullet points only.
-
Consult a stronger model before major decisions, when stuck, and before declaring done.
-
Build apps, scripts, and automations with the TypeScript SDK.
-
Generate presentations, documents, and webpages.
Has a listing on Docker MCP Catalog (5)
-
Tools for interacting with Hugging Face models, datasets, research papers, and more.
-
Read and score Opik traces, experiments, datasets and prompts from your AI assistant.
-
Bridges multiple AI models and CLIs, enabling orchestrated workflows across Claude Code, Gemini CLI, Codex CLI, and other AI development tools.
-
Provides tools to search and retrieve Google Gemini API documentation.
-
Sequential Thinking (Reference)
Dynamic and reflective problem-solving through thought sequences.
Has a listing on Official MCP Registry (5)
-
Connect to Hugging Face Hub and thousands of Gradio AI Applications
-
claude-prompt-optimizer io.github.rishiatlan/claude-prompt-optimizer
Scores, compiles & optimizes prompts for any LLM. Zero AI calls inside. Freemium.
-
Local-first MCP server for versioning, searching, evaluating, and improving AI prompts.
-
Onde Inference CLI: Fine-tune & Deploy Local LLMs
MCP server to fine-tune LoRA, export GGUF, and deploy local LLMs on Onde Inference.
-
Compare text LLMs across OpenRouter, Bedrock, Vertex AI and Foundry with automated grading.
Has a listing on PyPI (MCP servers) (5)
-
Read and score Opik traces, experiments, datasets and prompts from your AI assistant.
-
local-delegate io.github.ZahiriNatZuke/local-delegate
Delegate mechanical text tasks to a local OpenAI-compatible LLM to save Claude quota.
-
offline-mcp io.github.gabrielmahia/offline-mcp
Local AI over Ollama for low connectivity: status, local inference, model and deployment guides.
-
Let one coding-agent CLI consult another: Codex, Claude Code, OpenCode, Copilot or Antigravity.
-
Read, measure and explain LLM eval runs of a digline suite. Cannot promote a baseline.
Has a listing on npm registry (MCP servers) (5)
-
Alibaba Cloud DashScope — Qwen
Alibaba Cloud DashScope MCP: Qwen chat, embeddings, and model discovery on your own account.
-
rubber-duck io.github.nesquikm/rubber-duck
Bridge to multiple LLMs and CLI agents: councils, debates, voting, and more
-
Intelligent CLI tool with AI-powered model selection that analyzes your hardware and recommends optimal LLM models for your system
-
gemini io.github.houtini-ai/gemini
Model Context Protocol server for Google Gemini AI with chat, research, and grounding
-
claude-prompts-mcp io.github.minipuft/claude-prompts-mcp
Reusable prompt templates, multi-step workflow chains, and quality gates for any MCP client.
Found by meaning, not by shared code or a shared repository: similar plugins stay separate products, and this is not a review or a recommendation.
Want this mark on your plugin in our catalog?
Prove you maintain it with a file in its repository, a file on your domain or a DNS record, and you can show this mark on the card, with live banners for your site and README. How verification works
You also get alerts when a marketplace lists it, drops it, changes its verified mark or what it asks for, and its remote endpoint goes on monitoring as a web service.
Data comes from public marketplace files in GitHub repositories of their authors. Figures come from our own regular passes over the marketplaces, last read on . We publish no contact details for plugin publishers.