Add Pipeline
verl-project/verl-omni
Router for adding a diffusion or omni pipeline to verl-omni.
Fine-tune LLMs using the Tinker API. An agent skill from sundial-org/skills.
Install Tinker
$ npx skills add sundial-org/skills --skill tinker -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install sundial-org/skills tinker --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/sundial-org/skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/tinker .claude/skills/tinker && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "tinker" agent skill from https://github.com/sundial-org/skills/tree/main/skills/tinker into .claude/skills/tinker/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "tinker", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/sundial-org/skills/tree/main/skills/tinkerType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add sundial-org/skills --skill tinker -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install sundial-org/skills tinker --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/sundial-org/skills.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/tinker .agents/skills/tinker && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "tinker" agent skill from https://github.com/sundial-org/skills/tree/main/skills/tinker into .agents/skills/tinker/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "tinker", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add sundial-org/skills --skill tinker -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install sundial-org/skills tinker --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/sundial-org/skills.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/tinker .cursor/skills/tinker && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "tinker" agent skill from https://github.com/sundial-org/skills/tree/main/skills/tinker into .cursor/skills/tinker/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "tinker", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/sundial-org/skills.git --path skills/tinker--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add sundial-org/skills --skill tinker -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install sundial-org/skills tinker --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/sundial-org/skills.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/tinker .gemini/skills/tinker && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "tinker" agent skill from https://github.com/sundial-org/skills/tree/main/skills/tinker into .gemini/skills/tinker/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "tinker", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install sundial-org/skills tinkerInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add sundial-org/skills --skill tinker -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/sundial-org/skills.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/tinker .github/skills/tinker && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "tinker" agent skill from https://github.com/sundial-org/skills/tree/main/skills/tinker into .github/skills/tinker/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "tinker", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add sundial-org/skills --skill tinker -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install sundial-org/skills tinker --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/sundial-org/skills.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/tinker .opencode/skills/tinker && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "tinker" agent skill from https://github.com/sundial-org/skills/tree/main/skills/tinker into .opencode/skills/tinker/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "tinker", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
tinker- GitHub stars
- 152
- Token cost
- ~1.2k tokens
- SKILL.md length
- 199 words
- Files
- 10 (incl. references)
- Skills in repo
- 13
- Repo updated
- First seen
- Licence
- None found
At a glance
Fine-tune LLMs using the Tinker API. An agent skill from sundial-org/skills.
- Tasks that involve Fine-tuning
- SKILL.md covers Overview, Quick Reference, Installation and Minimal Example, plus 3 more sections
- Calls pip; needs TINKER_API_KEY
- Tasks that involve Reinforcement learning
What it does
Tinker is an agent skill from sundial-org/skills. Fine-tune LLMs using the Tinker API. Covers supervised fine-tuning, reinforcement learning, LoRA training, multimodal models including Thinking Machines' Inkling (vision, audio, thinking effort), and both high-level Cookbook patterns and low-level API usage.
Its SKILL.md is about 1.2k tokens, which your agent loads only when the skill is triggered. The skill folder holds 10 other files, including reference files (for example `references/api-reference.md`, `references/getting-started.md` and `references/inkling.md`).
It sits in AI & LLM Engineering, covering Fine-tuning, Reinforcement learning and Diffusion and image models. The repository describes itself as: Claude Code Skills by Sundial.
When your agent uses it
- Tasks that involve Fine-tuning
- Tasks that involve Reinforcement learning
- Tasks that involve Diffusion and image models
Example prompts
- “/tinker”
Requirements
- Python 3
- A credential in TINKER_API_KEY
What it can do on your machine
Read from SKILL.md and the folder at commit 5a3bf9f. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
Shell commands in SKILL.md call:
pip
From the folder's file list and the shell code blocks in SKILL.md.
Network
Links to these hosts (documentation or services it may open):
tinker-docs.thinkingmachines.aigithub.comtinker-console.thinkingmachines.ai
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names these keys or tokens, usually read from environment variables:
TINKER_API_KEY
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Tinker loads about 1.2k tokens when it runs, and up to ~14k if it reads all its reference files. Until then it costs about 66 tokens; SKILL.md has 199 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
SKILL.md
Without a licence we can't republish the file, so here is its outline and opening line. It has 199 words (~1,235 tokens).
“Tinker is a training API for large language models from Thinking Machines Lab. It provides:”
- name
- tinker
Files
SKILL.md and 9 other files (references) in skills/tinker of sundial-org/skills.
- SKILL.md
- references/api-reference.md
- references/getting-started.md
- references/inkling.md
- references/loss-functions.md
- references/models-and-lora.md
- references/recipes.md
- references/reinforcement-learning.md
- references/rendering.md
- references/supervised-learning.md
Open the folder on GitHubat commit 5a3bf9f
Compare with similar skills
Tinker next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Tinker this skillsundial-org/skills | 152 | — | ~1.2k | Automated safety check: Pass | None | |
| Add Pipelineverl-project/verl-omni | 1.2k | — | ~1k | Automated safety check: Pass | Apache-2.0 | |
| Train RlOpenPipe/ART | 11k | — | ~2.4k | Automated safety check: Pass | Apache-2.0 | |
| Qwopus27b Rl TrainingR6410418/Jackrong-llm-finetuning-guide | 1.7k | — | ~830 | Automated safety check: Pass | Apache-2.0 | |
| Fine Tuning With TrlOrchestra-Research/AI-Research-SKILLs | 13k | 6 repos | ~2.9k | Automated safety check: Pass | MIT | |
| Optim AgentOptim-Agent/optim-agent | 801 | — | ~1.3k | Automated safety check: Pass | MIT |
Similar skills
Train Rl
OpenPipe/ART
RL training reference for the ART framework. An agent skill from OpenPipe/ART.
Qwopus27b Rl Training
R6410418/Jackrong-llm-finetuning-guide
Prepare, validate, launch-plan, monitor, resume, and stop configurable Qwopus 27B reinforcement-learning workflows for GRPO or GSPO.
Fine Tuning With Trl
Orchestra-Research/AI-Research-SKILLs
Fine-tune LLMs using reinforcement learning with TRL - SFT for instruction tuning, DPO for preference alignment, PPO/GRPO for reward optimization, and reward model training.
Optim Agent
Optim-Agent/optim-agent
A skill your agent uses when the user wants to optimize configurable system parameters against a measurable scalar objective, especially for model training, inference, quantitative strategies…
Safactory Workflows
AI45Lab/SAfactory
Integrate a benchmark or custom environment into SAfactory using fixed adapter templates and local contract tests, optionally run Docker/RJob evaluation, or prepare GRPO/RL training.
More from sundial-org/skills
All 13 skills in this repoAI Co Scientist
sundial-org/skills
Transform Claude Code into an AI Scientist that orchestrates research workflows using tree-based hypothesis exploration.
Skill
sundial-org/skills
Find, install, create, improve, and publish AI agent skills through the Sundial ecosystem.
Skill To Card
sundial-org/skills
End-to-end workflow that creates a skill from a description and attached files, publishes it to Sundial as a private skill, generates a trading card (front + back with QR code), and sends it to a…
Commit Splitter
sundial-org/skills
Split large sets of uncommitted changes into logical, well-organized commits.
Tinker Training Cost
sundial-org/skills
Calculate training costs for Tinker fine-tuning jobs. An agent skill from sundial-org/skills.
Codex
sundial-org/skills
Run OpenAI's Codex CLI agent in non-interactive mode using codex exec.
Related
Categories
Questions about Tinker
What does Tinker do?
Fine-tune LLMs using the Tinker API. An agent skill from sundial-org/skills. Tinker is an agent skill from sundial-org/skills. Fine-tune LLMs using the Tinker API.
When should I use Tinker?
Tinker fits situations like: tasks that involve Fine-tuning; tasks that involve Reinforcement learning; tasks that involve Diffusion and image models.
How do I install Tinker in Claude Code?
Run `npx skills add sundial-org/skills --skill tinker -a claude-code`. Or copy the skill folder (skills/tinker in sundial-org/skills) into .claude/skills/tinker in your project. Claude Code loads it when a task matches its description.
How do I install Tinker in Codex?
Run `npx skills add sundial-org/skills --skill tinker -a codex`. Or copy the skill folder (skills/tinker in sundial-org/skills) into .agents/skills/tinker in your project. Codex loads it when a task matches its description.
Can I use Tinker in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add sundial-org/skills --skill tinker -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/tinker, .gemini/skills/tinker, .github/skills/tinker and .opencode/skills/tinker in your project.
What does Tinker need to run?
Going by SKILL.md and its folder, Tinker needs the command-line tools its instructions call (pip) and credentials named TINKER_API_KEY. Our summary lists: Python 3; A credential in TINKER_API_KEY.
Does Tinker access the network?
SKILL.md names 3 domains. As links in the text: tinker-docs.thinkingmachines.ai, github.com and tinker-console.thinkingmachines.ai. This is read from the text; nothing was executed.
Is Tinker safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
What licence does Tinker use?
No licence was found for Tinker or its repository. Without one, default copyright applies: ask the author before reusing or redistributing it.
How many tokens does Tinker use?
About 1.2k tokens (SKILL.md is roughly 4.9k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 13k tokens, read only when the agent opens those files.
What are the alternatives to Tinker?
Skills that share tags, products or a category with Tinker: Add Pipeline (verl-project/verl-omni, 1.2k stars), Train Rl (OpenPipe/ART, 11k stars), Qwopus27b Rl Training (R6410418/Jackrong-llm-finetuning-guide, 1.7k stars) and Fine Tuning With Trl (Orchestra-Research/AI-Research-SKILLs, 13k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Tinker?
sundial-org (a GitHub organization) maintains it in sundial-org/skills, which has 152 GitHub stars. The repository holds 13 skills in this directory. The repository was last updated on July 15, 2026.
Source: sundial-org/skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.