Repoprompt Tool Guidance Refresh
w-winter/dot314
Refresh RepoPrompt tool guidance when the CLI/MCP surface changes.
Synthesize training data for ANY tool-use / agentic benchmark, in ANY repo.
Install Tool Use Data Synthesis
$ npx skills add sunny-glow/Auto-BenchMax --skill tool-use-data-synthesis -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install sunny-glow/Auto-BenchMax tool-use-data-synthesis --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/sunny-glow/Auto-BenchMax.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/tool-use-data-synthesis .claude/skills/tool-use-data-synthesis && 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 "tool-use-data-synthesis" agent skill from https://github.com/sunny-glow/Auto-BenchMax/tree/main/skills/tool-use-data-synthesis into .claude/skills/tool-use-data-synthesis/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "tool-use-data-synthesis", 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/sunny-glow/Auto-BenchMax/tree/main/skills/tool-use-data-synthesisType 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 sunny-glow/Auto-BenchMax --skill tool-use-data-synthesis -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install sunny-glow/Auto-BenchMax tool-use-data-synthesis --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/sunny-glow/Auto-BenchMax.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/tool-use-data-synthesis .agents/skills/tool-use-data-synthesis && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "tool-use-data-synthesis" agent skill from https://github.com/sunny-glow/Auto-BenchMax/tree/main/skills/tool-use-data-synthesis into .agents/skills/tool-use-data-synthesis/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "tool-use-data-synthesis", 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 sunny-glow/Auto-BenchMax --skill tool-use-data-synthesis -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install sunny-glow/Auto-BenchMax tool-use-data-synthesis --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/sunny-glow/Auto-BenchMax.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/tool-use-data-synthesis .cursor/skills/tool-use-data-synthesis && 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 "tool-use-data-synthesis" agent skill from https://github.com/sunny-glow/Auto-BenchMax/tree/main/skills/tool-use-data-synthesis into .cursor/skills/tool-use-data-synthesis/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "tool-use-data-synthesis", 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/sunny-glow/Auto-BenchMax.git --path skills/tool-use-data-synthesis--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 sunny-glow/Auto-BenchMax --skill tool-use-data-synthesis -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install sunny-glow/Auto-BenchMax tool-use-data-synthesis --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/sunny-glow/Auto-BenchMax.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/tool-use-data-synthesis .gemini/skills/tool-use-data-synthesis && 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 "tool-use-data-synthesis" agent skill from https://github.com/sunny-glow/Auto-BenchMax/tree/main/skills/tool-use-data-synthesis into .gemini/skills/tool-use-data-synthesis/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "tool-use-data-synthesis", 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 sunny-glow/Auto-BenchMax tool-use-data-synthesisInstalls 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 sunny-glow/Auto-BenchMax --skill tool-use-data-synthesis -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/sunny-glow/Auto-BenchMax.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/tool-use-data-synthesis .github/skills/tool-use-data-synthesis && 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 "tool-use-data-synthesis" agent skill from https://github.com/sunny-glow/Auto-BenchMax/tree/main/skills/tool-use-data-synthesis into .github/skills/tool-use-data-synthesis/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "tool-use-data-synthesis", 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 sunny-glow/Auto-BenchMax --skill tool-use-data-synthesis -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install sunny-glow/Auto-BenchMax tool-use-data-synthesis --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/sunny-glow/Auto-BenchMax.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/tool-use-data-synthesis .opencode/skills/tool-use-data-synthesis && 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 "tool-use-data-synthesis" agent skill from https://github.com/sunny-glow/Auto-BenchMax/tree/main/skills/tool-use-data-synthesis into .opencode/skills/tool-use-data-synthesis/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "tool-use-data-synthesis", 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
tool-use-data-synthesis- GitHub stars
- 1.3k
- Token cost
- ~3.3k tokens
- SKILL.md length
- 1,398 words
- Files
- 4 (incl. references)
- Skills in repo
- 1
- Repo updated
- First seen
- Licence
- None found
At a glance
Synthesize training data for ANY tool-use / agentic benchmark, in ANY repo.
- Works in 2 steps: The scoring mechanism dictates the… → Distribution alignment is the whole…
- Tasks that involve Structured output and tool calling
- SKILL.md covers Overview, The first decision: read the…, The overriding principle:… and Diagnose from failures: let…, plus 4 more sections
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
Tool Use Data Synthesis is an agent skill from sunny-glow/Auto-BenchMax. Synthesize training data for ANY tool-use / agentic benchmark, in ANY repo. Given a handful of runnable reference tasks, produce thousands of "same-distribution, different-entity" tasks, roll out real trajectories, and emit SFT, RL data. Use this when: you have a tool-calling / MCP / agentic benchmark and want to expand a few dozen tasks into thousands of in-distribution training samples without changing the environment or tools; when synthetic data mysteriously LOWERS the benchmark score and you need to diagnose…
Its SKILL.md is about 3.3k tokens, which your agent loads only when the skill is triggered. The skill folder holds 4 other files, including reference files (for example `references/operational-playbook.md`, `references/paradigm-a-execute-then-extract.md` and `references/paradigm-b-construct-then-verify.md`).
It sits in AI & LLM Engineering, covering Structured output and tool calling and Test data and fixtures. It works with Model Context Protocol.
When your agent uses it
- Tasks that involve Structured output and tool calling
- Tasks that involve Test data and fixtures
Example prompts
- “same-distribution, different-entity”
- “/tool-use-data-synthesis”
Workflow steps
2 steps, taken from the first numbered list in SKILL.md.
- The scoring mechanism dictates the paradigm. Read the evaluator FIRST. It splits the world in
- Distribution alignment is the whole game. Synthetic data that is structurally simpler than
What it can do on your machine
Read from SKILL.md and the folder at commit 8befe78. 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
No scripts in the folder and no shell commands in SKILL.md.
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Tool Use Data Synthesis loads about 3.3k tokens when it runs, and up to ~11k if it reads all its reference files. Until then it costs about 214 tokens; SKILL.md has 1,398 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 1,398 words (~3,332 tokens).
“This skill is a generic recipe for synthesizing training data inside any tool-calling environment, validated end-to-end on two very different benchmarks (one LLM-judged, one rule-based). The concrete goal: you have N runnable benchmark tasks and want to expand them into…”
- name
- tool-use-data-synthesis
Files
SKILL.md and 3 other files (references) in skills/tool-use-data-synthesis of sunny-glow/Auto-BenchMax.
- SKILL.md
- references/operational-playbook.md
- references/paradigm-a-execute-then-extract.md
- references/paradigm-b-construct-then-verify.md
Open the folder on GitHubat commit 8befe78
Compare with similar skills
Tool Use Data Synthesis 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 |
|---|---|---|---|---|---|---|
| Tool Use Data Synthesis this skillsunny-glow/Auto-BenchMax | 1.3k | — | ~3.3k | Automated safety check: Pass | None | |
| Repoprompt Tool Guidance Refreshw-winter/dot314 | 139 | — | ~1.7k | Automated safety check: Pass | MIT | |
| Agent Interface DesignNeeeophytee/finding-unknowns-skills | 344 | — | ~650 | Automated safety check: Pass | MIT | |
| Ax Gendosco/aithy | 107 | — | ~5.4k | Automated safety check: Pass | Apache-2.0 | |
| Perfupraullenchai/Rapid-MLX | 4k | — | ~1.6k | Automated safety check: Notes | Custom licence | |
| Anthropic Product Knowledgesyahiidkamil/Software-Engineer-AI-Agent-Atlas | 401 | 4 repos | ~651 | Automated safety check: Pass | None |
Similar skills
Agent Interface Design
Neeeophytee/finding-unknowns-skills
Design tools, scripts, and CLIs that an agent will call, so the interface teaches its own use instead of a wall of prose and examples.
Ax Gen
dosco/aithy
This skill helps an LLM generate correct AxGen code using @ax-llm/ax.
Perfup
raullenchai/Rapid-MLX
Autonomous performance optimization: research, PoC, benchmark, implement, review, PR
Anthropic Product Knowledge
syahiidkamil/Software-Engineer-AI-Agent-Atlas
Stop and consult this skill whenever your response would include specific facts about Anthropic's products.
Fieldflow CLI
guillaumegay13/fieldflow
Use FieldFlow to inspect and reduce noisy JSON CLI output before it reaches model context.
Related
Works with
Categories
Questions about Tool Use Data Synthesis
What does Tool Use Data Synthesis do?
Synthesize training data for ANY tool-use / agentic benchmark, in ANY repo. Tool Use Data Synthesis is an agent skill from sunny-glow/Auto-BenchMax. Synthesize training data for ANY tool-use / agentic benchmark, in ANY repo.
When should I use Tool Use Data Synthesis?
Tool Use Data Synthesis fits situations like: tasks that involve Structured output and tool calling; tasks that involve Test data and fixtures.
How do I install Tool Use Data Synthesis in Claude Code?
Run `npx skills add sunny-glow/Auto-BenchMax --skill tool-use-data-synthesis -a claude-code`. Or copy the skill folder (skills/tool-use-data-synthesis in sunny-glow/Auto-BenchMax) into .claude/skills/tool-use-data-synthesis in your project. Claude Code loads it when a task matches its description.
How do I install Tool Use Data Synthesis in Codex?
Run `npx skills add sunny-glow/Auto-BenchMax --skill tool-use-data-synthesis -a codex`. Or copy the skill folder (skills/tool-use-data-synthesis in sunny-glow/Auto-BenchMax) into .agents/skills/tool-use-data-synthesis in your project. Codex loads it when a task matches its description.
Can I use Tool Use Data Synthesis 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 sunny-glow/Auto-BenchMax --skill tool-use-data-synthesis -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/tool-use-data-synthesis, .gemini/skills/tool-use-data-synthesis, .github/skills/tool-use-data-synthesis and .opencode/skills/tool-use-data-synthesis in your project.
What does Tool Use Data Synthesis need to run?
SKILL.md names no scripts, command-line tools or credentials: Tool Use Data Synthesis is instructions for the agent only.
Does Tool Use Data Synthesis access the network?
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Is Tool Use Data Synthesis 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 Tool Use Data Synthesis use?
No licence was found for Tool Use Data Synthesis or its repository. Without one, default copyright applies: ask the author before reusing or redistributing it.
How many tokens does Tool Use Data Synthesis use?
About 3.3k tokens (SKILL.md is roughly 13k 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 7.4k tokens, read only when the agent opens those files.
What are the alternatives to Tool Use Data Synthesis?
Skills that share tags, products or a category with Tool Use Data Synthesis: Repoprompt Tool Guidance Refresh (w-winter/dot314, 139 stars), Agent Interface Design (Neeeophytee/finding-unknowns-skills, 344 stars), Ax Gen (dosco/aithy, 107 stars) and Perfup (raullenchai/Rapid-MLX, 4k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Tool Use Data Synthesis?
sunny-glow (a GitHub user) maintains it in sunny-glow/Auto-BenchMax, which has 1,335 GitHub stars. The repository was last updated on July 24, 2026.
Source: sunny-glow/Auto-BenchMax on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.