Crush Configuration
charmbracelet/crush
Explains how to configure the Crush coding agent with crushrc or crush.json, covering providers, models, LSPs, MCP servers, hooks, permissions and config precedence.
Evaluates whether the agent selected appropriate MCP tools instead of shell workarounds.
Install Tool Selection
$ npx skills add databricks-solutions/ai-dev-kit --skill tool-selection -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install databricks-solutions/ai-dev-kit tool-selection --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/databricks-solutions/ai-dev-kit.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.test/eval-criteria/tool-selection .claude/skills/tool-selection && 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-selection" agent skill from https://github.com/databricks-solutions/ai-dev-kit/tree/main/.test/eval-criteria/tool-selection into .claude/skills/tool-selection/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "tool-selection", 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/databricks-solutions/ai-dev-kit/tree/main/.test/eval-criteria/tool-selectionType 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 databricks-solutions/ai-dev-kit --skill tool-selection -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install databricks-solutions/ai-dev-kit tool-selection --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/databricks-solutions/ai-dev-kit.git skills-src && mkdir -p .agents/skills && cp -r skills-src/.test/eval-criteria/tool-selection .agents/skills/tool-selection && 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-selection" agent skill from https://github.com/databricks-solutions/ai-dev-kit/tree/main/.test/eval-criteria/tool-selection into .agents/skills/tool-selection/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "tool-selection", 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 databricks-solutions/ai-dev-kit --skill tool-selection -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install databricks-solutions/ai-dev-kit tool-selection --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/databricks-solutions/ai-dev-kit.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/.test/eval-criteria/tool-selection .cursor/skills/tool-selection && 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-selection" agent skill from https://github.com/databricks-solutions/ai-dev-kit/tree/main/.test/eval-criteria/tool-selection into .cursor/skills/tool-selection/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "tool-selection", 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/databricks-solutions/ai-dev-kit.git --path .test/eval-criteria/tool-selection--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 databricks-solutions/ai-dev-kit --skill tool-selection -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install databricks-solutions/ai-dev-kit tool-selection --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/databricks-solutions/ai-dev-kit.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/.test/eval-criteria/tool-selection .gemini/skills/tool-selection && 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-selection" agent skill from https://github.com/databricks-solutions/ai-dev-kit/tree/main/.test/eval-criteria/tool-selection into .gemini/skills/tool-selection/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "tool-selection", 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 databricks-solutions/ai-dev-kit tool-selectionInstalls 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 databricks-solutions/ai-dev-kit --skill tool-selection -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/databricks-solutions/ai-dev-kit.git skills-src && mkdir -p .github/skills && cp -r skills-src/.test/eval-criteria/tool-selection .github/skills/tool-selection && 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-selection" agent skill from https://github.com/databricks-solutions/ai-dev-kit/tree/main/.test/eval-criteria/tool-selection into .github/skills/tool-selection/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "tool-selection", 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 databricks-solutions/ai-dev-kit --skill tool-selection -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install databricks-solutions/ai-dev-kit tool-selection --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/databricks-solutions/ai-dev-kit.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/.test/eval-criteria/tool-selection .opencode/skills/tool-selection && 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-selection" agent skill from https://github.com/databricks-solutions/ai-dev-kit/tree/main/.test/eval-criteria/tool-selection into .opencode/skills/tool-selection/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "tool-selection", 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-selection- GitHub stars
- 1.9k
- Token cost
- ~519 tokens
- SKILL.md length
- 224 words
- Files
- 2 (incl. references)
- Skills in repo
- 5
- Repo updated
- First seen
- Licence
- Custom licence
At a glance
Evaluates whether the agent selected appropriate MCP tools instead of shell workarounds.
- Works in 5 steps: MCP Over Bash → Correct Tool for Task → No Shell Workarounds → …
- Tasks that involve MCP servers
- Calls databricks
What it does
Tool Selection is an agent skill from databricks-solutions/ai-dev-kit. Evaluates whether the agent selected appropriate MCP tools instead of shell workarounds. Load when the trace contains Bash tool calls that could have used MCP tools, or when evaluating tool call efficiency.
Its SKILL.md is about 520 tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files, including reference files (for example `references/MCP_TOOL_GUIDE.md`).
It sits in Agent Workflows, covering MCP servers. It works with Bash, Databricks, Model Context Protocol and SQL. The repository describes itself as: Databricks Toolkit for Coding Agents provided by Field Engineering.
When your agent uses it
- Tasks that involve MCP servers
Example prompts
- “Use the tool-selection skill to evaluate whether the agent selected appropriate MCP tools instead of shell workarounds”
- “/tool-selection”
Requirements
- Python 3
Workflow steps
5 steps, taken from the step headings in SKILL.md.
- MCP Over Bash
- Correct Tool for Task
- No Shell Workarounds
- Reasonable Call Count
- Error Recovery
What it can do on your machine
Read from SKILL.md and the folder at commit b059fd0. 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:
databricks
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 Selection loads about 519 tokens when it runs, and up to ~1.1k if it reads all its reference files. Until then it costs about 55 tokens; SKILL.md has 224 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
Its licence (Custom licence) doesn't allow us to republish the file, so here is its outline and opening line. It has 224 words (~519 tokens).
“When evaluating tool selection in agent traces:”
- name
- tool-selection
- metadata.category
- evaluation
- metadata.version
- 1.0
Files
SKILL.md and 1 other file (references) in .test/eval-criteria/tool-selection of databricks-solutions/ai-dev-kit.
- SKILL.md
- references/MCP_TOOL_GUIDE.md
Open the folder on GitHubat commit b059fd0
Compare with similar skills
Tool Selection 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 Selection this skilldatabricks-solutions/ai-dev-kit | 1.9k | — | ~519 | Automated safety check: Pass | Custom licence | |
| Crush Configurationcharmbracelet/crush | 29k | — | ~3.7k | Automated safety check: Pass | Custom licence | |
| Record Demoapify/mcpc | 981 | — | ~3.3k | Automated safety check: Notes | Apache-2.0 | |
| Releasejgravelle/jcodemunch-mcp | 2.7k | — | ~6.5k | Automated safety check: Pass | Custom licence | |
| Mcpcapify/mcpc | 981 | — | ~3.5k | Automated safety check: Pass | Apache-2.0 | |
| Meridian MCPMeridiona/meridian | 405 | — | ~967 | Automated safety check: Notes | Custom licence |
Similar skills
- Official
Record Demo
apify/mcpc
Record or regenerate the mcpc demo GIFs (the README hero docs/images/mcpc-demo.gif and the focused tapes in docs/vhs/) with VHS.
Release
jgravelle/jcodemunch-mcp
Publishing a jMunch release (jcodemunch-mcp, jdocmunch-mcp, jdatamunch-mcp, jragmunch-cli), reviewing/merging/closing PRs, and responding to the community.
- Official
Mcpc
apify/mcpc
Use the mcpc CLI to work with MCP (Model Context Protocol) servers from the shell - connect to a server as a persistent session, then list and call tools, read resources, get prompts, and run async…
Meridian MCP
Meridiona/meridian
Build, configure, and debug the Meridian MCP server. An agent skill from Meridiona/meridian.
Orchard
okooo5km/Skills4U
Use the local Orchard app to interact with macOS Apple apps and services: Calendar, Reminders, Clock, Mail, Contacts, Notes, Music, Weather, Messages, Location/Maps, and Apple Shortcuts.
More from databricks-solutions/ai-dev-kit
Skill Test
databricks-solutions/ai-dev-kit
Testing framework for evaluating Databricks skills. An agent skill from databricks-solutions/ai-dev-kit.
Python Dev
databricks-solutions/ai-dev-kit
Python development guidance with code quality standards, error handling, testing practices, and environment management.
SQL Correctness
databricks-solutions/ai-dev-kit
SQL evaluation criteria for Databricks. An agent skill from databricks-solutions/ai-dev-kit.
General Quality
databricks-solutions/ai-dev-kit
General response quality evaluation. An agent skill from databricks-solutions/ai-dev-kit.
Related
Works with
Categories
Questions about Tool Selection
What does Tool Selection do?
Evaluates whether the agent selected appropriate MCP tools instead of shell workarounds. Tool Selection is an agent skill from databricks-solutions/ai-dev-kit. Evaluates whether the agent selected appropriate MCP tools instead of shell workarounds.
When should I use Tool Selection?
Tool Selection fits situations like: tasks that involve MCP servers.
How do I install Tool Selection in Claude Code?
Run `npx skills add databricks-solutions/ai-dev-kit --skill tool-selection -a claude-code`. Or copy the skill folder (.test/eval-criteria/tool-selection in databricks-solutions/ai-dev-kit) into .claude/skills/tool-selection in your project. Claude Code loads it when a task matches its description.
How do I install Tool Selection in Codex?
Run `npx skills add databricks-solutions/ai-dev-kit --skill tool-selection -a codex`. Or copy the skill folder (.test/eval-criteria/tool-selection in databricks-solutions/ai-dev-kit) into .agents/skills/tool-selection in your project. Codex loads it when a task matches its description.
Can I use Tool Selection 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 databricks-solutions/ai-dev-kit --skill tool-selection -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-selection, .gemini/skills/tool-selection, .github/skills/tool-selection and .opencode/skills/tool-selection in your project.
What does Tool Selection need to run?
Going by SKILL.md and its folder, Tool Selection needs the command-line tools its instructions call (databricks). Our summary lists: Python 3.
Does Tool Selection 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 Selection 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 Selection use?
Tool Selection has a licence file (the repository's licence) that doesn't match a standard licence. Read it on GitHub before reusing the skill.
How many tokens does Tool Selection use?
About 519 tokens (SKILL.md is roughly 2.1k 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 567 tokens, read only when the agent opens those files.
What are the alternatives to Tool Selection?
Skills that share tags, products or a category with Tool Selection: Crush Configuration (charmbracelet/crush, 29k stars), Record Demo (apify/mcpc, 981 stars), Release (jgravelle/jcodemunch-mcp, 2.7k stars) and Mcpc (apify/mcpc, 981 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Tool Selection?
databricks-solutions (a GitHub organization) maintains it in databricks-solutions/ai-dev-kit, which has 1,938 GitHub stars. The repository holds 5 skills in this directory. The repository was last updated on August 13, 2026.
Source: databricks-solutions/ai-dev-kit on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.