Menu

Individual skill

tools

Add studio-owned MCP tools, prompts, app-record resources or signed inbound integrations to a Homie studio, sell goods or priced services to customers' AIs, declare event functions, and connect an AI through browser approval.

plugins/homie-rocks/homie/skills/tools/SKILL.md

Read pinned source

Source commit d780783eba4ecc7c8b9429f95c9362df95f07c61

What was checked

Matches the observed repository HEAD
Yes
Scanner rules are current
Yes
Repository scan complete
No
Skill scan complete
No
Observed behavior
Network or broad shell
Last checked
Nov 4, 2026

These are observations at the recorded commit, not a guarantee of safety. Review the source before running it.

Install this skill

Choose an agent in your Stack or copy a command below. Commands fetch the pinned commit and copy only this skill directory. Existing destinations are refused. Copying a command does not install anything.

An install command is unavailable: current rules, complete repository and skill scans, an eligible behavior level and a permitted license are required.

Repository context

Repository stars (not skill ratings)
1,532
Repository last updated
Nov 6, 2026
License
Apache-2.0

Observed agent integration: No specific integration evidence. Standard SKILL.md installation does not imply verified compatibility.

Files and excerpt

File metadata and permitted, redacted excerpts come from the recorded scan. Source links are pinned to that commit.

Browse files
Read excerpt

# A studio's own tools

Read `node_modules/@homie-rocks/studio/tools/TOOLS.md` first. Use this skill when an
AI needs to perform a business action, read app records, join a room, or expose a
small integration. Reuse built-ins before adding code. A tool should name a useful
operation such as "finish this job", not expose arbitrary SQL, shell or secrets.

Run `homie-studio tool new <name> --app <id>` for an app operation, or omit `--app`
for studio-wide work. Declare an explicit audience, bounded JSON schema and useful
description. Use `context.records` so the app's validation, grants and versions
remain authoritative. Never trust a role in model input. Review every imported
part as trusted Worker code. Never return credentials or raw environment bindings.

Build and run locally. Test valid calls, bad input, anonymous refusal, the intended