agent-creator
Mode: Script-First - Use scripts/main.cjs as the canonical path for generation and validation, then use this guide for research, skill assignment, and integration follow-through.
Agent Creator Skill
Creates specialized AI agents on-demand for capabilities that do not already have a good owner.
When This Skill Is Triggered
- The router finds no suitable existing agent.
- The user explicitly asks for a new agent.
- A capability gap requires a persistent specialist rather than a one-off task.
Reference Docs
- Occupational alignment details - preserved router notes, trigger guidance, companion checks, domain research, and occupational-alignment fetch details.
- Research and skills-gap details - preserved keyword research, skill discovery, configuration notes, and the full template contract reference.
- Integration reference - preserved validation, routing-table, registry, memory, README, and ecosystem-integration guidance.
- Examples and evaluation - preserved workflow integration notes, ecosystem alignment contract, examples, assertions, and optional eval add-ons.
More from oimiragieo/agent-studio
gcloud-cli
Google Cloud CLI operations and resource management
966pyqt6-ui-development-rules
PyQt6 desktop GUI development rules -- signal/slot architecture, QSS theming, QThread concurrency, layout management, and cross-platform rendering. Enforces MVC separation and responsive UI patterns.
575filesystem
File system operations guidance - read, write, search, and manage files using Claude Code's built-in tools.
360chrome-browser
Browser automation with two integrations - Chrome DevTools MCP (always available, performance tracing) and Claude-in-Chrome extension (authenticated sessions, GIF recording). Use DevTools for testing/debugging, Claude-in-Chrome for authenticated workflows.
304slack-notifications
Slack messaging, channels, and notifications - send messages, manage channels, interact with users, upload files, and add reactions. Use for team communication, incident notifications, and workflow alerts.
251context-compressor
Compress large context before reasoning to reduce token usage while preserving evidence. Use this whenever the user mentions huge files, long prompts, RAG payloads, prompt caching, expensive sessions, codebase context, chat history compaction, or wants the same answer quality with fewer tokens.
147