fabis94

First example skill for add-skill tests

Second example skill with a non-kebab name

Validate uac's assumptions about supported AI tools (Claude Code, Copilot, Cursor, etc.) against current upstream documentation and produce a written report of drift — renamed fields, new events, deprecated features, schema changes — so the user can plan follow-up changes. Does not modify source code.

Import existing AI tool configurations (from Claude, Copilot, Cursor, or Codex) into universal-ai-config templates. Converts target-specific files into universal templates.

Draft a pull request description from either the current chat session or the full feature branch (committed + uncommitted). Use when the user asks to write a PR description, prep a PR, or summarize changes for review.

Create, update, or manage universal-ai-config agent templates. Handles finding existing agents, deciding whether to create or modify, and writing the template.

Create, update, or manage AI configuration templates. Analyzes what the user needs and delegates to the appropriate template-specific skill.

Create, update, or manage universal-ai-config hook templates. Handles finding existing hooks, deciding whether to create or modify, and writing the template.

Generate a Product Requirements Document for a new feature. Use when planning a feature, starting a new project, or asked to create a PRD. Triggers on: create a prd, write prd for, plan this feature, requirements for, spec out.

Convert an existing PRD into prd.json format for Ralph autonomous agent execution. Use when you have a PRD and want to run it through the Ralph loop. Triggers on: convert this prd, turn this into ralph format, create prd.json, ralph json.

Update the fabis-ralph-loop.config.ts configuration file. Use when adding backpressure commands, changing container settings, updating project metadata, or modifying any Ralph loop config. Triggers on: update ralph config, add backpressure command, change container settings, modify ralph-loop config.

Create, update, or manage universal-ai-config MCP server templates. Handles finding existing configs, deciding whether to create or modify, and writing the template.

Check, build, and publish the package to npm with pnpm

Create a new git release with changelog generation and GitHub release

Import existing AI tool configurations (from Claude, Copilot, or Cursor) into universal-ai-config templates. Converts target-specific files into universal templates.

Audit a codebase scope for tech debt, generate a prioritized refactoring plan. Covers dead code, complexity hotspots, DRY violations, dependency health, type safety gaps, test coverage, architecture/coupling issues, security smells, and naming/readability problems. Outputs an actionable plan at the requested detail level — from high-level subtasks for a ralph loop to precise file-and-function changes for immediate execution.

Update project documentation after feature changes. Uses conversation context and optional dev pointers to update repo guide, README, extension description, and in-app help modal. Invoke after implementing user-visible changes.

Audit a codebase scope for tech debt, generate a prioritized refactoring plan. Covers dead code, complexity hotspots, DRY violations, dependency health, type safety gaps, test coverage, architecture/coupling issues, security smells, and naming/readability problems. Outputs an actionable plan at the requested detail level — from high-level subtasks to precise file-and-function changes for immediate execution.

Scan the codebase for unused files, dependencies, and exports using Knip and clean them up