Skill UI

This skill enables non-interactive execution of the Antigravity CLI for coding tasks. It involves setting the working directory, checking CLI availability, and running tasks via JSON output format. Users must handle authentication separately and respect permission settings. It parses JSON status fields to determine success or failure. Safety measures include avoiding interactive modes, not handling credentials, and managing file permissions within the workspace. Use this when delegating coding work to Antigravity.

Run Claude Code non-interactively for coding tasks via the claude -p CLI with JSON output. Covers availability checks, timeouts, read-only tool defaults, and safe handling of missing authentication.

Run Codex CLI non-interactively to delegate coding tasks, parse JSONL event output, and enforce safe sandbox and authentication handling.

Run DeepSeek Harness non-interactively to delegate coding tasks to a headless agent. Covers availability checks, timeouts, prompt passing, exit codes, authentication limits, and safe read-only versus write workflows.

Run GitHub Copilot CLI non-interactively to delegate coding tasks. Covers availability checks, JSONL output parsing, and safe tool permission handling.

Run Hermes Agent non-interactively in one-shot mode for local coding tasks. Covers availability checks, timeout limits, exit code meanings, authentication boundaries, and safe workspace scoping.

Run Kimi Code non-interactively in a constrained Bash directory to delegate coding tasks. Covers availability checks, single-prompt JSONL execution, parsing final results, and safe handling of authentication, permissions, and sandbox escalation.

This skill enables non-interactive execution of Qwen Code for coding tasks within the Code Mate environment. It involves setting the working directory, verifying tool availability, and running specific commands with JSON output format. Users should delegate coding work to Qwen Code using this method. Authentication and permissions must be configured properly, avoiding credential exposure. It supports restricted approval behavior and limits tool calls for safety.

This skill rewrites unprofessional code comments into clear, professional documentation while performing safe non-semantic cleanup like whitespace and indentation. It ensures consistent voice without altering logic, behavior, or architecture, suitable for code reviews, open-sourcing, or handoffs.

Orchestrator skill for delegating a bounded coding task to the Command Code CLI implementer, then reviewing its diff and landing the commit yourself. Covers brief writing, dispatch, prerequisites and safety limits.

Execute tasks from a Conductor track implementation plan using a TDD workflow, with pre-flight checks, track selection, context loading, phase verification gates, and safe git commits.

Evaluate, adapt, and safely install Context Kit personal context artifacts for Claude Code or adjacent agent workflows. Includes safety rules, installation review checklist, and best practices for local-first storage.