
2 results

Automatically announces plans, issues, and summaries out loud using TTS. Use this skill PROACTIVELY after completing major tasks like finalizing a plan, resolving an issue, or generating a summary. Each project gets a unique voice so users can identify which project is speaking from another room. Providers fallback in order (google, openai, elevenlabs, say) on rate limits.

Agentic LLDB fuzzer and crash-triage toolkit for Apple Mach-O on arm64(e). Use this skill whenever a user mentions alf, wants an AI agent to drive LLDB over MCP, asks about triaging a crash on macOS, wants to fuzz a Mach-O target with LLM guidance, is debugging a macOS kernel via Virtualization.framework / KDP / gdb-remote, references `alf analyze`/`alf fuzz`/`alf server`/`alf director`, or needs to wire alf into Claude Code / Codex / Gemini CLI via ACP. Invoke even when the user just describes the task ("I have a crash input from my fuzzer", "I want to break on smb2_rq_decompress_read in the VM kernel", "set up an agent to fuzz this IOKit method") without naming the tool.