hex

Executes agent-enhanced council queries by spawning parallel Claude subagents that each query a provider, evaluate response quality, ask follow-up questions, and return structured insights with confidence ratings and blind spot analysis. Invoked when the --agents flag is used or when complex architectural decisions are detected.

Adds new AI providers to claude-council, configures provider API settings, troubleshoots provider connections, and documents the provider script interface. Covers creating provider shell scripts, setting API keys, and validating connectivity. Triggers on "add provider", "new AI agent", "provider not working", "API configuration", or "extend council".

Executes council queries by running the query pipeline across selected AI providers (Gemini, OpenAI, Grok, Perplexity), displaying formatted responses verbatim, and generating a synthesis of consensus, divergence, and recommendations. Invoked by the ask command during standard (non-agent) council queries.

Generates and edits images using Google Gemini, OpenAI GPT Image, and xAI Grok Image APIs via shell scripts. This skill should be used when the user asks to "generate an image", "create an image", "edit an image", "modify an image", "make a picture", "draw me a", "text to image", "generate with gemini", "generate with openai", "generate with xai", "generate with grok", "gpt image", "gemini image", or "grok image".

This skill should be used when the user asks to "run commands on a remote pane", "check remote pane output", "capture output from remote", "send commands to remote server", "tail logs on prod", "check disk space on staging", "run uptime across servers", "is my SSH connection alive", "read what's on the remote pane", or needs to interact with already-established SSH connections in tmux panes. Also activates when you are about to suggest the user manually SSH into a remote host to run a command, when a command needs to run on a remote machine, when troubleshooting requires executing something on a known remote host, or when you would otherwise tell the user to "run this on the server" or "SSH in and do X". Not for creating new connections (use the /remote command for that).

This skill should be used when a command is blocked by claude-guard, when the response contains "BLOCKED by claude-guard", when the user asks "why was my command blocked", "what commands are blocked", "guard rules", "safety rules", or when Claude is about to execute a potentially dangerous command. Covers git force push, git reset --hard, git checkout --, git clean, git commit --no-verify, rm -rf, chmod 777, DROP TABLE, TRUNCATE, DELETE without WHERE, docker system prune, docker compose down -v, kubectl delete, terraform destroy, aws s3 rm, gh repo delete, Route53 delete, and credential exposure warnings after file writes.