.claude/skills/deploy-bot/SKILL.md
# Deploy Bot Deploys the bot to Pipecat Cloud using cloud builds. ## Parameters The user specifies the environment as an argument: `/deploy-bot dev` or `/deploy-bot prod`. If not provided, ask which environment to deploy to. - `dev` → config file: `deployment/pcc-deploy.dev.toml` - `prod` → config file: `deployment/pcc-deploy.prod.toml` ## Steps ### 1. Deploy to Pipecat Cloud ```bash pipecat cloud deploy --config-file deployment/pcc-deploy.<env>.toml --yes ``` The `--yes` flag skips all
npx skillsauth add pipecat-ai/gradient-bang .claude/skills/deploy-botInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Deploys the bot to Pipecat Cloud using cloud builds.
The user specifies the environment as an argument: /deploy-bot dev or /deploy-bot prod. If not provided, ask which environment to deploy to.
dev → config file: deployment/pcc-deploy.dev.tomlprod → config file: deployment/pcc-deploy.prod.tomlpipecat cloud deploy --config-file deployment/pcc-deploy.<env>.toml --yes
The --yes flag skips all confirmation prompts. Pipecat Cloud will build the Docker image remotely using the Dockerfile and context specified in the toml file.
Report the result. The deploy command has a 90-second health check window that will often time out with a message like "Deployment did not enter ready state within 90 seconds." This is normal — the deployment was still submitted successfully. Treat this as a successful deploy and report the agent name.
If the build fails, check the build logs using the build ID from the error output:
pipecat cloud build logs <build-id>
deployment/pcc-deploy.dev.toml and deployment/pcc-deploy.prod.toml..dockerignore at the repo root controls what gets included in the build context.testing
# Restore Ship Restores a ship to a healthy state for testing. Clears the `destroyed_at` flag, restocks fighters/shields/warp power to max values from the ship definition, re-adds corporation ships to `corporation_ships` if missing, and recreates the pseudo-character record for corp ships so tasks can be issued. No events are emitted — this is a database-only operation. ## Parameters Ask the user for: - **ship_id**: UUID of the ship to restore (required) ## Steps ### 1. Source environment
development
# Reset World Resets the game database, generates a fresh universe, loads quest definitions, and seeds combat cron config. ## Parameters The user specifies the environment as an argument: `/reset-world local`, `/reset-world dev`, or `/reset-world prod`. If not provided, ask which environment. - `local` → env file: `.env.supabase` - `dev` → env file: `.env.cloud.dev` - `prod` → env file: `.env.cloud` Additional optional parameters (ask if not provided, or use defaults): - **Sector count**: n
devops
# NPC Runs an autonomous AI task agent as a game character. Resolves a character name to its UUID, then launches the `npc-run` script which connects to the game server and executes the given task using a Pipecat + Gemini LLM pipeline. ## Parameters - **character_name** (required): The character's display name (e.g. `JOETRADER`). Passed as the argument to `/npc`. - **task** (required): A natural language description of what the character should do (e.g. "Explore and find 5 new sectors"). If `
data-ai
# Run Database Migration Applies pending Supabase migrations to the local or production database. This skill is strictly additive — it only applies new migrations and NEVER resets, truncates, or drops existing data. ## Safety rules — READ BEFORE PROCEEDING **You MUST follow every rule below. No exceptions.** 1. **NEVER** run `supabase db reset`, `supabase db reset --linked`, or any command that drops/recreates the database. 2. **NEVER** run `DROP TABLE`, `DROP SCHEMA`, `TRUNCATE`, or `DELETE