Update to PlanetScale

{
  "name": "pscale-cli-automation",
  "description": "Use the PlanetScale CLI (pscale) from automated agents with --format json, auth check, pscale sql, and per-command --force. Run before other PlanetScale skills when driving pscale directly. Use when the user asks to automate pscale, run CLI commands headless, or verify pscale auth from an agent.",
  "included_files": [],
  "skill_md_contents": "---\nname: pscale-cli-automation\ndescription: >-\n  Use the PlanetScale CLI (pscale) from automated agents with --format json,\n  auth check, pscale sql, and per-command --force. Run before other PlanetScale\n  skills when driving pscale directly. Use when the user asks to automate\n  pscale, run CLI commands headless, or verify pscale auth from an agent.\n---\n\n# PlanetScale CLI automation\n\n## Purpose\n\nTeach agents how to invoke `pscale` non-interactively. This skill covers **CLI\nconventions only**. Operational workflows (inventory, safety review, schema\nrecommendations) use the other skills in this repo — start with\n`../safe-orchestrator/SKILL.md` for a full assessment.\n\n## Two AGENTS.md files (do not confuse them)\n\n| Document | Where | Purpose |\n|----------|-------|---------|\n| **CLI agent guide** | Shipped with `pscale` (`AGENTS.md` in the CLI repo, or `pscale agent-guide`) | How to call `pscale`: auth, `--format json`, flag placement, `pscale sql` |\n| **Project agent guide** | Your application repository's `AGENTS.md` | Which org, database, branch, engine, prod branch, MCP scope, approval rules |\n\nDo not edit project `AGENTS.md` without operator approval (see\n`../mcp-agent-operating-model/SKILL.md`).\n\n## Bootstrap (always start here)\n\n```bash\npscale agent-guide --format json\npscale auth check --format json\n```\n\nIf `auth check` returns `\"status\": \"action_required\"`, follow `issues` and\n`next_steps` in the JSON. For login, the human may need to approve in the\nbrowser; use `pscale auth login --format json`.\n\n## Conventions\n\n- Always pass **`--format json`** for automation.\n- Put **`--org <org>`** on resource subcommands (`database`, `branch`, `sql`,\n  `api`, …) — not on root `pscale`.\n- Put **positional arguments before flags** (`pscale sql mydb main --org bb …`).\n- Use **`pscale sql`**, not `pscale shell` (shell requires a TTY).\n- Default SQL role is **reader**; pass `--role admin` (or writer/readwriter) for\n  writes. Match `pscale shell` semantics for `--role` and `--replica`.\n- **`--force`** is per subcommand only (e.g. `database delete … --force`, `pscale\n  sql … --force`). There is no global `--force` or `PSCALE_FORCE`.\n- **`--format json` alone never skips confirmations** — add `--force` on the\n  destructive subcommand after explicit user approval.\n\n## Typical workflow\n\n```bash\npscale auth check --format json\npscale org list --format json\npscale database list --org <org> --format json\npscale branch list <database> --org <org> --format json\npscale sql <database> <branch> --org <org> --format json --query \"SELECT 1\"\n```\n\nMySQL uses `@primary` by default (same as `pscale shell`); pass `--keyspace` only\nfor multi-keyspace databases.\n\n## MCP vs CLI\n\n- **MCP clients** — use the hosted PlanetScale MCP server (see `pscale agent-guide\n  --format json` for the current URL).\n- **Shell scripts and coding agents** — use `pscale` with `--format json` as above.\n\n## When this skill is not enough\n\nInstall the full PlanetScale skills pack (if not already):\n\n```sh\ngit clone https://github.com/planetscale/skills.git && cd skills && script/setup\n# or: npx skills add planetscale/skills -g -y\n```\n\nThen run sub-skills or `../safe-orchestrator/SKILL.md` for database operations\nbeyond basic CLI invocation.\n\n## Current conventions source of truth\n\nPrefer live output over memorized flag syntax:\n\n```bash\npscale agent-guide --format json\n```\n\nThe embedded `guide` field contains the full CLI agent guide shipped with your\n`pscale` binary.\n"
}