Update to Preset CLI Skills

{
  "description": "Drive Preset's `sup` CLI (PyPI package `superset-sup`) for shell, scripting, CI/CD, and agent-driven Preset workflows. Use only for CLI workflows; Do not use for MCP-only work or for direct HTTP/SDK code paths.",
  "included_files": [
    {
      "relative_path": "references/asset-filter-matrix.md",
      "size_in_bytes": 1338
    },
    {
      "relative_path": "references/assets-read.md",
      "size_in_bytes": 2522
    },
    {
      "relative_path": "references/cli-vs-api.md",
      "size_in_bytes": 3325
    },
    {
      "relative_path": "references/command-coverage.md",
      "size_in_bytes": 5162
    },
    {
      "relative_path": "references/command-examples.md",
      "size_in_bytes": 786
    },
    {
      "relative_path": "references/config-precedence.md",
      "size_in_bytes": 1699
    },
    {
      "relative_path": "references/install-and-auth.md",
      "size_in_bytes": 3102
    },
    {
      "relative_path": "references/output-formats.md",
      "size_in_bytes": 2633
    },
    {
      "relative_path": "references/safety-policy.md",
      "size_in_bytes": 5312
    },
    {
      "relative_path": "references/saved-query-reads.md",
      "size_in_bytes": 758
    },
    {
      "relative_path": "references/sql-and-query.md",
      "size_in_bytes": 2476
    },
    {
      "relative_path": "references/sql-data-safety.md",
      "size_in_bytes": 2057
    },
    {
      "relative_path": "references/workspace-and-config.md",
      "size_in_bytes": 3584
    }
  ],
  "name": "preset-cli",
  "skill_md_contents": "---\nname: preset-cli\ndescription: Drive Preset's `sup` CLI (PyPI package `superset-sup`) for shell, scripting, CI/CD, and agent-driven Preset workflows. Use only for CLI workflows; Do not use for MCP-only work or for direct HTTP/SDK code paths.\n---\n\n# preset-cli\n\nUse as the foundation for shell, scripting, CI/CD, and agent-driven Preset workflows through the `sup` CLI.\n\n## Always\n\n- CLI surface only; stay on MCP or direct API if that's what the user requested.\n- Default to `--json` for automation and agent consumption.\n- Keep `SUP_PRESET_API_TOKEN` / `SUP_PRESET_API_SECRET` out of command lines and shared output; use env vars or `sup config auth`, never paste secrets on the command line.\n- Route push, sync, overwrite, and `--force` to `preset-cli-mutations`.\n- Redact tokens and credential-bearing output in transcripts.\n\n## Decision Rules\n\n- Classify CLI vs MCP vs direct API intent before acting; if MCP or direct API was requested, defer to that plugin.\n- Run metadata reads and explicitly requested data-returning reads (e.g. `sup sql`, `sup chart data`) on familiar workspaces directly with bounded output; for `sup sql`, this direct path requires a pure single-statement `SELECT`. Load safety policy before mutations, SQL that is not a pure single-statement `SELECT`, untrusted-source SQL, unfamiliar workspaces, or broad outputs.\n- Choose output format based on the downstream consumer: `--json` for automation, `--csv` for files, default Rich for humans, `--porcelain` for shell pipelines.\n- If a command group is not named on this card, load command coverage before composing commands.\n- For mutating intent, stop and load `preset-cli-mutations` rather than continuing on this card. Non-`SELECT` SQL is confirmation-gated by the safety policy even when it is pasted by the user for a familiar workspace.\n\n## Workflow Order\n\n1. Establish install, auth, and workspace context.\n2. Choose output format.\n3. Classify risk (metadata read vs data-returning read vs mutation).\n4. Load the focused reference for the operation.\n5. Run only the safe / read command.\n6. Redact output before sharing.\n\n## Retrieve\n\n- Install, entry points, OAuth, env vars: [references/install-and-auth.md](references/install-and-auth.md)\n- Config precedence and source resolution: [references/config-precedence.md](references/config-precedence.md)\n- Workspace selection and `--workspace-id` override: [references/workspace-and-config.md](references/workspace-and-config.md)\n- Registered command coverage and routing: [references/command-coverage.md](references/command-coverage.md)\n- Output formats and exit behavior: [references/output-formats.md](references/output-formats.md)\n- Asset read/export entity scope: [references/assets-read.md](references/assets-read.md)\n- Asset list filter matrix: [references/asset-filter-matrix.md](references/asset-filter-matrix.md)\n- Ad-hoc SQL routing: [references/sql-and-query.md](references/sql-and-query.md)\n- SQL/data-returning read safety: [references/sql-data-safety.md](references/sql-data-safety.md)\n- Saved query reads: [references/saved-query-reads.md](references/saved-query-reads.md)\n- Detailed command examples: [references/command-examples.md](references/command-examples.md)\n- CLI vs API routing decision: [references/cli-vs-api.md](references/cli-vs-api.md)\n- Approval gates and credential redaction: [references/safety-policy.md](references/safety-policy.md)\n"
}