Claude Cursor GitHub Copilot Skill

preset-cli

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.

LLM Mart · 0 points · 2 views 0 listing impressions 0 install-command copies
Download preset-io-agent-skills-plugins_preset-cli-skills_skills_preset-cli-73d2674.zip · 18 KB

Install

skills CLI npx skills add https://github.com/preset-io/agent-skills/tree/master/plugins/preset-cli-skills/skills/preset-cli
Claude Code claude plugin marketplace add https://llmmart.ai/marketplace.json && claude plugin install preset-io-agent-skills@llmmart
Git git clone https://github.com/preset-io/agent-skills.git

The skills CLI installs just this skill, for any of its supported agents. Claude Code installs the whole preset-io/agent-skills collection as a plugin from our marketplace. Git is the plain clone.

Skill manifest

preset-cli

Use as the foundation for shell, scripting, CI/CD, and agent-driven Preset workflows through the sup CLI.

Always

  • CLI surface only; stay on MCP or direct API if that's what the user requested.
  • Default to --json for automation and agent consumption.
  • 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.
  • Route push, sync, overwrite, and --force to preset-cli-mutations.
  • Redact tokens and credential-bearing output in transcripts.

Decision Rules

  • Classify CLI vs MCP vs direct API intent before acting; if MCP or direct API was requested, defer to that plugin.
  • 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.
  • Choose output format based on the downstream consumer: --json for automation, --csv for files, default Rich for humans, --porcelain for shell pipelines.
  • If a command group is not named on this card, load command coverage before composing commands.
  • 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.

Workflow Order

  1. Establish install, auth, and workspace context.
  2. Choose output format.
  3. Classify risk (metadata read vs data-returning read vs mutation).
  4. Load the focused reference for the operation.
  5. Run only the safe / read command.
  6. Redact output before sharing.

Retrieve

Files (agent-skills)
  • references
    • asset-filter-matrix.md 1.3 KB
      Loading…
    • assets-read.md 2.5 KB
      Loading…
    • cli-vs-api.md 3.2 KB
      Loading…
    • command-coverage.md 5 KB
      Loading…
    • command-examples.md 786 B
      Loading…
    • config-precedence.md 1.7 KB
      Loading…
    • install-and-auth.md 3 KB
      Loading…
    • output-formats.md 2.6 KB
      Loading…
    • safety-policy.md 5.2 KB
      Loading…
    • saved-query-reads.md 758 B
      Loading…
    • sql-and-query.md 2.4 KB
      Loading…
    • sql-data-safety.md 2 KB
      Loading…
    • workspace-and-config.md 3.5 KB
      Loading…
  • SKILL.md 3.3 KB
    ---
    name: preset-cli
    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.
    ---
    
    # preset-cli
    
    Use as the foundation for shell, scripting, CI/CD, and agent-driven Preset workflows through the `sup` CLI.
    
    ## Always
    
    - CLI surface only; stay on MCP or direct API if that's what the user requested.
    - Default to `--json` for automation and agent consumption.
    - 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.
    - Route push, sync, overwrite, and `--force` to `preset-cli-mutations`.
    - Redact tokens and credential-bearing output in transcripts.
    
    ## Decision Rules
    
    - Classify CLI vs MCP vs direct API intent before acting; if MCP or direct API was requested, defer to that plugin.
    - 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.
    - Choose output format based on the downstream consumer: `--json` for automation, `--csv` for files, default Rich for humans, `--porcelain` for shell pipelines.
    - If a command group is not named on this card, load command coverage before composing commands.
    - 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.
    
    ## Workflow Order
    
    1. Establish install, auth, and workspace context.
    2. Choose output format.
    3. Classify risk (metadata read vs data-returning read vs mutation).
    4. Load the focused reference for the operation.
    5. Run only the safe / read command.
    6. Redact output before sharing.
    
    ## Retrieve
    
    - Install, entry points, OAuth, env vars: [references/install-and-auth.md](references/install-and-auth.md)
    - Config precedence and source resolution: [references/config-precedence.md](references/config-precedence.md)
    - Workspace selection and `--workspace-id` override: [references/workspace-and-config.md](references/workspace-and-config.md)
    - Registered command coverage and routing: [references/command-coverage.md](references/command-coverage.md)
    - Output formats and exit behavior: [references/output-formats.md](references/output-formats.md)
    - Asset read/export entity scope: [references/assets-read.md](references/assets-read.md)
    - Asset list filter matrix: [references/asset-filter-matrix.md](references/asset-filter-matrix.md)
    - Ad-hoc SQL routing: [references/sql-and-query.md](references/sql-and-query.md)
    - SQL/data-returning read safety: [references/sql-data-safety.md](references/sql-data-safety.md)
    - Saved query reads: [references/saved-query-reads.md](references/saved-query-reads.md)
    - Detailed command examples: [references/command-examples.md](references/command-examples.md)
    - CLI vs API routing decision: [references/cli-vs-api.md](references/cli-vs-api.md)
    - Approval gates and credential redaction: [references/safety-policy.md](references/safety-policy.md)
    

Comments (0)

Sign in to join the conversation.

No comments yet.

Reviews (0)

No reviews yet.