OpenParable
Skip to content
← Back to skills

Mxs CLI AI Author

Apps & Automation
mxs-cli-ai-author

Mxs CLI AI Author is an Agent Skill for apps & automation published in the mx-space/core repository on GitHub: a SKILL.md instruction file an AI agent can load to do this task.

Use when an agent must inspect, draft, validate, edit, publish, unpublish, delete, or configure mx-space content through packages/cli or the mxs binary.

View on GitHub ↗
QUICK START

How to use this skill

Bring this guide into your coding agent with a prompt tailored to the tool you use.

  1. Open your project in Codex.
  2. Copy and paste the prompt below.
  3. Review files and risks before approving any action.
Prompt to paste
Inspect the Agent Skill at https://github.com/mx-space/core/blob/HEAD/.claude/skills/mxs-cli-ai-author/SKILL.md and all supporting files. Report provenance, permissions, scripts, dependencies, and security risks. Propose an exact installation into .agents/skills/mxs-cli-ai-author, but wait for my approval before writing files or running scripts.

Copying this prompt does not install or run the skill. Review third-party files before use.

mxs CLI AI Author

Use mxs as the deterministic interface for mx-core content operations without opening the admin UI. Load only the references needed for the requested operation.

Reference Map

NeedRead
Exact command syntax, flags, resource coverageCommand Index
Post, note, and page authoring workflowsContent Authoring
Authentication, target selection, output modes, config filesAuth, Config, And Output
Mutation safety, verification, failures, exit codesSafety And Troubleshooting

Mandatory Workflow

┌──────────────────────┐
│ Identify operation   │
└──────────┬───────────┘
           ▼
┌──────────────────────┐
│ Load relevant refs   │
└──────────┬───────────┘
           ▼
┌──────────────────────┐
│ Confirm target/auth  │
└──────────┬───────────┘
           ▼
     ◆ Mutation? ◆
      /          \
     ▼            ▼
┌──────────┐  ┌──────────────────────┐
│ Read cmd │  │ Dry run if supported │
└────┬─────┘  └──────────┬───────────┘
     │                   ▼
     │          ┌──────────────────────┐
     │          │ Execute mutation     │
     │          └──────────┬───────────┘
     │                   ▼
     └─────────>┌──────────────────────┐
                │ Verify read-back     │
                └──────────────────────┘

Required Safety Rules

  • Always use machine-readable output: pass --json for mutations and reads unless the task explicitly asks for human output.
  • Never print access tokens, refresh tokens, cookies, API keys, or raw credential files.
  • Treat MXS_API_URL, MXS_TOKEN, MXS_API_KEY, --api-url, --token, and --api-key as execution context, not content.
  • Do not publish to production unless the user explicitly requested publication or the configured target has been confirmed as the intended target.
  • If testing the write path without publication, set <state>draft</state> or pass --state draft.
  • After any create, edit, update, publish, or unpublish operation, read the resource back and verify observable fields.
  • For destructive operations, prefer --dry-run first where supported, then require an explicit user request or confirmed intended target before using delete --force.

Target Confirmation

Before writing, establish the target. See Auth, Config, And Output for complete auth and configuration behavior.

mxs auth status --json
mxs auth whoami --json
mxs category list --json

If the command returns fetch failed, start or select the intended mx-core server before continuing. In this repository, local development normally uses http://localhost:2333, with no /api/v2 prefix. If writes return auth.expired while reads work, confirm whether the available credential is an API key. API keys must be passed through MXS_API_KEY or --api-key, not MXS_TOKEN.

Command Coverage

The CLI command surface includes auth, post, note, page, category, topic, comment, snippet, and config. Before using an unfamiliar command or flag, read Command Index. Do not infer unsupported flags from another resource type.

Verification Checklist

CheckEvidence
Targetauth whoami --json and API URL
Categorycategory list --json includes requested slug
Topictopic list --json includes requested slug when writing notes
Mutationcreate/update/publish/unpublish/delete command returns ok: true under --json
Retrievalmatching get <slugOrId> --json or --output llm succeeds
Publicationread-back state matches requested draft, publish, or unpublish state
Bodyrepresentative content text survives LiteXML or markdown conversion

Output Discipline

  • Mutations: use --json.
  • Script reads: use --json.
  • Agent read-back for document content: use --output llm or --output envelope.
  • Human inspection: use --output readable only when requested.
  • Troubleshooting: use --verbose without printing credentials.