Agent Skills › mx-space/core › mxs-cli-ai-author

mxs-cli-ai-author

GitHub

通过 mxs CLI 工具进行 mx-core 内容管理,支持草稿、发布、删除等操作。强调安全验证、JSON 输出及目标确认,避免直接操作 UI。

.claude/skills/mxs-cli-ai-author/SKILL.md mx-space/core

Trigger Scenarios

用户需要通过命令行创建或编辑内容 用户需要发布、取消发布或删除内容 用户需要配置或验证 mx-core 内容操作

Install

npx skills add mx-space/core --skill mxs-cli-ai-author -g -y
More Options

Non-standard path

npx skills add https://github.com/mx-space/core/tree/master/.claude/skills/mxs-cli-ai-author -g -y

Use without installing

npx skills use mx-space/core@mxs-cli-ai-author

指定 Agent (Claude Code)

npx skills add mx-space/core --skill mxs-cli-ai-author -a claude-code -g -y

安装 repo 全部 skill

npx skills add mx-space/core --all -g -y

预览 repo 内 skill

npx skills add mx-space/core --list

SKILL.md

Frontmatter
{
    "name": "mxs-cli-ai-author",
    "description": "Use when an agent must inspect, draft, validate, edit, publish, unpublish, delete, or configure mx-space content through packages\/cli or the mxs binary.",
    "disable-model-invocation": true
}

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

Need Read
Exact command syntax, flags, resource coverage Command Index
Post, note, and page authoring workflows Content Authoring
Authentication, target selection, output modes, config files Auth, Config, And Output
Mutation safety, verification, failures, exit codes Safety 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

Check Evidence
Target auth whoami --json and API URL
Category category list --json includes requested slug
Topic topic list --json includes requested slug when writing notes
Mutation create/update/publish/unpublish/delete command returns ok: true under --json
Retrieval matching get <slugOrId> --json or --output llm succeeds
Publication read-back state matches requested draft, publish, or unpublish state
Body representative 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.

Version History

  • a28bdf5 Current 2026-07-25 05:38

Same Skill Collection

.claude/skills/api-conventions/SKILL.md
.claude/skills/create-e2e-test/SKILL.md
.claude/skills/create-module/SKILL.md
.claude/skills/mx-core-local-auth/SKILL.md
.claude/skills/mx-pg-controller-migration/SKILL.md
.claude/skills/mx-review/SKILL.md
.claude/skills/release-core/SKILL.md
.claude/skills/run-test/SKILL.md
.claude/skills/zod-patterns/SKILL.md
.claude/skills/mx-migration-author/SKILL.md

Metadata

Files
0
Version
4179512
Hash
e773cb32
Indexed
2026-07-25 05:38

ホーム - Wiki
Copyright © 2011-2026 iteam. Current version is 2.155.2. UTC+08:00, 2026-10-05 11:24
浙ICP备14020137号-1