Neura Market Logo

Clip2MD

Use clip2md to configure an access token, save web pages or article URLs as Markdown clipping tasks, check remaining daily/permanent quota, query task status, and wait for clipping…

mgtv

@kllb520

What This Skill Does

Saves web page URLs as Markdown files via the clip2md service. Also checks remaining daily and permanent quota. Requires a one-time token configuration from the clip2md web dashboard.

Replaces manually copying and formatting web content into Markdown by automating the clipping process through a single command.

When to Use It

  • Save a web article as Markdown for offline reading or note-taking
  • Clip a URL into an Obsidian vault or other Markdown-based knowledge base
  • Check how many daily or permanent clipping credits remain
  • Batch archive multiple web pages by running the clip command for each URL

Install

$ openclaw skills install @kllb520/clip2md

clip2md Agent Tool

Use the bundled CLI. Run commands from this skill folder unless the caller provides another path.

node scripts/clip2md.js <command>

Agent Workflow

  • Before clipping, querying quota, or checking a task, rely on the CLI to detect whether ~/.clip2md/config.json contains a token.
  • If the CLI says the token is missing, expired, or invalid, ask the user for a fresh clip2md token from the web profile page.
  • Never print, quote, summarize, or echo the token in user-facing output.
  • Summarize command results: task id, status, quota, title/error, and whether Markdown is ready. Do not paste full Markdown content unless the user explicitly asks for it.
  • Use clip only to submit a URL. Use wait only when the user asks to wait for completion or when completion is necessary for the request.

Commands

Configure token:

node scripts/clip2md.js config <token>

Check quota:

node scripts/clip2md.js quota

Submit a URL:

node scripts/clip2md.js clip "https://example.com/article"

Query one task:

node scripts/clip2md.js status <task_id>

Wait for one task:

node scripts/clip2md.js wait <task_id> [--timeout <seconds>] [--interval <seconds>]

Defaults: timeout 120 seconds, interval 5 seconds.

Status Semantics

  • SUCCESS: completed; Markdown is ready when the summary says Markdown: 已生成.
  • PENDING, PROCESSING, WAITING_SERVICE: still waiting; use wait if the user asked for completion.
  • FAILED, FAILED_AUTH_EXPIRED, FAILED_SERVICE_UNAVAILABLE, MANUAL_REVIEW: not completed; explain the error message/category if present and suggest retrying later or refreshing credentials based on the CLI message.

Errors

  • 401: token expired or invalid; ask the user for a new token and run config.
  • 403: quota or permission problem; report quota/permission failure without retry loops.
  • 409: duplicate link or task conflict; report the conflict and task context.
  • 429 or 503: rate limit or temporary service outage; respect the CLI retry hint when present.

配置

Token 存储在 ~/.clip2md/config.json。 API 默认地址为 https://clip2.md/api/v1。Set CLIP2MD_API_BASE only for tests or private deployments.

Top skills in this category

Proactive Agent Lite

@bestrocky

Transform AI agents from task-followers into proactive partners with memory architecture, reverse prompting, and self-healing patterns. Lightweight version f...

6442k

腾讯文档 TENCENT DOCS

@liyang58

腾讯文档（docs.qq.com）-在线云文档平台，是创建、编辑、管理文档的首选 skill。涉及"新建/创建/编辑/读取/查看/搜索文档"、"保存文件"、"云文档"、"腾讯文档"、"docs.qq.com"等操作，请优先使用本 skill。支持能力：(1) 创建各类在线文档（文档/Word/Excel/幻灯片/...

1920k

Figma

@maddiedreese

Professional Figma design analysis and asset export. Use for extracting design data, exporting assets in multiple formats, auditing accessibility compliance, analyzing design systems, and generating comprehensive design documentation. Read-only analysis of Figma files with powerful export and reporting capabilities.

1610k

Smart Model Switching

@millibus

Auto-route tasks to the cheapest Claude model that works correctly. Three-tier progression: Haiku → Sonnet → Opus. Classify before responding. HAIKU (default): factual Q&A, greetings, reminders, status checks, lookups, simple file ops, heartbeats, casual chat, 1-2 sentence tasks. ESCALATE TO SONNET: code >10 lines, analysis, comparisons, planning, reports, multi-step reasoning, tables, long writing >3 paragraphs, summarization, research synthesis, most user conversations. ESCALATE TO OPUS: architecture decisions, complex debugging, multi-file refactoring, strategic planning, nuanced judgment, deep research, critical production decisions. Rule: If a human needs >30 seconds of focused thinking, escalate. If Sonnet struggles with complexity, go to Opus. Save 50-90% on API costs by starting cheap and escalating only when needed.

216.9k

AI Daily Briefing

@jeffjhunter

Start every day focused. Get a morning briefing with overdue tasks, today's priorities, calendar overview, and context from recent meetings. Works with ai-meeting-notes to-do list. No setup. Just say 'briefing'.

207.1k