Neura Market Logo

Hypertxt Content Operations

Operate Hypertxt articles and GSC safely

Julian Engel

@julianengel

What This Skill Does

Operates Hypertxt articles and Google Search Console through the Hypertxt MCP server. Enables agents to inspect credits, projects, article templates, and drafts; find content opportunities in GSC; generate articles; review or change editorial state; export content; and create CMS drafts or live publications.

Replaces manual content operations and GSC analysis by providing a controlled, permission-based layer for article generation, editorial state management, and search console data queries.

When to Use It

  • Inspect account credits and project list before proposing article generation
  • Query Google Search Console to find content opportunities ranked by clicks and impressions
  • Generate a new article using a specific project, template, and keyword after confirming credit availability
  • Review an article's content and change its editorial state to reviewed, approved, or posted
  • Publish an article as a CMS draft or live publication to a connected destination
  • Export an article for use outside the Hypertxt system

Install

$ openclaw skills install @julianengel/hypertxt

Hypertxt

Use Hypertxt as a controlled content-operations layer. Prefer discovery and inspection before generation, state changes, GSC refreshes, or publishing.

Preflight

  1. Confirm that account_status and list_projects are available from the Hypertxt MCP server.
  2. If they are missing, stop and direct the user to https://www.hypertxt.ai/guides/openclaw/. Do not invent configuration.
  3. Never request or echo a Hypertxt API key. Tell the user to store it as HYPERTXT_API_KEY in the client's environment or secret configuration.
  4. Call account_status before proposing generation. Report the plan and remaining article credits.
  5. Discover IDs with list tools. Never guess a project, article template, article, GSC connection, or publishing destination ID.

Permission boundary

Treat these as read-only:

  • account_status
  • list_projects
  • list_workflows
  • list_articles
  • get_article
  • export_article
  • list_integrations
  • list_gsc_connections
  • query_gsc

Obtain explicit user approval immediately before each of these actions:

  • generate_article: spends one article credit.
  • change_article_state: records an editorial decision.
  • sync_gsc: queues a durable refresh.
  • publish_article: writes to a connected destination; live mode publishes.

Approval for one action does not authorize later actions. Never infer approval to publish from approval to generate or review.

Find an opportunity with GSC

  1. Call list_projects.
  2. Call list_gsc_connections for the selected project.
  3. Call query_gsc with a clear grouping and filters.
    • Omit dates for the latest synchronized snapshot.
    • Supply start_date and end_date for an exact live window.
  4. Rank opportunities from returned clicks, impressions, CTR, and position. Distinguish observed metrics from editorial inference.
  5. Present a proposed title, primary keyword, audience, search intent, and brief. Do not generate yet.

Generate an article

  1. Call account_status and require at least one article credit.
  2. Call list_workflows for the selected project.
  3. Present the exact project, article template, title, keyword, brief, and one-credit cost.
  4. Ask for explicit approval.
  5. Call generate_article once.
  6. Report the returned article ID and state. Use get_article or list_articles to monitor; do not repeat generation when status is queued.
  7. If Hypertxt returns HTTP 402, report that no article or task was created.

Review and change state

  1. Call get_article and inspect the complete content.
  2. Summarize material editorial issues and recommend a decision.
  3. Ask for approval before change_article_state.
  4. Explain that reviewed and approved map to ready; posted maps to published as a manual state record and does not contact a CMS.
  5. Report the article ID, previous state, and confirmed new state.

Publish

  1. Call get_article; require reviewed, ready content.
  2. Call list_integrations and name the exact destination.
  3. Ask whether to create a destination draft or publish live.
  4. State the article ID, destination, and mode in the confirmation.
  5. Call publish_article once after approval.
  6. Report the returned external URL and final state when present.

A destination draft keeps the Hypertxt article ready. Live publishing changes it to published. Do not describe a destination draft as publicly posted.

Finish every workflow

Report:

  • project and article IDs used;
  • GSC window and filters, when applicable;
  • credit count before generation;
  • actions performed and actions deliberately not performed;
  • current article state and destination URL, when applicable;
  • any remaining approval or setup step.

Top skills in this category

API Gateway

@byungkyu

Call third-party APIs through the Maton gateway, which injects the credential for an app the user has already connected. Use this skill when the user names a connected app and a concrete action in it - read a mailbox, query a CRM, file an issue, update a spreadsheet, etc.

39488k

Playwright MCP

@spiceman161

Browser automation via Playwright MCP server. Navigate websites, click elements, fill forms, extract data, take screenshots, and perform full browser automation workflows.

16047k

YouTube

@byungkyu

YouTube Data API integration with managed OAuth. Search videos, manage playlists, access channel data, and interact with comments. Use this skill when users want to interact with YouTube. For other third party apps, use the api-gateway skill (https://clawhub.ai/byungkyu/api-gateway). Calls run through the `maton` CLI with OAuth login, or over raw HTTP with a Maton API key where the CLI cannot be installed. Every call is authenticated as the user's connection and reaches only what that connection's authorization allows, which the provider enforces on every request; the endpoints documented here are the ones this skill uses, and any other endpoint of this app needs the user to ask for it by name. Default to read and list calls, and confirm every write or new connection with the user. This file also documents the three constructs that turn a YouTube connection into automation, in the order they are used: the connection (the first step), a hosted function that runs a YouTube action through the Maton SDK, and a trigger that calls that function on a schedule or on an event. Those sections are the platform's own reference text, shared with the api-gateway skill, with YouTube examples; they add no YouTube capability - YouTube is not an event source, a trigger cannot read YouTube data, and the files under `references/<source>/triggers.md` are the platform's event catalogues for the sources Maton offers (time, Calendly, GitHub, Gmail, HubSpot, Linear, Notion, Slack, Stripe).

14529k

Peekaboo

@steipete

Capture and automate macOS UI with the Peekaboo CLI.

8532k

google-slides

@byungkyu

Google Slides API integration with managed OAuth. Create presentations, add slides, insert content, and manage slide formatting. Use this skill when users want to interact with Google Slides. For other third party apps, use the api-gateway skill (https://clawhub.ai/byungkyu/api-gateway). Calls run through the `maton` CLI with OAuth login, or over raw HTTP with a Maton API key where the CLI cannot be installed. Every call is authenticated as the user's connection and reaches only what that connection's authorization allows, which the provider enforces on every request; the endpoints documented here are the ones this skill uses, and any other endpoint of this app needs the user to ask for it by name. Default to read and list calls, and confirm every write or new connection with the user. This file also documents the three constructs that turn a Google Slides connection into automation, in the order they are used: the connection (the first step), a hosted function that runs a Google Slides action through the Maton SDK, and a trigger that calls that function on a schedule or on an event. Those sections are the platform's own reference text, shared with the api-gateway skill, with Google Slides examples; they add no Google Slides capability - Google Slides is not an event source, a trigger cannot read Google Slides data, and the files under `references/<source>/triggers.md` are the platform's event catalogues for the sources Maton offers (time, Calendly, GitHub, Gmail, HubSpot, Linear, Notion, Slack, Stripe).

3420k