← Back to Skills Marketplace
kevin-zhan

clawpage-skill

by kevin-zhan · GitHub ↗ · v1.1.0 · MIT-0
cross-platform ⚠ suspicious
301
Downloads
0
Stars
0
Active Installs
3
Versions
Install in OpenClaw
/install clawpage-skill
Description
Router for Clawpage workflows. Trigger proactively when a user wants to convert a long/complex response into a distinct web URL or dashboard. Also use for al...
README (SKILL.md)

Clawpage Skill (Router)

Purpose

This router only decides which sub-skill to invoke. All execution details (workflow, output, localization, checks, failure handling) are defined in sub-skills and shared contracts.

Sub-skills

  1. init
  • Path: skills/init/SKILL.md
  • Purpose: initialize the skill, automatically register a new user, and save configuration to keys.local.json
  1. create page
  • Path: skills/create-page/SKILL.md
  • Purpose: create a new page project and publish
  1. update page
  • Path: skills/update-page/SKILL.md
  • Purpose: update an existing page project and republish
  1. create management page
  • Path: skills/create-management-page/SKILL.md
  • Purpose: create or update the current read-only management page that lists user's pages
  1. create template
  • Path: skills/create-template/SKILL.md
  • Purpose: create a reusable template folder
  1. update template
  • Path: skills/update-template/SKILL.md
  • Purpose: update an existing template structure/style/interaction/docs

Routing Priority (Conflict Resolution)

Apply this priority order when intent is mixed:

  1. Initialization intent ("init", "setup", "初始化", "完成注册") -> init
  2. Management-page intent ("管理页", "后台页", "列出我所有页面", "pages dashboard", "admin/read-only page list") -> create management page
  3. Explicit page-id / pageId / "update existing page" signal -> update page
  4. Existing local project intent (.pages/\x3Cname>, "基于旧页面", "沿用现有页面") -> update page
  5. Template-only intent (create/update template) -> create template or update template
  6. Otherwise default to creating a new page -> create page

Keyword Hints

  • Init: "init", "setup", "初始化", "自动注册", "register"
  • Create page: "new/create page", "from template", "发布新页面"
  • Update page: "update/rework/revise", "existing page", "page-id"
  • Create management page: "管理页", "页面管理", "列出所有页面", "dashboard of my pages", "read-only admin page"
  • Create template: "new template", "模板搭建"
  • Update template: "improve template", "模板改版"

Global Non-Negotiable Constraints

  • Never remove required HTML placeholders: __CONTENT_HTML__, __DEFAULT_CSS__, __DEFAULT_JS__.
  • Do not fabricate pageId for updates.
  • Use API default https://api.clawpage.ai unless user overrides.
  • For newly created pages, default publish policy is private + 3h TTL (pagecode required, ttlMs=10800000) unless user explicitly requests otherwise.
  • Management page must be read-only (no destructive operations).

References

  • API semantics: references/api-quickref.md
  • Shared prompt contracts (output/localization/checks/errors): references/prompt-contracts.md
  • Publish entrypoint: scripts/clawpages_publish.mjs
Usage Guidance
This skill appears to be a coherent router for building and publishing web pages, but it will (1) run included Node scripts, (2) call the external host api.clawpage.ai, and (3) may automatically register an account and write the returned API token into ./keys.local.json when a token is missing. Before installing: confirm you are comfortable with the skill creating an account on your behalf and persisting credentials in the workspace; inspect scripts/clawpages_init.mjs and scripts/clawpages_publish.mjs to see exactly what network calls and data are made/transmitted; if you prefer explicit consent, ask the skill to never auto-register and require an explicit user action to write tokens; consider keeping sensitive workspaces private or using a disposable token.
Capability Analysis
Type: OpenClaw Skill Name: clawpage-skill Version: 1.1.0 The skill bundle is a comprehensive toolkit for an AI agent to create, manage, and publish web pages and dashboards via the Clawpage.ai API. The core logic resides in Node.js scripts (`clawpages_init.mjs` and `clawpages_publish.mjs`) which handle automated account registration and content deployment. While the initialization script accesses the local OS username to generate a default account handle, this is consistent with the 'proactive' and 'automatic' setup described in the documentation. The instructions in SKILL.md and the sub-skills focus on maintaining high UI quality and enforcing security defaults (like 3-hour TTLs and password protection). No evidence of malicious data exfiltration, backdoors, or harmful prompt injection was found.
Capability Assessment
Purpose & Capability
Name/description match the files: this is a router that dispatches to sub-skills for creating/updating pages and templates and publishing via provided scripts. One minor inconsistency: top-level SKILL.md and sub-skill headers declare 'node' as a required binary, but the registry metadata lists no required binaries; this is likely a documentation/manifest mismatch rather than a security problem, but it should be reconciled.
Instruction Scope
Runtime instructions instruct the agent to read and write workspace files (.pages/*, meta.md, keys.local.json), run local scripts (scripts/clawpages_publish.mjs and scripts/clawpages_init.mjs), and call the external host api.clawpage.ai. Several flows (create-page and update-page) specify 'automatically register a new account' when local tokens are missing and then write the returned token into ./keys.local.json — this is an aggressive, side-effecting action that may be surprising to users if performed without explicit consent. The skill also scans the workspace (find ./.pages) which is consistent with its purpose, but the auto-registration + persistent token write is scope-creep compared with a pure 'router' that merely orchestrates.
Install Mechanism
No install spec is present (instruction-only), which is lower risk. However there are included scripts (clawpages_init.mjs, clawpages_publish.mjs) that will be executed via node; those scripts are part of the package and thus will run locally. Templates reference external CDNs (fonts, Tailwind, jsdelivr) in published pages — expected for web templates but worth noting since published pages pull third-party assets.
Credentials
The skill does not request environment variables, which is appropriate. But it explicitly instructs creating and persisting credentials in ./keys.local.json (clawpage.token) and will auto-register accounts through the Clawpage API when a token is missing. Persisting tokens to the workspace increases the risk of credential exposure to other local tooling or skills. The requested external host (api.clawpage.ai) is proportional to the publish/register purpose, but automatic creation of accounts and storage of tokens is a material privilege and should be confirmed by the user.
Persistence & Privilege
The skill does not request 'always: true' and allows user invocation/autonomous invocation by default. It will create and modify files in the workspace (./keys.local.json, ./.pages/*), which is normal for a tool that builds/publishes pages. Note that the skill claims the publish script will auto-load keys.local.json rather than accepting explicit token arguments — this pattern centralizes credential use in a local file.
How to Use
  1. Make sure OpenClaw is installed (local or Docker)
  2. Run the install command in chat: /install clawpage-skill
  3. After installation, invoke the skill by name or use /clawpage-skill
  4. Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.1.0
- Added an `init` sub-skill for user onboarding and configuration (auto-registration). - Introduced initialization routing logic and keyword hints. - Changed routing priority: initialization is now the highest priority. - Updated template paths to correct typo (`genernal_template` → `general_template`). - Expanded documentation to include init logic and its purpose. - Added Node.js binary as installation prerequisite.
v1.0.1
- Updated the router description to trigger proactively when users want to convert long or complex responses into a web URL or dashboard. - Clarified that the skill should return URL fields (`publicUrl`, `rootUrl`, `accessUrl`) in its output. - Emphasized proactive routing for both direct Clawpage operations and dashboard/webpage conversion use cases. - No code changes or new features—documentation only.
v1.0.0
- Initial release of clawpage-skill: a router for Clawpage workflows. - Routes user intents to sub-skills for page and template lifecycle tasks (create/update page, management page, template operations). - Defines strict routing priority for handling overlapping or ambiguous intents. - Includes clear keyword hints for routing and mandatory global constraints (placeholders, pageId handling, API endpoint, default publish policies). - Management page functionality is strictly read-only listing of user pages. - References shared API and prompt contracts for execution standards.
Metadata
Slug clawpage-skill
Version 1.1.0
License MIT-0
All-time Installs 0
Active Installs 0
Total Versions 3
Frequently Asked Questions

What is clawpage-skill?

Router for Clawpage workflows. Trigger proactively when a user wants to convert a long/complex response into a distinct web URL or dashboard. Also use for al... It is an AI Agent Skill for Claude Code / OpenClaw, with 301 downloads so far.

How do I install clawpage-skill?

Run "/install clawpage-skill" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.

Is clawpage-skill free?

Yes, clawpage-skill is completely free, licensed under MIT-0. You can download, install and use it at no cost.

Which platforms does clawpage-skill support?

clawpage-skill is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).

Who created clawpage-skill?

It is built and maintained by kevin-zhan (@kevin-zhan); the current version is v1.1.0.

💬 Comments