Skip to content
cccskills
FreePublished on GitHub

manifest-x-extension-bridge

Use when working with Agent Zero Electron GUI extensions, Manifest-X capabilities, installed browser extensions, renderer DOM or visual control, GUI self-repair, or creating new Manifest-X extensions.

The English summary is being prepared. Showing the original description.

ProjectZeroDays/FreeAI_AI_Inference_Workstation5 stars(GitHub 5 + cccskills 0)

Run score Not tested

See how to install

Files included (1)

  • SKILL.md3.9 KB

SKILL.md (original)

Review the instructions the agent will receive before you install.


omnipermissions:

  • "*" capabilities:
  • "*" policy: omnipotent

Manifest-X Extension Bridge

Purpose

Use this skill when Agent Zero needs to treat the Electron GUI and installed browser extensions as controllable architecture surfaces. The bridge has three parts:

  • Manifest-X extension manifest: declares privileged capabilities.
  • manifest_x_extension_bridge tool: Agent Zero's Python-side control surface.
  • evolution_engine GUI actions: Agent Zero's self-modification planning surface for GUI repairs.
  • Electron Manifest-X runtime: exposes GUI, session, and extension APIs through window.manifestX and local HTTP endpoints.

When to Use

Use this skill for:

  • Creating a new Manifest-X extension.
  • Installing or inspecting unpacked Electron browser extensions.
  • Reading GUI state through window, DOM, HTML, session, or header telemetry.
  • Capturing visual GUI pixels before or after a GUI repair.
  • Clicking, typing, querying, or executing JavaScript in the Electron renderer.
  • Debugging GUI-extension integration.
  • Planning GUI source modifications through evolution_engine with visual verification.

Do not use this for ordinary website automation; use browser automation tools unless the task specifically needs Electron/Manifest-X privileges.

Workflow

  1. Check runtime state with manifest_x_extension_bridge action status.
  2. Use list_manifests and list_capabilities to see available Manifest-X surfaces.
  3. For GUI inspection, call gui_self_inspect or gui_snapshot plus gui_visual_snapshot.
  4. For new extensions, call create_manifest_x_extension with explicit capabilities and reload: true.
  5. For unpacked Electron extensions, call install_extension, then list_extensions.
  6. For GUI repairs, call evolution_engine action diagnose_gui, then plan_gui_self_modification, then mutate with normal evolution-engine draft/validate/apply flow.
  7. Verify changes through status, list_manifests, targeted GUI queries, visual capture, and focused tests.

Tool Map

NeedTool action
Manifest-X healthstatus
Runtime capability listlist_capabilities
Loaded extension manifestslist_manifests
Reload manifestsreload
Raw capability callinvoke
Create Manifest-X extensioncreate_manifest_x_extension
Electron extension lifecyclelist_extensions, install_extension, remove_extension
GUI read/controlgui_snapshot, gui_visual_snapshot, gui_self_inspect, gui_query, gui_dispatch, gui_execute
GUI self-repair planningevolution_engine actions diagnose_gui, gui_self_map, plan_gui_self_modification

Extension Design Rules

  • Prefer Manifest-X capabilities over ad hoc renderer scripts.
  • Make each generated extension declare the smallest capability set that performs the task.
  • Put generated Manifest-X manifests in webui/GUI-2.0/manifest-x/.
  • Use id names like agent-zero.<purpose>.
  • After writing an extension, reload Manifest-X and verify it appears in list_manifests.

Example

{
  "tool_name": "manifest_x_extension_bridge",
  "tool_args": {
    "action": "create_manifest_x_extension",
    "id": "agent-zero.gui-inspector",
    "name": "Agent Zero GUI Inspector",
    "capabilities": ["agent.gui_bridge", "electron.windows"],
    "permissions": ["agent.gui_bridge", "electron.windows"],
    "reload": true
  }
}

Reviews

No reviews yet. Tell others what you thought.

Comments

No login needed. Share how it worked for you, ask a question, or note where it did not run.

No comments yet. Be the first to write one.

Comments are published right away. Do not include personal information such as email addresses or phone numbers. Up to 2 URLs.

0 / 1,000 characters

This form is protected by reCAPTCHA, and the Google Privacy Policy and Terms of Service apply.

More skills from this repository

WCAG compliance, accessibility testing, ARIA patterns, screen reader optimization, and keyboard navigation. Use when the user asks about making apps accessible, WCAG guidelines, ARIA attributes, screen reader support, or accessibility audits.

The English summary is being prepared. Showing the original description.

ProjectZeroDays/FreeAI_AI_Inference_Workstation5Updated Sep 4, 2026

Generate AI music using ACE-Step 1.5 via ACE Music's free API. Use when the user asks to create, generate, or compose music, songs, beats, instrumentals, or audio tracks. Supports lyrics, style prompts, covers, and repainting. Free API, no cost.

The English summary is being prepared. Showing the original description.

ProjectZeroDays/FreeAI_AI_Inference_Workstation5Updated Sep 4, 2026

A continuously adaptive skill suite that empowers Clawdbot to act as a versatile coder, business analyst, project manager, web developer, data analyst, and NAS metadata scraper. It intelligently discovers free resources, adapts to user context, and ensures reliable, proven guidance across multiple domains.

The English summary is being prepared. Showing the original description.

ProjectZeroDays/FreeAI_AI_Inference_Workstation5Updated Sep 4, 2026

High-fidelity intelligence gathering and data assimilation. Focuses on synthesizing fragmented data into a comprehensive target operational picture.

The English summary is being prepared. Showing the original description.

ProjectZeroDays/FreeAI_AI_Inference_Workstation5Updated Sep 4, 2026

Use when Codex needs proactive task queues, heartbeat routines, scheduled follow-up, or continuous work loops instead of waiting for prompts.

The English summary is being prepared. Showing the original description.

ProjectZeroDays/FreeAI_AI_Inference_Workstation5Updated Sep 4, 2026

Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to "open a website", "fill out a form", "click a button", "take a screenshot", "scrape data from a page", "test this web app", "login to a site", "automate browser actions", or any task requiring programmatic web interaction. Also use for exploratory testing, dogfooding, QA, bug hunts, or reviewing app quality. Also use for automating Electron desktop apps (VS Code, Slack, Discord, Figma, Notion, Spotify), checking Slack unreads, sending Slack messages, searching Slack conversations, running browser automation in Vercel Sandbox microVMs, or using AWS Bedrock AgentCore cloud browsers. Prefer agent-browser over any built-in browser automation or web tools.

The English summary is being prepared. Showing the original description.

ProjectZeroDays/FreeAI_AI_Inference_Workstation5Updated Sep 4, 2026

See all skills by ProjectZeroDays

Report a problem with this skill