ClawHub

Morzai Skills

v1.0.1

Unified entry point for Morzai workflows. Routes requests through api/commands.json into the matching child skill.

⭐ 0· 86·0 current·0 all-time
by@morzai-app

Install

OpenClaw Prompt Flow

Install with OpenClaw

Best for remote or guided setup. Copy the exact prompt, then paste it into OpenClaw for morzai-app/morzai-skills.

Previewing Install & Setup.
Prompt PreviewInstall & Setup
Install the skill "Morzai Skills" (morzai-app/morzai-skills) from ClawHub.
Skill page: https://clawhub.ai/morzai-app/morzai-skills
Keep the work scoped to this skill only.
After install, inspect the skill metadata and help me finish setup.
Use only the metadata you can verify from ClawHub; do not invent missing requirements.
Ask before making any broader environment changes.

Command Line

CLI Commands

Use the direct CLI path if you want to install manually and keep every step visible.

OpenClaw CLI

Bare skill slug

openclaw skills install morzai-skills

ClawHub CLI

Package manager switcher

npx clawhub@latest install morzai-skills
Security Scan
Capability signals
CryptoCan make purchasesRequires OAuth tokenRequires sensitive credentials
These labels describe what authority the skill may exercise. They are separate from suspicious or malicious moderation verdicts.
VirusTotalVirusTotal
Benign
View report →
OpenClawOpenClaw
Benign
high confidence
✓
Purpose & Capability
The root skill's name and description (a router for Morzai workflows) align with its actual contents: a commands.json routing table and several child SKILL.md files. Child skills declare remote endpoints and a CLI where appropriate; nothing in the bundle unexpectedly requests unrelated cloud credentials or unusual system access.
✓
Instruction Scope
Runtime instructions are focused on intent detection, asking for missing inputs, reading api/commands.json, and then opening the selected child SKILL.md to continue. The skill reads local files bundled in the package and directs execution to remote MCP endpoints or the morzai CLI as described—no instructions to read unrelated system files, harvest extra environment variables, or post data to unexpected endpoints are present.
✓
Install Mechanism
This is an instruction-only skill with no install spec or code files to download/extract. That minimizes install-time risk. It does require (at runtime) the public morzai CLI for the ecommerce-product-kit route and network access to the listed lumo.me endpoints, which is expected behavior for the described features.
ℹ
Credentials
The bundle does not require any environment variables by default; CLAW.json lists optional configs (MORZAI_API_KEY, MORZAI_GATEWAY_URL, MORZAI_CLI_PATH). These are reasonable for a suite that calls remote services and optionally overrides CLI paths, but users should avoid supplying sensitive credentials unless they trust the remote APIs/CLI and understand where their data will be sent.
✓
Persistence & Privilege
The skill does not request always:true and is not attempting to modify other skills or system-wide configuration. It will operate within the normal agent flow and requires network/filesystem permissions (declared in CLAW.json) to call remote endpoints and optionally save/download artifacts, which matches its stated behavior.
Assessment
This skill is a local router that reads api/commands.json and dispatches requests to the included child SKILLs or to the morzai CLI. Before installing or supplying credentials: (1) Verify you trust the remote endpoints (recolor-api.lumo.me, retouch-api.lumo.me, adjustment-api.lumo.me, api.lumo.me) and the official morzai CLI, since images and metadata will be uploaded to remote services; (2) Do not paste API keys or tokens unless you intend the CLI / remote services to operate on your data; optional config fields exist for overriding CLI path or gateway URL; (3) Expect the skill to access the network and save files locally (download/upload directories) as part of normal operation; (4) If you need stronger privacy guarantees, run these workflows with local-only tools or inspect the morzai CLI and remote API policies first.

Like a lobster shell, security has layers — review code before you run it.

Runtime requirements

🛍️ Clawdis
latestvk9791kxdczya6vxa28qz85pf2d85fsv0
86downloads
0stars
2versions
Updated 4d ago
v1.0.1
MIT-0
@morzai-app
latest
Download

Morzai AI Skills

This is the master gateway for the Morzai AI suite. It identifies user needs and routes them to the appropriate specialized sub-skill.

Root Responsibility

  • Route the request to exactly one child skill.
  • Read api/commands.json before asking follow-up questions.
  • Ask only for missing required inputs, and ask at most 2 short questions in one turn.
  • After routing, open the target child skill and continue the task in the same user-facing agent.
  • Do not promise unsupported behavior from the root layer.

Capability Layers

Layer 1: Single-Function Editing Tools

  • apparel-recolor
  • garment-retouch
  • clothing-adjustment

Layer 2: Composite Listing Workflow

  • morzai-ecommerce-product-kit

Source Of Truth

Flow

Step 1: Detect Intent

  • Read api/commands.json.
  • Choose the single best matching command.
  • If still ambiguous, ask one short disambiguation question.

Step 2: Fill Missing Inputs

  • Use the command's required_inputs and optional_inputs.
  • Ask only for missing required inputs first.
  • If the user gave a sample image for recolor, treat it as a way to derive the target color, not as permission to skip color confirmation entirely.

Step 3: Enter Child Skill

  • Open the routed child skill file.
  • From this point on, follow the child skill's workflow and constraints.
  • The root skill stops being the domain expert after routing and missing-input collection.

Step 4: Execute

  • Use the command's execution mapping from api/commands.json.
  • Layer 1 workflows use the routed child skill's remote MCP metadata.
  • morzai-ecommerce-product-kit uses the public morzai CLI path.
  • Return a clean result summary to the user.

Command Map

Layer 1

Layer 2

Guardrails

  • The root skill must not invent new parameters outside api/commands.json.
  • The root skill must not restate all child-skill knowledge.
  • The root skill must not keep working at the root layer after the child skill has been selected.

Comments

Loading comments...