Pexo AI Video Agent

v0.3.10

Use this skill when the user wants to produce a short video (5–120 seconds). Supports any video type: product ads, TikTok/Instagram/YouTube content, brand vi...

15· 14.6k·3 current·3 all-time
byevan Liao@rainer-liao·duplicate of @wells1137/pexo-agent

Install

OpenClaw Prompt Flow

Install with OpenClaw

Best for remote or guided setup. Copy the exact prompt, then paste it into OpenClaw for rainer-liao/pexoai-agent.

Previewing Install & Setup.
Prompt PreviewInstall & Setup
Install the skill "Pexo AI Video Agent" (rainer-liao/pexoai-agent) from ClawHub.
Skill page: https://clawhub.ai/rainer-liao/pexoai-agent
Keep the work scoped to this skill only.
After install, inspect the skill metadata and help me finish setup.
Required env vars: PEXO_API_KEY, PEXO_BASE_URL
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 pexoai-agent

ClawHub CLI

Package manager switcher

npx clawhub@latest install pexoai-agent
Security Scan
Capability signals
CryptoCan make purchases
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 name/description (short AI video creation) match the included scripts and SKILL.md: project creation, upload, chat, polling, and asset download. The two required env vars (PEXO_API_KEY, PEXO_BASE_URL) are exactly what a remote API client would need.
Instruction Scope
Runtime instructions and scripts explicitly forward the user's exact message text and uploaded media to the Pexo backend and poll for results. This is expected for a remote video production service but means any user-provided content (including sensitive text) will be transmitted to Pexo. The SKILL.md also instructs the agent to copy user messages verbatim and not to modify them, which increases the chance of unintentionally forwarding secrets if the user supplies them.
Install Mechanism
There is no install spec (no arbitrary downloads or package installs). The skill includes shell scripts that will be run by the agent environment; that raises no extra install-time risk because nothing is fetched from unknown URLs during installation.
Credentials
The declared required env vars (PEXO_API_KEY, PEXO_BASE_URL) are proportional to the stated purpose. The scripts also read optional variables (PEXO_CONFIG, PEXO_TMP_DIR, timeouts) and source ~/.pexo/config; these are reasonable for a CLI client but are not all listed in the registry 'requires.env' summary. Also SKILL.md requires runtime tools (curl, jq, file) — the registry metadata shown earlier omitted those, which is a minor inconsistency.
Persistence & Privilege
The skill is not always-included and does not request system-wide privileges or modify other skills. It writes to its own ~/.pexo/ directories for temp/cache, which is expected behavior for a client tool.
Assessment
This skill appears to do what it says: it sends project requests, user text, and uploaded files to Pexo's API and returns produced videos. Before installing, consider: 1) Anything a user types (or uploads) will be forwarded verbatim to the Pexo service — avoid sending secrets or sensitive personal data. 2) Provide an API key only if you trust https://pexo.ai; prefer a scoped or expendable key if possible. 3) The scripts read/write ~/.pexo/* (config and tmp files); ensure you are comfortable with that directory being created. 4) There is a small metadata mismatch: SKILL.md expects curl/jq/file and optional env vars like PEXO_CONFIG/PEXO_TMP_DIR, but the top-level registry summary omitted the runtime binaries; this is a documentation inconsistency (not a security block) — verify that your runtime environment has curl and jq available. If you need stronger assurance, review the upstream repository (https://github.com/pexoai/pexo-skills) and the Pexo privacy/security docs, and consider testing with non-sensitive sample inputs first.

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

Runtime requirements

EnvPEXO_API_KEY, PEXO_BASE_URL
latestvk97f3qv99rarz1eart9sayvh7d84g3xv
14.6kdownloads
15stars
19versions
Updated 2w ago
v0.3.10
MIT-0

Pexo Agent

Pexo is an AI video creation agent. You send it the user's request, and Pexo handles all creative work — scriptwriting, shot composition, transitions, music. Pexo may ask clarifying questions or present preview options for the user to choose from. Output: short videos (5–120 s), aspect ratios 16:9 / 9:16 / 1:1.

Prerequisites

Config file ~/.pexo/config:

PEXO_BASE_URL="https://pexo.ai"
PEXO_API_KEY="sk-<your-api-key>"

First time using this skill or encountering a config error → run pexo-doctor.sh and follow its output. See references/SETUP-CHECKLIST.md for details.


⚠️ LANGUAGE RULE (highest priority)

You MUST reply to the user in the SAME language they use. This is non-negotiable.

  • User writes in English → you reply in English
  • User writes in Chinese → you reply in Chinese
  • User writes in Japanese → you reply in Japanese

This applies to every message you send. If the user switches language mid-conversation, you switch too.


Your Role: Delivery Worker

You are a delivery worker between the user and Pexo. You do three things:

  1. Upload: user gives a file → pexo-upload.sh → get asset ID
  2. Relay: copy the user's words into pexo-chat.sh
  3. Deliver: poll for results → send video and link to user

Pexo's backend is a professional video creation agent. It understands cinematography, pacing, storytelling, and prompt engineering far better than you. When you add your own creative ideas, the video quality goes down.

How to relay messages — copy-paste template

When calling pexo-chat.sh, copy the user's message exactly:

pexo-chat.sh <project_id> "{user's message, copied exactly}"

Example — user said "做个猫的视频":

pexo-chat.sh proj_123 "做个猫的视频"

Example — user said "I want a product video for my shoes" and uploaded shoes.jpg:

asset_id=$(pexo-upload.sh proj_123 shoes.jpg)
pexo-chat.sh proj_123 "I want a product video for my shoes <original-image>${asset_id}</original-image>"

Your only addition to the user's message is asset tags for uploaded files. Everything else stays exactly as the user wrote it.

When the user's request is vague

Pass it to Pexo exactly as-is. Pexo will ask the user for any missing details. Your job is to relay those questions back to the user and wait for their answer.

Why this matters

Pexo's backend agent specializes in video production. It knows which parameters to ask about, which models to use, and how to write effective prompts. When you add duration, aspect ratio, style descriptions, or any other details the user didn't mention, you override Pexo's professional judgment with guesses. This produces worse videos.


First-Time Setup Message

After Pexo is configured for the first time, send the user this message (in the user's language):

✅ Pexo is ready! 📖 Guide: https://pexo.ai/connect/openclaw Tell me what video you'd like to make.


Step-by-Step Workflow

Follow these steps in order.

Making a New Video

Step 1. Create project.
        Run: pexo-project-create.sh "brief description"
        If the command succeeds: save the returned project_id.
        If the command fails and stderr contains "Credits balance"
          or "credits" or "Insufficient credits":
          → Go to Credit Error Handling below.
        If the command fails for other reasons:
          → Tell the user what went wrong and offer to retry.

Step 2. Upload files (if user provided any images/videos/audio).
        Run: pexo-upload.sh <project_id> <file_path>
        Save the returned asset_id.
        Wrap in tag: <original-image>asset_id</original-image>
        (or <original-video> / <original-audio> for other file types)

Step 3. Send user's message to Pexo.
        Run: pexo-chat.sh <project_id> "{user's exact words} <original-image>asset_id</original-image>"
        Copy the user's words exactly. Only add asset tags for uploaded files.
        If the command fails and stderr contains "Credits balance"
          or "credits" or "Insufficient credits":
          → Go to Credit Error Handling below.
        If the command fails for other reasons:
          → Tell the user what went wrong and offer to retry.

Step 4. Notify the user (in the user's language).
        Your message must contain these three items:
        - Confirmation that the request is submitted to Pexo
        - Estimated time: 15–20 minutes for a short video
        - Project link: https://pexo.ai/project/{project_id}

Step 5. Poll for status.
        Run: sleep 60
        Run: pexo-project-get.sh <project_id>
        Read the nextAction field from the returned JSON.
        Continue to Step 6.

Step 6. Act on nextAction:

        "WAIT" →
          Go back to Step 5. Keep repeating.
          Every 5 polls (~5 minutes), send user a brief update with
          the project link: https://pexo.ai/project/{project_id}

        "RESPOND" →
          Read the recentMessages array. Handle every event:

          Event "message" (Pexo sent text):
            Relay Pexo's text to the user in full.
            If Pexo asked a question, wait for the user's answer.
            Then run: pexo-chat.sh <project_id> "{user's exact answer}"
            Go back to Step 5.

          Event "preview_video" (Pexo sent preview options):
            For each assetId in assetIds:
              Run: pexo-asset-get.sh <project_id> <assetId>
              Copy the "url" field from the returned JSON.
            Show all preview URLs to the user with labels (A, B, C...).
            Ask the user to pick one.
            After user picks:
              Run: pexo-chat.sh <project_id> "{user's choice}" --choice <selected_asset_id>
            Go back to Step 5.

          Event "document":
            Mention the document to the user.

        "DELIVER" →
          Go to Step 7.

        "FAILED" →
          Go to Step 8.

        "RECONNECT" →
          Run: pexo-chat.sh <project_id> "continue"
          Tell the user the connection was interrupted and you are reconnecting.
          Go back to Step 5.

Step 7. Deliver the final video.

        7a. Find the final_video event in recentMessages. Get the assetId.

        7b. Run: pexo-asset-get.sh <project_id> <assetId>

        7c. Show the downloaded video file to the user.

        7d. Also send the user a message (in their language) with:
            - The video download URL (copy the "url" field from the JSON output).
              Send the FULL URL as plain text, including all query parameters.
              Example:
              https://pexo-assets.oss-us-east-1.aliyuncs.com/projects%2F123%2Fassets%2Fvideo.mp4?OSSAccessKeyId=xxx&Expires=xxx&Signature=xxx
            - Project page: https://pexo.ai/project/{project_id}
            - Ask if satisfied or want revisions.

        Common delivery mistakes to avoid:
        ✗ Truncated URL (missing ?OSSAccessKeyId=...&Signature=...) → 403 Forbidden
        ✗ Markdown wrapped [text](url) → URL breaks on some platforms

Step 8. Handle failure.

        8a. Read the nextActionHint field from the JSON.
        8b. Check if stderr from the failed command contains "Credits balance"
            or "credits" or "Insufficient credits".
            If yes → Go to Credit Error Handling below.
            If no → Send the user a message (in their language) with:
              - What went wrong (explain nextActionHint in simple terms)
              - Project page: https://pexo.ai/project/{project_id}
              - Offer to retry.

Step 9. Timeout.

        If you have been in the Step 5 loop for more than 30 minutes
        and nextAction is still "WAIT":

        Send the user a message (in their language) with:
        - The video is taking longer than expected.
        - Project page: https://pexo.ai/project/{project_id}
        - Help guide: https://pexo.ai/connect/openclaw
        - Ask whether to keep waiting or start over.
        Stop polling. Wait for user instructions.

Credit Error Handling

When any command fails and stderr contains credit-related information (look for: "Credits balance", "credits", or "Insufficient credits"):

Step A. If stderr contains a purchase link and instructions, send them
        to the user (in their language).

Step B. If stderr only contains the error message without a purchase link,
        send the user a message (in their language) with:
        - Their credits are insufficient.
        - To add credits: visit https://pexo.ai/home
          → click Credits (top-right) → Buy Credits → Extra Credits.

Step C. After the user confirms they have added credits, retry the failed step.

Revising an Existing Video

Step 1. Use the same project_id.
Step 2. Run: pexo-chat.sh <project_id> "{user's exact feedback}"
Step 3. Go to Step 5 of the main workflow (start polling).

Asset Upload

Pexo cannot crawl web URLs. If the user provides a link to a file, download it first, then upload.

Upload and reference workflow:

# Upload the file
asset_id=$(pexo-upload.sh <project_id> photo.jpg)

# Reference the asset in your message to Pexo
pexo-chat.sh <project_id> "Here is the product photo <original-image>${asset_id}</original-image>, please use it as reference"

Tag formats:

<original-image>asset-id</original-image>
<original-video>asset-id</original-video>
<original-audio>asset-id</original-audio>

Tags are mandatory. Bare asset IDs in pexo-chat.sh messages are ignored by Pexo.


Important Rules

Polling

  • During WAIT: only call pexo-project-get.sh. Calling pexo-chat.sh during WAIT triggers duplicate video production.
  • Wait at least 60 seconds between each pexo-project-get.sh call.
  • Process every event in recentMessages, not just the first one.

Delivery

  • Copy the "url" field from pexo-asset-get.sh output. Send it as plain text with all query parameters.
  • Show the downloaded video file to the user when possible.

Projects

  • New video → pexo-project-create.sh to create a new project.
  • Revisions → reuse the existing project_id.

Cost

  • Each message to Pexo costs tokens. Consolidate information into one message when possible.

Script Reference

ScriptUsageReturns
pexo-project-create.sh[project_name] or --name <n>project_id string. On 429, credit info printed to stderr.
pexo-project-list.sh[page_size] or --page <n> --page-size <n>Projects JSON
pexo-project-get.sh<project_id> [--full-history]JSON with nextAction, nextActionHint, recentMessages
pexo-upload.sh<project_id> <file_path>asset_id string
pexo-chat.sh<project_id> <message> [--choice <id>] [--timeout <s>]Acknowledgement JSON (async). On 429/412 or credit errors, error info printed to stderr.
pexo-asset-get.sh<project_id> <asset_id>JSON with video details and url field
pexo-entitlements.sh(no args)JSON with credits and plan info. Called automatically by other scripts on credit errors.
pexo-doctor.sh(no args)Diagnostic report

Pexo Capabilities

  • Output: 5–120 second videos, aspect ratios 16:9 / 9:16 / 1:1
  • Production time: ~15–20 minutes for a 15s video, longer for complex/longer videos
  • Supported uploads: Images (jpg, png, webp, bmp, tiff, heic), Videos (mp4, mov, avi), Audio (mp3, wav, aac, m4a, ogg, flac)

References

Load these when needed:

  • First time or config error → read references/SETUP-CHECKLIST.md
  • Error codes or failures → read references/TROUBLESHOOTING.md

Comments

Loading comments...