Pexo Agent
Turn a plain-language brief into a finished short-form video (ads, explainers, or social clips) without opening a separate editor.
Overview
Pexo Agent is an agent skill for the Launch phase that produces short AI videos (5–120 s) from a text brief via the Pexo API.
Install
npx skills add https://github.com/pexoai/pexo-skills --skill pexo-agentWhat is this skill?
- Delegates full creative pipeline—script, shots, transitions, and music—to Pexo’s hosted agent via API.
- Targets 5–120 second outputs with 16:9, 9:16, and 1:1 aspect ratios for multi-channel posting.
- Requires ~/.pexo/config with PEXO_API_KEY and PEXO_BASE_URL plus curl, jq, and file at runtime.
- Includes pexo-doctor.sh and SETUP-CHECKLIST for first-run config validation.
- Enforces replying in the user’s language (English, Chinese, Japanese, etc.) for every message.
- 5–120 second video outputs
- Aspect ratios 16:9, 9:16, and 1:1
Adoption & trust: 33.3k installs on skills.sh; 732 GitHub stars; 2/3 security scanners passed (skills.sh audits).
What problem does it solve?
You need professional short video for launch or social channels but lack time, editing tools, or a production workflow inside your agent session.
Who is it for?
Solo builders shipping product teasers, UGC-style ads, or explainer clips during launch and content sprints.
Skip if: Teams that need long-form film editing, offline-only workflows, or video generation without network access and a Pexo API key.
When should I use this skill?
User wants to produce a short video (5–120 seconds)—product ads, TikTok/Instagram/YouTube content, brand videos, explainers, or social clips.
What do I get? / Deliverables
After setup and a successful API run, you get a rendered short video aligned to your brief and chosen aspect ratio, ready to publish or iterate with Pexo’s previews.
- Rendered short video file from Pexo
- Clarification or preview choices from the Pexo agent flow
Recommended Skills
Journey fit
Launch is the canonical shelf because the skill’s payoff is publish-ready promotional and social video assets, not application code. Distribution fits short clips meant for TikTok, Instagram, YouTube, and brand promos that ship alongside a product launch.
How it compares
Use as a hosted generative-video integration skill, not a local FFmpeg or Remotion rendering workflow in your repo.
Common Questions / FAQ
Who is pexo-agent for?
Indie founders and marketers who want AI-assisted short video from inside their coding agent, using Pexo’s cloud service and API key.
When should I use pexo-agent?
Use it at launch or growth when you need product videos, brand clips, explainers, or social shorts; also when the user says make a video, product video, or promotional clip.
Is pexo-agent safe to install?
It needs network access, shell tools, and a secret API key in ~/.pexo/config—review the Security Audits panel on this page and scope keys before automated runs.
SKILL.md
READMESKILL.md - Pexo Agent
# 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