Automated summary
Generates images via DALL-E by automating ChatGPT login sessions using saved browser profiles, supporting parallel execution across multiple accounts.
Strengths
- Parallel image generation across multiple accounts simultaneously
- Automated browser profile management
- Clear success/failure reporting per account
- Interactive setup for adding new accounts
Limitations
- Requires manual login for each new account
- Depends on Chrome and persistent sessions
- No fallback if ChatGPT UI changes
When you need to generate multiple images in parallel using different ChatGPT accounts.
If you need a single image quickly or if accounts are not yet set up.
Security analysis
CautionThe skill relies on Node.js dependencies and custom TypeScript scripts to manage browser profiles and interact with ChatGPT. While the scripts appear to be part of the skill, the use of npm install and browser automation introduces moderate risk if the packages or code are malicious or incorrectly vetted. No destructive or exfiltration commands are explicitly present, but the potential for hidden malicious payloads exists.
- •Uses Bash to run npm install and npx ts-node, executing scripts that automate browser sessions. If dependencies or local scripts are compromised, they could exfiltrate data or perform unintended actions.
Examples
/generate-image --all "a cat wearing a top hat, digital art"/generate-image --profile=acc1,acc2 "sunset over mountains"/generate-image "a futuristic city skyline"name: generate-image description: Generate an image via ChatGPT DALL-E using a saved browser session. Usage: /generate-image [--profile=acc1] <prompt> allowed-tools: Bash(npx:) Bash(npm:)
generate-image skill
Generates images by automating ChatGPT with saved browser profiles. Supports parallel generation across multiple accounts.
Step 1 — Install dependencies (once)
Check whether node_modules exists in the skill directory. If not, run:
cd ".claude/skills/generate-image" && npm install
Step 2 — Discover available profiles
Always run this first before anything else:
cd ".claude/skills/generate-image" && npx ts-node scripts/list-profiles.ts
Parse the output:
PROFILES_READY:acc1,acc2→ accounts that are set up and ready to generatePROFILES_AVAILABLE:acc3,acc4,acc5→ empty slots available to add new accountsNO_PROFILES_FOUND→ no accounts set up yet
Step 3 — Decide the flow
Case A — No profiles set up (NO_PROFILES_FOUND)
Tell the user no accounts are logged in yet. Open Chrome immediately for acc1 without asking:
cd ".claude/skills/generate-image" && npx ts-node scripts/setup-profile.ts acc1
After setup completes, if the user had a prompt, generate with acc1 automatically. Then ask:
Account added! What would you like to do next?
- Generate the image now with acc1
- Add another account first
- Cancel
Case B — Profiles exist AND user provided a prompt (no add-account request)
Skip asking. Generate immediately using all ready profiles (or the ones specified with --profile). Go to Step 4.
Case C — Profiles exist AND user provided a prompt AND user wants to add more accounts
Do not ask for confirmation. Immediately:
- Show which profiles are ready: e.g.
Ready: acc1, acc2 — Next slot: acc3 - Open Chrome right away for the next available slot:
cd ".claude/skills/generate-image" && npx ts-node scripts/setup-profile.ts <next_available_slot>
- After Chrome setup completes, ask:
New account added! What would you like to do with your prompt?
- Generate with all accounts (including the new one)
- Generate using selected existing accounts
- Add yet another account
Case D — Profiles exist AND no prompt was given
Show the user a compact summary, for example:
Ready accounts: acc1, acc2
Free slots: acc3, acc4, acc5What would you like to do?
- Generate an image with all ready accounts
- Generate with specific accounts
- Add another account
Wait for the user's choice before proceeding.
Step 4 — Generate images (parallel)
Run with a comma-separated list of profiles. The script launches all profiles simultaneously:
cd ".claude/skills/generate-image" && npx ts-node scripts/generate-image.ts --profile=acc1,acc2 "your prompt here"
To use all ready accounts automatically, use --all:
cd ".claude/skills/generate-image" && npx ts-node scripts/generate-image.ts --all "your prompt here"
After the script exits:
- Report
✓/✗status per account - Show each image path (printed as
Image saved → <path>) - If an account shows "not set up" error, suggest running setup for that profile
Step 5 — Add a new account
Run setup for the next available slot (e.g., acc3):
cd ".claude/skills/generate-image" && npx ts-node scripts/setup-profile.ts acc3
Chrome opens interactively. The user logs in manually, then presses Enter. The session is saved to profiles/acc3/.
After setup completes, offer to generate an image immediately with the newly added account.
Parsing the /generate-image invocation
/generate-image [--profile=acc1|acc1,acc2] [--all] <image prompt text>
--profile=acc1,acc2— use specific profiles (comma-separated)--all— use every ready profile- No flag → auto-detect all ready profiles
- Everything else is the image prompt
Environment (optional)
If Chrome is not in its default location, create .env from .env.example and set CHROME_PATH.
From the file to a first result
The download contains exactly the content displayed on this page. This copy may differ from the latest version in the source repository.
View the source and supporting filesThis download contains SKILL.md only. Any scripts, references, templates and dependencies are not included. Get the required files from the source, preserving their directory structure, before continuing.
1. Download the file
Download SKILL.mdFrom the root of a test project, save the file as .skill-downloads/generate-image-via-dall-e-mrzxup2k/SKILL.md, or use the command below. This folder is for inspecting the skill before installation.
Command for macOS/Linux or WSL: requires a POSIX shell and curl. On Windows without WSL, use the download button and create the folder manually.
mkdir -p '.skill-downloads/generate-image-via-dall-e-mrzxup2k' && curl --fail --show-error --location 'https://skills-guides.com/api/skills/generate-image-via-dall-e-mrzxup2k/download' --output '.skill-downloads/generate-image-via-dall-e-mrzxup2k/SKILL.md.part' && mv '.skill-downloads/generate-image-via-dall-e-mrzxup2k/SKILL.md.part' '.skill-downloads/generate-image-via-dall-e-mrzxup2k/SKILL.md'2. Check prerequisites
Read SKILL.md before using it. If it references scripts or external services, inspect them and prepare the required access in your test environment.
No recognized prerequisites section in this file. This does not mean it is self-contained: libraries, tools and access requirements may be mentioned elsewhere in the content or source repository.
The platforms on this page are catalog indications. The paths below follow tool documentation; they do not prove this skill has been run in those tools. No minimum tool version is confirmed for this listing.
3. Load the skill
This file does not provide a usable name/description header for this native procedure. It remains available to download and inspect; use the manual method below.
Manual method or another tool: attach SKILL.md to a conversation, or open it in an agent that can read files. Include any required supporting resources. No universal folder is recognized by every tool.
4. Try a first task
Use a short, synthetic input: an API endpoint, a small document or an interface brief. In a new conversation, attach the file or give the agent its path, then adapt this request:
Read .skill-downloads/generate-image-via-dall-e-mrzxup2k/SKILL.md and apply its instructions to this example: [describe a test input]. Identify any missing files, dependencies or access. Produce the result requested by the skill without inventing data or running unreviewed scripts.Expected result: output matching the skill instructions, or a precise list of missing prerequisites. A read confirmation alone does not validate a first use. If an external resource is unavailable, that path remains untested.
Writing Fragments
Content
Mine raw writing fragments through a relentless interview, without imposing structure. Capture ideas, quotes, and leading words for later use.
UI Copywriting & Auditing
Content
Write or audit user-facing UI copy including buttons, errors, empty states, and tooltips across the monorepo, following the design system source of truth.
Music MIDI Extraction
Content
Extracts the MIDI or score from an existing music production via the CogMusic MCP tool and confirms availability.