Anygen Website

AnyGen AI Website Generator

Build a landing page or simple website from a natural language prompt using AnyGen OpenAPI. Output: online task URL for viewing the generated website.

When to Use

• User needs to create a landing page, portfolio site, or simple website
• User has files to upload as reference material for website generation

Security & Permissions

What this skill does:

• Sends task prompts and parameters to the AnyGen API at www.anygen.io
• Uploads user-provided reference files to www.anygen.io when --file is specified
• Reads/writes API key config at ~/.config/anygen/config.json

What this skill does NOT do:

• Does not upload files unless the user explicitly provides them via --file
• Does not send your API key to any endpoint other than www.anygen.io
• Does not modify system configuration beyond ~/.config/anygen/config.json
• Does not run background processes or install additional software

Bundled scripts: scripts/anygen.py (Python — uses requests)

Review the bundled scripts before first use to verify behavior.

Prerequisites

• Python3 and requests: pip3 install requests
• AnyGen API Key (sk-xxx) — Get one → Setting → Integration
• Configure once: python3 scripts/anygen.py config set api_key "sk-xxx"

All scripts/ paths below are relative to this skill's installation directory.

Communication Style

When interacting with the user, communicate naturally and professionally:

1. You may refer to AnyGen as the service powering the website generation when relevant.
2. Present questions and suggestions in a natural, conversational tone — avoid exposing raw API responses or technical implementation details.
3. Summarize prepare responses in your own words rather than echoing them verbatim.
4. Stick to the questions prepare returned — do not add unrelated questions.

Examples

Less ideal (overly technical):

• "The prepare API returned the following JSON response with status=collecting..."

Better (natural and professional):

• "What is the primary purpose of this website, and who is the target audience?"
• "Based on what you've shared, here is the website plan: [summary]. Should I go ahead, or would you like to adjust anything?"

Website Workflow (MUST Follow)

For websites, you MUST go through all 4 phases. A good website needs clear purpose, target audience, content structure, and style. Users rarely provide all of these upfront.

Phase 1: Understand Requirements

If the user provides files, you MUST handle them yourself before calling prepare:

1. Read the file content yourself using your own file reading capabilities. Extract key information (topic, content, structure) that is relevant to creating the website.
2. Check if the file was already uploaded in this conversation. If you already have a file_token for the same file, reuse it — do NOT upload again.
3. Inform the user and get consent before uploading. Tell them the file will be uploaded to AnyGen's server for processing.
4. Upload the file to get a file_token for later use in task creation.
5. Include the extracted content as part of your --message text when calling prepare, so that the requirement analysis has full context.

The prepare API does NOT read files internally. You are responsible for providing all relevant file content as text in the conversation.

# Step 1: Tell the user you are uploading, then upload the file
python3 scripts/anygen.py upload --file ./product_brief.pdf
# Output: File Token: tk_abc123

# Step 2: Call prepare with extracted file content included in the message
python3 scripts/anygen.py prepare \
  --message "I need a product landing page. Here is the product brief: [your extracted summary/content here]" \
  --file-token tk_abc123 \
  --save ./conversation.json

Present the questions from reply naturally (see Communication Style above). Then continue the conversation with the user's answers:

python3 scripts/anygen.py prepare \
  --input ./conversation.json \
  --message "Target audience is small business owners, include hero section, features, pricing, and CTA" \
  --save ./conversation.json

Repeat until status="ready" with suggested_task_params.

Special cases:

• If the user provides very complete requirements and status="ready" on the first call, proceed directly to Phase 2.
• If the user says "just create it, don't ask questions", skip prepare and go to Phase 3 with create directly.

Phase 2: Confirm with User (MANDATORY)

When status="ready", prepare returns suggested_task_params containing a detailed prompt. You MUST present this to the user for confirmation before creating the task.

How to present:

1. Summarize the key aspects of the suggested plan in natural language (purpose, sections, content, style).
2. Ask the user to confirm or modify. For example: "Here is the website plan: [summary]. Should I go ahead, or would you like to adjust anything?"
3. NEVER auto-create the task without the user's explicit approval.

When the user requests adjustments:

1. Call prepare again with the user's modification as a new message, loading the existing conversation history:

python3 scripts/anygen.py prepare \
  --input ./conversation.json \
  --message "<the user's modification request>" \
  --save ./conversation.json

2. prepare will return an updated suggestion that incorporates the user's changes.
3. Present the updated suggestion to the user again for confirmation (repeat from step 1 above).
4. Repeat this confirm-adjust loop until the user explicitly approves. Do NOT skip confirmation after an adjustment.

Phase 3: Create Task

Once the user confirms:

python3 scripts/anygen.py create \
  --operation website \
  --prompt "<prompt from suggested_task_params, with any user modifications>" \
  --file-token tk_abc123
# Output: Task ID: task_xxx, Task URL: https://...

Immediately tell the user:

1. Website is being generated (takes a few minutes).
2. Give them the Task URL so they can check progress online.

Phase 4: Return Results

No file download for website. When the task completes, return the Task URL for online viewing.

python3 scripts/anygen.py poll --task-id task_xxx

Tell the user:

• Task URL — for viewing and interacting with the generated website

Command Reference

prepare

python3 scripts/anygen.py prepare --message "..." [--file-token tk_xxx] [--input conv.json] [--save conv.json]

create

python3 scripts/anygen.py create --operation website --prompt "..." [options]

upload

python3 scripts/anygen.py upload --file ./document.pdf

Returns a file_token. Max file size: 50MB. Tokens are persistent and reusable.

Error Handling

Notes

• Max task execution time: 20 minutes
• Results are viewable online at the task URL
• Poll interval: 3 seconds