duotify/githubclawtoolkit/felo-superagent

Felo SuperAgent Skill

Constraints (MUST READ FIRST)

These rules are mandatory. Violating any of them will produce incorrect behavior.

1. NEVER treat image/product descriptions as prompt-writing or prompt-optimization tasks. If the user's message contains a visual description — regardless of phrasing such as "我的提示詞為", "my prompt is", "生成一張", "generate a photo of", "create a product image" — you MUST call the felo-superAgent API immediately to generate the actual image. Do NOT:

• Rewrite, refine, or "improve" the description as a text output
• Suggest keywords or aspect ratios as your final response
• Write a better prompt to result.md instead of calling the API
• Describe what you would do instead of doing it

The ONLY correct response to an image/product generation request is to execute the skill (run run_superagent.mjs with --skill-id ecommerce-product-image or logo-and-branding) and output the resulting image URLs. If you find yourself writing text about the image instead of calling the API, stop and call the API.

1. ALWAYS use `--json` flag. The script MUST run in JSON mode (--json). In Claude Code's Bash tool, stdout is always captured — it never streams directly to the user. JSON mode returns the full answer in a structured response that Claude can then output as text. State IDs are extracted from the JSON response fields thread_short_id and live_doc_short_id.

1. ALWAYS output the answer and all tool results. After the script finishes: (a) print data.answer verbatim as your response text — do NOT summarize or paraphrase; (b) render every entry in data.image_urls as a Markdown inline image ![title](url) immediately after the answer — NEVER skip image URLs; (c) list any entries in data.discoveries, data.documents, data.ppts, data.htmls.

1. `--live-doc-id` is optional for the first call. run_superagent.mjs works without --live-doc-id — the API will auto-assign a LiveDoc and return its live_doc_short_id in the JSON response. On the FIRST call in a session (no live_doc_id known yet), you MAY omit --live-doc-id. After the first call, always reuse the returned live_doc_short_id (see Constraint #4 and Step 2).

1. Reuse `live_doc_id` from ANY source. If you already have a live_doc_id from any previous operation in this session — whether from a prior SuperAgent call's JSON response (data.live_doc_short_id), user-provided input, or any other skill — use it directly. Do NOT try to fetch LiveDoc list via felo-livedoc (it may not be installed). Only omit --live-doc-id when you truly have no ID from any source. (Note: live_doc_id corresponds to the API field live_doc_short_id and the [state] output key live_doc_short_id.)

1. One LiveDoc per session. All conversations within a session MUST use the same --live-doc-id. Do NOT create a new LiveDoc unless the user explicitly asks to "open a new canvas" / "start a new LiveDoc" / "create a new workspace".

1. Default behavior is follow-up, not new conversation. After the first question, every subsequent user message is a follow-up. You MUST pass --thread-id from the previous response. Only omit --thread-id (to start a new thread on the same LiveDoc) when:

• The user explicitly says "new topic" / "change subject" / "start over"
• The user's intent requires a specific --skill-id (e.g., tweet writing, logo design, product image) and the current thread was not created with that skill — because --skill-id only takes effect in new conversations

1. Always persist state. After every call, extract thread_short_id and live_doc_id from the stderr [state] line (where live_doc_id is output as live_doc_short_id). Use them in the next call. Losing these IDs breaks conversation continuity.

1. Skill ID selection (New Conversations Only). When creating a new conversation (no --thread-id), analyze the user's intent and determine if it matches one of the supported skill IDs:

Available skill IDs:

• twitter-writer — For composing, drafting, or posting tweets/X posts
• logo-and-branding — For creating logos, brand designs, or visual identity
• ecommerce-product-image — For generating product images for e-commerce use

Selection logic:

• If the user explicitly requests a specific skill-id, use their specified value
• If the user's intent clearly matches one of the above, pass --skill-id with that value
• If none of the above match, do NOT pass --skill-id (general conversation mode)
• --skill-id is only effective when creating a new conversation. It is ignored in follow-up mode (--thread-id).

1. Brand style selection for skill-based new conversations. When starting a NEW conversation that uses a skill ID (twitter-writer, logo-and-branding, ecommerce-product-image), you MUST fetch the style library and let the user choose a style BEFORE calling run_superagent.mjs. The chosen style is passed via --ext '{"brand_style_requirement":"<style_string>"}'. See Step 4.5 for the full procedure.

• The style string is the exact text block output by run_style_library.mjs for that entry. Fields vary by category:
• TWITTER: Style name + Style labels (language-aware) + Style DNA + Cover file ID (omitted if null)
• IMAGE: Style name + Style labels + Style DNA or Cover file ID depending on what is present
• Use the category that matches the skill: TWITTER for twitter-writer, IMAGE for logo-and-branding and ecommerce-product-image.
• Always pass --accept-language to run_style_library.mjs so labels are returned in the user's language.
• If the user has already specified a style (by name or by pasting the style block), skip the fetch and use their choice directly.
• If the style library returns no entries, proceed without --ext.
• --ext is only valid for new conversations. Never pass it in follow-up mode (--thread-id).

1. Never create a new LiveDoc casually. Reuse the existing one. The only exception is an explicit user request for a new canvas/workspace.

When to Use

Trigger this skill when users want:

• SuperAgent conversation: AI conversation with Felo SuperAgent, with real-time streaming output
• Continuous conversation: Multi-turn Q&A on a persistent LiveDoc canvas
• Logo & branding: Create logos or brand designs (auto-selects logo-and-branding skill)
• E-commerce images: Generate product images for e-commerce use (auto-selects ecommerce-product-image skill). This includes any request where the user provides a visual description and wants an AI-generated product photo — e.g., "生成一張…產品照片", "generate a photo of a leather wallet", "幫我生成一張商品圖"
• Image generation from description: Any request where the user describes a scene, product, or visual concept and expects an actual AI-generated image as output — NOT a text description or prompt refinement
• Tool-augmented answers: Responses that may include image generation, document creation, PPT generation, or Twitter/X search
• Streaming responses: Real-time answer generation with Server-Sent Events (SSE)

⚠️ IMPORTANT — Do NOT misinterpret image requests as prompt-writing tasks. If the user provides a visual description and asks to "生成"/"generate"/"create" an image or photo, ALWAYS call the felo-superAgent API with --skill-id ecommerce-product-image. Do NOT respond with refined text prompts or suggestions — execute the skill and output the generated image URLs.

Trigger words:

• English: superagent, super agent, stream chat, streaming conversation, livedoc conversation, continuous chat, follow-up question, create a logo, brand design, product image, e-commerce image, generate image, generate photo, product photo, product shot
• 繁體中文：超級助手、串流對話、連續對話、追問、設計 logo、品牌設計、電商圖片、商品圖片、商品照片、產品照片、產品圖片、生成圖片、生成照片、生圖、AI 生圖、AI 作圖、製作圖片、電商產品圖
• 简体中文：超级助手、流式对话、连续对话、追问、设计 logo、品牌设计、电商图片、商品图片、商品照片、产品照片、产品图片、生成图片、生成照片、生图、AI 生图
• Japanese (romaji): suupaa eejento, sutoriimingu kaiwa, keizoku kaiwa, rogo sakusei, shouhin gazou, gazou seisei, shouhin shashin

Explicit commands: /felo-superagent, "use felo superagent", "felo superagent"

Do NOT use for:

• Tweet/X post writing of any kind (use felo-twitter-writer instead)
• Simple one-off Q&A or real-time information queries (prefer felo-search)
• Web page content fetching only (use felo-web-fetch)
• PPT/slide generation only (use felo-slides)
• LiveDoc knowledge base management only (use felo-livedoc)
• Twitter/X search only (use felo-x-search)

Setup

1. Get Your API Key

1. Visit felo.ai and log in (or register)
2. Click your avatar in the top right corner → Settings
3. Navigate to the "API Keys" tab
4. Click "Create New Key" to generate a new API Key
5. Copy and save your API Key securely

2. Configure API Key

The scripts (run_superagent.mjs, run_style_library.mjs) read the API key only from the `FELO_API_KEY` environment variable. The felo config set CLI command writes to ~/.felo/config.json which these scripts do NOT read — environment variable is the only supported method.

Linux/macOS:

export FELO_API_KEY="your-api-key-here"

For permanent configuration, add to your shell profile (~/.bashrc or ~/.zshrc):

echo 'export FELO_API_KEY="your-api-key-here"' >> ~/.zshrc
source ~/.zshrc

Windows (PowerShell):

$env:FELO_API_KEY="your-api-key-here"

Windows (CMD):

set FELO_API_KEY=your-api-key-here

3. Dependency: felo-livedoc (Optional)

felo-livedoc is NOT required. run_superagent.mjs can be called without --live-doc-id on the first call — the API auto-assigns a LiveDoc and returns its ID in the response for reuse.

How to Execute

When this skill is triggered, follow these steps strictly in order. Execute all commands using the Bash tool.

Step 1: Check API Key

if [ -z "$FELO_API_KEY" ]; then
  echo "ERROR: FELO_API_KEY not set"
  exit 1
fi

If not set, stop and show the user the setup instructions above.

Step 2: Obtain live_doc_id

(Note: live_doc_id corresponds to the API field live_doc_short_id.)

2a. If you already have a `live_doc_id` from ANY source in this session: Skip to Step 3. Reuse the same ID. Sources include: a previous SuperAgent call's JSON response (data.live_doc_short_id), user-provided input, or any other skill that returned a LiveDoc ID.

2b. If no `live_doc_id` is available — proceed to Step 3 WITHOUT `--live-doc-id`. The API will auto-assign a LiveDoc. After the call completes, capture data.live_doc_short_id from the JSON response and reuse it in all subsequent calls.

2c. If the user explicitly requests a new canvas/workspace: Simply omit --live-doc-id in the next call. A new LiveDoc will be created automatically.

Step 3: Determine Conversation Mode

Decide whether this is a new conversation or a follow-up: