// Extract webpage content with Felo Web Extract API. Use for turning URLs into html/markdown/text, selecting specific page areas with CSS selectors, and controlling extraction options like crawl mode, cookies, user-agent, and timeout.
Use this skill when asked to create a pull request (PR). It creates a new branch, commits with detailed Traditional Chinese (zh-TW) messages, enriches the related issue with technical context and problem definition, then creates a PR with a zh-TW description.
Use this skill when the user wants to generate music or audio tracks from lyrics or text prompts using Gemini Lyria-3, including AI music composition, audio generation, track creation, and requests like "幫我作一首歌", "生成音樂", "根據這段歌詞產生音軌", or "compose a track".
Send Telegram Bot notifications for development events, CI/CD pipeline status, and AGENTS.md progress updates. Use when integrating Telegram messaging into GitHub Actions workflows, sending pipeline end summaries, notifying teams about automation progress or repository changes. Requires TELEGRAM_NOTIFY_BOT_TOKEN environment variable or GitHub Secret. Target Chat IDs are resolved from the CSV recipients list defined in AGENTS.md.
Felo SuperAgent API: AI conversation with real-time SSE streaming on a persistent LiveDoc canvas. Use when users want SuperAgent chat, continuous conversation, logo/branding design, or e-commerce product images. CRITICAL: When user provides ANY image/product description (e.g. '生成一張...產品照片', '我的提示詞為: 生成...', 'generate a product photo'), ALWAYS call the API to generate the actual image — NEVER rewrite the prompt as text output. Do NOT use for tweet/X post writing — use felo-twitter-writer instead. Explicit commands: /felo-superagent.
Use this skill when a user provides a web page URL, PDF file, video, or audio file and wants a Traditional Chinese summary. Prefer this skill for requests like "summarize this URL", "summarize this PDF", "summarize this video", "summarize this audio", "幫我摘要這篇", "這份報告重點是什麼", "幫我總結這段影片", "幫我摘要這段錄音", or when analyzing articles, documents, presentations, YouTube videos, audio recordings, or any content that needs a zh-TW summary. Automatically detects input type (web page, PDF, video, audio) — no manual type selection needed.
Felo AI real-time web search for questions requiring current/live information. Triggers on current events, news, trends, real-time data, information queries, location queries, how-to guides, shopping, or when Claude's knowledge may be outdated.
| name | felo-web-fetch |
| description | Extract webpage content with Felo Web Extract API. Use for turning URLs into html/markdown/text, selecting specific page areas with CSS selectors, and controlling extraction options like crawl mode, cookies, user-agent, and timeout. |
Trigger this skill when users want to extract or convert webpage content from a URL:
html, markdown, or textfast/fine)Trigger keywords (examples):
/felo-web-fetch, "use felo web fetch", "extract this URL with felo"Do NOT use this skill for:
felo-search)felo-slides)Linux/macOS:
export FELO_API_KEY="your-api-key-here"
Windows PowerShell:
$env:FELO_API_KEY="your-api-key-here"
Script (from repo):
node .agents/skills/felo-web-fetch/scripts/run_web_fetch.mjs --url "https://example.com/article" [options]
Packaged CLI (after npm install -g felo-ai): same options, with short forms allowed:
felo web-fetch -u "https://example.com" [options]
# Short forms: -u (url), -f (format), -t (timeout, seconds), -j (json)
Required parameter:
--urlCore optional parameters:
--output-format html|markdown|text--crawl-mode fast|fine--target-selector "article.main-content"--wait-for-selector ".content-ready"Other key optional parameters:
--cookie "session_id=xxx" (repeatable)--set-cookies-json '[{"name":"sid","value":"xxx","domain":"example.com"}]'--user-agent "Mozilla/5.0 ..."--timeout 60 (HTTP request timeout in seconds)--request-timeout-ms 15000 (API payload timeout in ms)--with-readability true--with-links-summary true--with-images-summary true--with-images-readability true--with-images true--with-links true--ignore-empty-text-image true--with-cache false--with-stypes true--json (print full JSON response)When the user wants a specific part of the page or a specific output format, phrase the command like this:
--output-format text, --output-format markdown, or --output-format html.#main" / "Fetch only article.main-content" → use --target-selector "article.main" or the selector they give.Examples:
# Basic: fetch as Markdown
node .agents/skills/felo-web-fetch/scripts/run_web_fetch.mjs --url "https://example.com" --output-format markdown
# Article-style with readability
node .agents/skills/felo-web-fetch/scripts/run_web_fetch.mjs --url "https://example.com/article" --with-readability true --output-format markdown
# Only the element matching a CSS selector
node .agents/skills/felo-web-fetch/scripts/run_web_fetch.mjs --url "https://example.com" --target-selector "article.main" --output-format markdown
# With cookies and custom user-agent
node .agents/skills/felo-web-fetch/scripts/run_web_fetch.mjs --url "https://example.com/private" --cookie "session_id=abc123" --with-readability true --json
# Full JSON response
node .agents/skills/felo-web-fetch/scripts/run_web_fetch.mjs --url "https://example.com" --output-format text --json
curl -X POST "https://openapi.felo.ai/v2/web/extract" \
-H "Authorization: Bearer $FELO_API_KEY" \
-H "Content-Type: application/json" \
-d '{"url": "https://example.com", "output_format": "markdown", "with_readability": true}'
POST /v2/web/extracthttps://openapi.felo.ai. Override with FELO_API_BASE env if needed.Authorization: Bearer YOUR_API_KEY| Parameter | Type | Required | Default | Description |
|---|---|---|---|---|
| url | string | Yes | - | Webpage URL to fetch |
| crawl_mode | string | No | fast | fast or fine |
| output_format | string | No | html | html, text, markdown |
| with_readability | boolean | No | - | Use readability (main content) |
| with_links_summary | boolean | No | - | Include links summary |
| with_images_summary | boolean | No | - | Include images summary |
| target_selector | string | No | - | CSS selector for target element |
| wait_for_selector | string | No | - | Wait for selector before fetch |
| timeout | integer | No | - | Timeout in milliseconds |
| with_cache | boolean | No | true | Use cache |
| set_cookies | array | No | - | Cookie entries |
| user_agent | string | No | - | Custom user-agent |
Success (200):
{
"code": 0,
"message": "success",
"data": {
"content": { ... }
}
}
Fetched content is in data.content; structure depends on output_format.
| HTTP | Code | Description |
|---|---|---|
| 400 | - | Parameter validation failed |
| 401 | INVALID_API_KEY | API key invalid or revoked |
| 500/502 | WEB_EXTRACT_FAILED | Fetch failed (server or page error) |
--json when user needs metadata and full response object.Error response format:
## Web Fetch Failed
- Message: <error message>
- Suggested Action: verify URL/parameters and retry
.agents/skills/ 下。若 cwd 不在 repo root，先執行 git rev-parse --show-toplevel 取得路徑再 cd。禁止用 $(...) 語法。set -e、set -u、set -o、set -euo pipefail 等 set 指令${var@P}、${!var} 等參數展開語法$(...) 指令替換cd 與 node 指令，不要包在 shell 腳本控制流程內output_format: html, markdown, textcrawl_mode: fast, fine--target-selector when users only want a specific part of the page.--request-timeout-ms for page rendering/extraction wait, and --timeout for local HTTP timeout.--timeout.--with-cache false only when fresh content is required.