refactor: convert web-fetch from skill to native tool

skills/skill-creator/SKILL.md

@@ -95,7 +95,7 @@ Do NOT create auxiliary documentation files:
 
 ## Installing a Skill from URL
 
-1. Fetch the URL content (curl or web-fetch skill)
+1. Fetch the URL content (curl or web_fetch tool)
 2. Extract `name` from YAML frontmatter
 3. Create directory `<workspace>/skills/<name>/` and save content as `SKILL.md`
 4. Check the saved SKILL.md for an installation/setup section — if it defines additional steps (e.g., downloading scripts, installing dependencies), execute them; otherwise installation is complete

skills/web-fetch/SKILL.md

@@ -1,56 +0,0 @@
----
-name: web-fetch
-description: Fetch and extract readable content from web pages. Use for lightweight page access without browser automation.
-homepage: https://github.com/zhayujie/chatgpt-on-wechat
-metadata:
-  emoji: 🌐
-  requires:
-    bins: ["curl"]
-  always: true
----
-
-# Web Fetch
-
-Fetch and extract readable content from web pages using curl and basic text processing.
-
-## Usage
-
-**Important**: Scripts are located relative to this skill's base directory.
-
-When you see this skill in `<available_skills>`, note the `<base_dir>` path.
-
-```bash
-# General pattern:
-bash "<base_dir>/scripts/fetch.sh" <url> [output_file]
-
-# Example (replace <base_dir> with actual path from skill listing):
-bash "~/chatgpt-on-wechat/skills/web-fetch/scripts/fetch.sh" "https://example.com"
-```
-
-**Parameters:**
-- `url`: The HTTP/HTTPS URL to fetch (required)
-- `output_file`: Optional file to save the output (default: stdout)
-
-**Returns:**
-- Extracted page content with title and text
-
-## Examples
-
-### Fetch a web page
-```bash
-bash "<base_dir>/scripts/fetch.sh" "https://example.com"
-```
-
-### Save to file
-```bash
-bash "<base_dir>/scripts/fetch.sh" "https://example.com" output.txt
-cat output.txt
-```
-
-## Notes
-
-- Uses curl for HTTP requests (timeout: 10s)
-- Extracts title and basic text content
-- Removes HTML tags and scripts
-- Works with any standard web page
-- No external dependencies beyond curl

skills/web-fetch/scripts/fetch.sh

@@ -1,54 +0,0 @@
-#!/usr/bin/env bash
-# Fetch and extract readable content from a web page
-
-set -euo pipefail
-
-url="${1:-}"
-output_file="${2:-}"
-
-if [ -z "$url" ]; then
-    echo "Error: URL is required"
-    echo "Usage: bash fetch.sh <url> [output_file]"
-    exit 1
-fi
-
-# Validate URL
-if [[ ! "$url" =~ ^https?:// ]]; then
-    echo "Error: Invalid URL (must start with http:// or https://)"
-    exit 1
-fi
-
-# Fetch the page with curl
-html=$(curl -sS -L --max-time 10 \
-    -H "User-Agent: Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36" \
-    -H "Accept: text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8" \
-    "$url" 2>&1) || {
-    echo "Error: Failed to fetch URL: $url"
-    exit 1
-}
-
-# Extract title
-title=$(echo "$html" | grep -oP '(?<=<title>).*?(?=</title>)' | head -1 || echo "Untitled")
-
-# Remove script and style tags
-text=$(echo "$html" | sed 's/<script[^>]*>.*<\/script>//gI' | sed 's/<style[^>]*>.*<\/style>//gI')
-
-# Remove HTML tags
-text=$(echo "$text" | sed 's/<[^>]*>//g')
-
-# Clean up whitespace
-text=$(echo "$text" | tr -s ' ' | sed 's/^[[:space:]]*//;s/[[:space:]]*$//')
-
-# Format output
-result="Title: $title
-
-Content:
-$text"
-
-# Output to file or stdout
-if [ -n "$output_file" ]; then
-    echo "$result" > "$output_file"
-    echo "Content saved to: $output_file"
-else
-    echo "$result"
-fi