feat: improve the memory system

skills/skill-creator/SKILL.md

@@ -214,6 +214,19 @@ These files contain established best practices for effective skill design.
 
 To begin implementation, start with the reusable resources identified above: `scripts/`, `references/`, and `assets/` files. Note that this step may require user input. For example, when implementing a `brand-guidelines` skill, the user may need to provide brand assets or templates to store in `assets/`, or documentation to store in `references/`.
 
+**Available Base Tools**:
+
+The agent has access to these core tools that you can leverage in your skill:
+- **bash**: Execute shell commands (use for curl, ls, grep, sed, awk, bc for calculations, etc.)
+- **read**: Read file contents
+- **write**: Write files
+- **edit**: Edit files with search/replace
+
+**Minimize Dependencies**:
+- ✅ **Prefer bash + curl** for HTTP API calls (no Python dependencies)
+- ✅ **Use bash tools** (grep, sed, awk) for text processing
+- ✅ **Keep scripts simple** - if bash can do it, no need for Python (document packages/versions if Python is used)
+
 **Important Guidelines**:
 - **scripts/**: Only create scripts that will be executed. Test all scripts before including.
 - **references/**: ONLY create if documentation is too large for SKILL.md (>500 lines). Most skills don't need this.

skills/web-fetch/SKILL.md

@@ -0,0 +1,49 @@
+---
+name: web-fetch
+description: Fetch and extract readable content from web pages
+homepage: https://github.com/zhayujie/chatgpt-on-wechat
+metadata:
+  emoji: 🌐
+  requires:
+    bins: ["curl"]
+---
+
+# Web Fetch
+
+Fetch and extract readable content from web pages using curl and basic text processing.
+
+## Usage
+
+Use the provided script to fetch a URL and extract its content:
+
+```bash
+bash scripts/fetch.sh <url> [output_file]
+```
+
+**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 scripts/fetch.sh "https://example.com"
+```
+
+### Save to file
+```bash
+bash scripts/fetch.sh "https://example.com" output.txt
+cat output.txt
+```
+
+## Notes
+
+- Uses curl for HTTP requests (timeout: 20s)
+- 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

@@ -0,0 +1,54 @@
+#!/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=$(curl -sS -L --max-time 20 \
+    -H "User-Agent: Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36" \
+    -H "Accept: text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8" \
+    "$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