Grab any URL and save it as beautifully formatted Obsidian-style Markdown. Powered by x-reader for content extraction.
text
/1coos-quickie <text-containing-url> [--output-dir path] [--raw]
ParameterRequiredDescription<text>YesAny text containing a URL to fetch--output-dirNoOutput directory (default: from config.json)--rawNoSkip formatting, output raw x-reader result--configNoPath to config.json
Core parameters are configurable via config.json in the skill directory:
json
{
"outputDir": "~/Documents/quickie",
"formatting": {
"maxWidth": 80,
"listMarker": "-"
},
"reader": {
"timeout": 120000
}
}
CLI arguments always override config.json values.
This skill runs third-party code at runtime:
When the user invokes this skill:
Check prerequisites: Verify uvx is available by running which uvx. If missing, tell the user: "uvx is required but not found. Please install uv from https://docs.astral.sh/uv/getting-started/installation/ and try again." Do NOT run any install commands on behalf of the user.
Run extraction: Execute the script using the skill's absolute path: bash
bun run /path/to/skills/1coos-quickie/scripts/main.ts <user-arguments>
Report results: Show the output file path, the extracted title, and a brief content summary.
Handle errors:
bash
# Grab a YouTube video transcript
/1coos-quickie https://www.youtube.com/watch?v=dQw4w9WgXcQ
# Save a tweet thread
/1coos-quickie 看看这条推特 https://x.com/user/status/123456 很有意思
# Clip an article with custom output
/1coos-quickie https://example.com/article --output-dir ~/notes/inbox
# Raw output without formatting
/1coos-quickie https://example.com/page --raw
x-reader[all] for full platform support