cog-url-extraction
Save URLs with auto-extracted insights, credibility scoring, and vault routing
npx skills add a5c-ai/babysitter --skill url-extraction --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
- Extract: title, summary, key takeaways, relevant quotes - Assess source credibility and assign confidence levels - Classify extracted insights by domain - Route insights to appropriate vault sections - Create cross-references to related vault entries ## Tool Use Instructions 1. Use `web-fetch` to retrieve URL content 2. Extract key insights: title, summary, takeaways, quotes 3. Assess source credibility using domain reputation and content quality 4. Use `file-read` to find related existing vault entries 5. Use `file-write` to store extracted insights in markdown format 6. Add cross-references to related entries 7. Use `git-commit` to commit extracted insights ## Examples ```json { "vaultPath": "./cog-vault", "captureType": "url-dump", "urls": [ "https://example.com/interesting-article", "https://blog.example.com/deep-dive-post" ], "targetQuality": 80 } ```
- Tool Use Instructions
- Examples
What does the cog-url-extraction skill do?
Save URLs with auto-extracted insights, credibility scoring, and vault routing
How do I install it?
Run `npx skills add a5c-ai/babysitter --skill url-extraction --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From a5c-ai/babysitter, a repository with 1,642 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.