I pointed Cowork at my til/ folder full of TIL drafts and asked it to "look at my drafts that were started within the last three months and then check that I didn't publish them on simonwillison.net using a search against content on that site and then suggest the ones that are most close to being ready". It ran a find command to identify 46 drafts modified in the past 90 days, then ran 44 independent Google searches - one for each - to check if they'd been published. It identified three ready-to-publish drafts: - "Frequently Argued Questions about LLMs" (22,602 bytes) - "Claude Code Timeline and Codex Timeline" (3,075 bytes) - "Datasette 1.0a20 Plugin Upgrade Instructions" (3,147 bytes) I love that it used file size as a proxy for "most ready" - a reasonable heuristic. This is a genuinely useful capability. I have dozens of half-finished drafts and now I have a tool that can help me figure out which ones are worth finishing first.
🔍 Research X (Twitter)
Blog Draft Discovery and Publication Check
Simon Willison had Claude scan 46 draft files, run 44 web searches, to find the most ready-to-publish unpublished blog posts
★★☆ Intermediate 5-10 min January 12, 2026
📋
Scenario
As a tech blogger, I have a folder with many accumulated drafts. I want to know which drafts haven't been published yet and which are closest to completion.
💬
Prompt
Look at my drafts that were started within the last three months and then check that I didn't publish them on simonwillison.net using a search against content on that site and then suggest the ones that are most close to being ready.
✨
Expected Result
Claude executed these steps: 1. Ran `find` command to identify 46 draft files modified within 90 days 2. Ran 44 independent web searches (`site:simonwillison.net`) to check publication status 3. Identified three drafts closest to completion: - "Frequently Argued Questions about LLMs" (22,602 bytes) - "Claude Code Timeline and Codex Timeline" (3,075 bytes) - "Datasette 1.0a20 Plugin Upgrade Instructions" (3,147 bytes)
💡
Tips
- • Claude automatically uses file size as a proxy for completion level
- • Web search can verify if content was published elsewhere
- • Can specify more specific time ranges
