Read Later
Skill35 starsChanged 4 days agoMITView on GitHub
Queue articles for later reading, and recall the queue on demand. 1. "Save this/read later" → read_later_add for the current page (or the URLs the user listed). The executor stores title, URL, and added-at time. 2. "What's on my reading list / show my queue" → read_later_list, then present items oldest-first (or newest-first if the user prefers). 3. Optionally add a one-line note per item from the page's own description. - Check the list before adding: if the URL is…
In this repository11 other files it gives its agents.
- Compare PricesSkill
- Deep ResearchSkill
- Extract DataSkill
- Fill FormSkill
- Find AlternativesSkill
- Manage BookmarksSkill
- Monitor PageSkill
- Organize TabsSkill
- Save PageSkill
- Screenshot WalkthroughSkill
- Summarize PageSkill
The file
We split this skill into the rules it gives an agent
2 rules. About 0 are common, 2 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈2
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 30
Check the list before adding: if the URL is already queued, say so and skip.
- Distinctive: line 31
Never auto-add more than the user asked for.
≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Read Later
Queue articles for later reading, and recall the queue on demand.
Procedure
- "Save this/read later" →
read_later_addfor the current page (or the URLs the user listed). The executor stores title, URL, and added-at time. - "What's on my reading list / show my queue" →
read_later_list, then present items oldest-first (or newest-first if the user prefers). - Optionally add a one-line note per item from the page's own description.
Tool discipline
- Check the list before adding: if the URL is already queued, say so and skip.
- Never auto-add more than the user asked for.
- Works fully offline in extension storage (and mirrors to the browser's reading list where available).
Answer format
📚 Added "Title" — 3 items in your queue now.
For list requests, a compact numbered list with titles + hosts.
Mirror in data: { "readingList": [...] }.
Verify before done
- Executor confirmed each add ({ ok: true }).
- Reported queue count matches the executor's list length.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

