Save Page
Skill35 starsChanged 4 days agoMITView on GitHub
Archive the current page as a real file the user can keep offline. 1. Default to full-page archive: call save_page (MHTML). It captures the current tab exactly as rendered, downloads go to the user's Downloads folder, and the executor returns the saved filename. 2. If the user asked for a picture (or the page is a canvas/map/visualization), use screenshot_save with a short label instead. 3. Report exactly where the file went and what it contains. - One save per request…
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
- Read LaterSkill
- Screenshot WalkthroughSkill
- Summarize PageSkill
The file
We split this skill into the rules it gives an agent
4 rules. About 0 are common, 2 are distinctive, and 2 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.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 22
Default to full-page archive: call save_page (MHTML).
- Very specific: line 25
If the user asked for a picture (or the page is a canvas/map/visualization), use screenshot_save with a short label instead.
- Distinctive: line 32
If the save fails (e.g. chrome:// pages cannot be captured), explain why and suggest a screenshot as fallback.
- Distinctive: line 34
Never re-navigate before saving — save the page in its current state.
≈ “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
Save Page
Archive the current page as a real file the user can keep offline.
Procedure
- Default to full-page archive: call
save_page(MHTML). It captures the current tab exactly as rendered, downloads go to the user's Downloads folder, and the executor returns the saved filename. - If the user asked for a picture (or the page is a canvas/map/visualization),
use
screenshot_savewith a shortlabelinstead. - Report exactly where the file went and what it contains.
Tool discipline
- One save per request — do not produce both formats unless asked.
- If the save fails (e.g. chrome:// pages cannot be captured), explain why and suggest a screenshot as fallback.
- Never re-navigate before saving — save the page in its current state.
Answer format
💾 Saved "<title>" as <filename> (MHTML archive, Downloads folder).
Mirror in data: { "file": filename }.
Verify before done
- Executor returned
{ ok: true, filename }— never claim a save happened without that confirmation.
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.

