summarise-url
Skill49 starsChanged 3 months agoMITView on GitHub
Fetch a URL and produce a structured summary with title, key points, and an action-oriented takeaway. Use when the user shares a link and asks for a summary, TL;DR, or "what's this about?".
We split this skill into the rules it gives an agent
5 rules. About 0 are common, 4 are distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈4
Distinctive · estimate
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 23
Keep summary to 100 words max
- Distinctive: line 33
Avoid hedging language ("seems to suggest").
- Very specific: line 37
Don't pretend you read more than was returned.
- Distinctive: line 38
Don't ignore the date — old articles may be outdated.
- Distinctive: line 39
Don't include section headers from the page verbatim — synthesise.
≈ “Common” is an estimate: at least 1 in 5 of the 308,232 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
Summarise URL
When to use
The user has shared a URL and wants a quick understanding without reading the whole thing.
Steps
- Fetch — use
browser_markdownto get the page as clean text. - Extract structure — produce a summary with:
- Title (1 line)
- Source (publisher, author if available, date)
- Summary (2-3 sentences capturing the main point)
- Key points (3-5 bullet points covering the substantive claims or arguments)
- Takeaway (1 sentence: what should the reader do or think differently?)
- Length-aware — if the page is very long (>3000 words):
- Keep summary to 100 words max
- Limit key points to 5 maximum
- Skip filler sections (related links, ads, comments)
- Use UI elements where helpful:
show_alertfor important caveats (paywall, opinion piece, sponsored content)offer_choicesat the end: "Read in full", "Find related articles", "Save to memory"
Style
- Be objective. If the article is opinionated, note that — don't echo its tone.
- Avoid hedging language ("seems to suggest"). Be direct.
- Preserve specific numbers and quotes that matter; paraphrase the rest.
What not to do
- Don't pretend you read more than was returned. If
browser_markdownreturns partial content, say so. - Don't ignore the date — old articles may be outdated.
- Don't include section headers from the page verbatim — synthesise.
In this repository32 other files it gives its agents.
- AGENTS.mdAGENTS.md
- docs/AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- agent-asks-tasksSkill
- caretakerSkill
- code-reviewSkill
- compare-optionsSkill
- create-reportSkill
- csv-analyseSkill
- document-qaSkill
- draft-emailSkill
- enrich-errorSkill
- extract-structured-dataSkill
- fact-checkSkill
- git-diff-summariserSkill
- librarian-curateSkill
- meeting-notesSkill
- morning-briefSkill
- plan-taskSkill
- reflectSkill
- remember-conversationSkill
- reverieSkill
- review-code-securitySkill
- review-email-toneSkill
- review-outputSkill
- review-summary-faithfulnessSkill
- rewrite-for-audienceSkill
- route-findingSkill
- routine-health-checkSkill
- save-research-docSkill
- score-importanceSkill
- web-researchSkill
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.

