agentleFS
princechouhan19princechouhan19/OpenCometAI/skills/summarize-page/SKILL.md

Summarize Page

Skill35 starsChanged 4 days agoMITView on GitHub

Summarize the page the user is already on. Text-first, zero-navigation by default. 1. Read Readable page text and Headings from the structured page data FIRST. Do not take a screenshot-driven approach unless text is empty or navigation is required. 2. If the content is longer than the visible excerpt, use ONE scroll to bottom, then one extract on the main content container if more detail is needed. 3. Identify: main topic, 3–7 key facts or arguments, data points, and the…

The file

We split this skill into the rules it gives an agent

6 rules. About 0 are common, 3 are distinctive, and 3 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈3

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 3

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Read Readable page text and Headings from the structured page data FIRST.

    line 23
  2. Distinctive:

    Do not take a screenshot-driven approach unless text is empty or navigation is required.

    line 24
  3. Very specific:

    If the content is longer than the visible excerpt, use ONE scroll to bottom, then one extract on the main content container if more detail …

    line 25
  4. Distinctive:

    NEVER navigate away from the page for a plain summary — everything needed is on the page.

    line 32
  5. Very specific:

    Prefer extract over repeated scrolling.

    line 33
  6. Distinctive:

    If the page is a paywall/login wall with no readable text, say so in the answer and stop.

    line 34

≈ “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.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Summarize Page

Summarize the page the user is already on. Text-first, zero-navigation by default.

Procedure

  1. Read Readable page text and Headings from the structured page data FIRST. Do not take a screenshot-driven approach unless text is empty or navigation is required.
  2. If the content is longer than the visible excerpt, use ONE scroll to bottom, then one extract on the main content container if more detail is needed.
  3. Identify: main topic, 3–7 key facts or arguments, data points, and the conclusion or call-to-action.
  4. Return done with a structured answer.

Tool discipline

  • NEVER navigate away from the page for a plain summary — everything needed is on the page.
  • Prefer extract over repeated scrolling. One scroll to bottom is the maximum.
  • If the page is a paywall/login wall with no readable text, say so in the answer and stop.

Answer format

**Topic:** one line
**Key points:** 3–7 bullets, each one line
**Details worth noting:** numbers, dates, names (only if present)
**Bottom line:** one sentence

Verify before done

  • The answer cites facts that actually appear in the page text — never invent content.
  • Under 300 words.

Download now (ZIP)

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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.