agentleFS
Sign inStart free
surfmind-spacesurfmind-space/awesome-surfmind/skills/answer/SKILL.md

answer

Skill8 starsChanged 5 months agoMITView on GitHub

Answers a question grounded in the selected text or visible page, researching further when the page falls short, always evidence-backed and never invented. Use when the user highlights a passage or is on a page and asks "what does this mean", "answer this", "where does it say", or any who/what/why/how question about that content.

1 other project uses a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

3 rules. About 0 are common, 3 are distinctive, and 0 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.

  • 0

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Start from the selected or visible page content.

    line 16
  2. Distinctive:

    If the page doesn't cover enough, gather more: use web search or any suitable MCP/tool available to research the topic, then base the …

    line 17
  3. Distinctive:

    If web search is disabled and no suitable tool is available, answer only what the context supports and clearly state what's missing or …

    line 18

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 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

Answer

Give an evidence-backed answer. Never invent facts, quotes, numbers, or sources, and never present a guess as if it were established.

  1. Start from the selected or visible page content. That is the primary evidence. If it fully answers the question, answer directly and point to where it comes from.
  2. If the page doesn't cover enough, gather more: use web search or any suitable MCP/tool available to research the topic, then base the answer on what you find and name the source.
  3. If web search is disabled and no suitable tool is available, answer only what the context supports and clearly state what's missing or unverified.

Match the answer's length to the question.

Example

Question: "What's the refund window?"

  1. Page states it: "Refunds are available within 30 days of purchase (stated on this page)."
  2. Page is silent, search available: research it, then "Per the vendor's Terms of Service, refunds are within 14 days. [link]"
  3. Page silent, no search or tools: "This page explains how to request a refund but doesn't give a time limit, and I can't look it up right now. Check the full Terms for the exact window."

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.

Check your setup, free