agentleFS
MicrosoftKnown publishermicrosoft/aibast-agents-library/llms.txt

aibast-agents-library

llms.txt8 starsChanged 3 months agoMITView on GitHub

Everything in the AIBAST Agents Library as static JSON, for AI agents first and people second: each solution, its demo, how to get it, how to learn it and its proof. Demo with sample data only. It is not connected to your organization's data, and it should not be. Site: https://microsoft.github.io/aibast-agents-library/ Raw fallback: https://raw.githubusercontent.com/microsoft/aibast-agents-library/main/

The file

We split this llms.txt into the rules it gives an agent

2 rules. About 0 are common, 1 is distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    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
  1. Distinctive:

    Every answer is a recorded sample answer.

    line 23
  2. Very specific:

    Read get.prompt in the solution document, replace {pages} with https://microsoft.github.io/aibast-agents-library/, and follow it.

    line 26

≈ “Common” is an estimate: at least 1 in 5 of the 3,592 llms.txt 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
llms.txt
# AIBAST Agents Library API

> Everything in the AIBAST Agents Library as static JSON, for AI agents first and people second: each solution, its demo, how to get it, how to learn it and its proof.

Demo with sample data only. It is not connected to your organization's data, and it should not be.

Site: https://microsoft.github.io/aibast-agents-library/
Raw fallback: https://raw.githubusercontent.com/microsoft/aibast-agents-library/main/

## Start here
- https://microsoft.github.io/aibast-agents-library/paths.html: choose a path with a shareable preview before starting.
- https://microsoft.github.io/aibast-agents-library/api/v1/paths.json: questions, prerequisite checks and every tutorial destination.
- https://microsoft.github.io/aibast-agents-library/api/v1/index.json: where to start, counts and every endpoint.
- https://microsoft.github.io/aibast-agents-library/api/v1/search.json: one line per solution (72). Find the right one here.
- https://microsoft.github.io/aibast-agents-library/api/v1/solutions/<slug>.json: everything about one solution: what it is, try it, get it, learn it, proof.
- https://microsoft.github.io/aibast-agents-library/api/v1/scenarios/<id>.json: one demo question with its recorded answer (384 recorded).
- https://microsoft.github.io/aibast-agents-library/api/v1/media/index.json: every screenshot and narration clip, by solution, with sha256. These files are served from https://raw.githubusercontent.com/microsoft/aibast-agents-library/main/ (pinned to the published commit), not from Pages.
- https://microsoft.github.io/aibast-agents-library/solutions/_shared/aibast-sdk.js: one script for pages (AibastLibrary, AibastMedia, AibastDemo); guide in docs/sdk.md.
- https://microsoft.github.io/aibast-agents-library/api/registry.json: every endpoint with its SHA-256 and a permanent copy under api/versions/.

## To show a solution
Open the solution's try.page. It plays the recorded demo in Microsoft 365 Copilot, Cowork or Copilot Studio.
Every answer is a recorded sample answer. Questions outside the recorded ones are not answered.

## To deploy a solution
Read get.prompt in the solution document, replace {pages} with https://microsoft.github.io/aibast-agents-library/, and follow it.
It asks the user once before changing anything. Check every download against its sha256.

## Learn RAPP step by step
- https://microsoft.github.io/aibast-agents-library/api/v1/rapp/index.json: the 14 RAPP production steps, 33 concepts, glossary and experimental tools.
- https://microsoft.github.io/aibast-agents-library/api/v1/rapp/steps/<n>.json: step n (1-14): do (what to do), get (what you get), proof (how you know), explain (the longer note).
- https://microsoft.github.io/aibast-agents-library/api/v1/rapp/concepts/<slug>.json, https://microsoft.github.io/aibast-agents-library/api/v1/rapp/glossary.json, https://microsoft.github.io/aibast-agents-library/api/v1/rapp/tools.json.
To teach a step, read its document and explain do, get and proof in plain words. Each document lists its source files with sha256.

## Public Microsoft content
- https://microsoft.github.io/aibast-agents-library/api/v1/public/index.json: values read exactly from public Microsoft pages, each with its source URL and sha256. First: api/v1/public/copilot-credit-rates.json (planning estimate, not a price quote).

## Rules
- Sample data only. Never connect a library solution to an organization's own data.
- Same-site reads use relative paths. Do not bypass the cache.

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.