agentleFS
Sign inStart free
bisque-cloudbisque-cloud/presenter/AGENTS.md

presenter

AGENTS.md40 starsChanged 9 days agoMITView on GitHub

Instructions for AI coding agents working in this repository. Three skills a coding agent installs to use Bisque: present (make a presentation people can watch and publish it), watch (read a published one as text), and video (render one to MP4). Each lives in skills/<name>/ as a SKILL.md plus scripts. Install with npx skills add bisque-cloud/presenter. - Read skills/<name>/SKILL.md in full before running a skill; it is the runbook, in the order the steps must happen. - Fetch the authoring…

  • Where files are headingNew AGENTS.md files have more rules about keeping secrets out of the code, and fewer about code style.

    Of the AGENTS.md files we read, the 31,843 first seen in the last six months, against the older ones: the kind of rule that gained most share, and the kind that lost most. About files like this in general, not this one, and an estimate, since a kind is a pattern in the words.

  • In this repository3 other files it gives its agents.

The file

We split this AGENTS.md into the rules it gives an agent

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

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈0

    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
  1. Very specific:

    Read skills/<name>/SKILL.md in full before running a skill.

    line 15
  2. Very specific:

    Keep SKILL.md frontmatter valid per agentskills.io: name matches the directory, description says what the skill does and when to use it.

    line 29

≈ “Common” is an estimate: at least 1 in 5 of the 40,246 AGENTS.md 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
AGENTS.md

AGENTS.md

Instructions for AI coding agents working in this repository.

What this repo is

Three skills a coding agent installs to use Bisque: present (make a presentation people can watch and publish it), watch (read a published one as text), and video (render one to MP4). Each lives in skills/<name>/ as a SKILL.md plus scripts. Install with npx skills add bisque-cloud/presenter.

Using the skills from an agent

  • Read skills/<name>/SKILL.md in full before running a skill; it is the runbook, in the order the steps must happen.
  • Fetch the authoring format from https://bisque.today/api/presentations/spec every time. Never write the html-presentation/v1 format from memory.
  • sdk/ is @bisquecloud/sdk, the TypeScript client for the REST API. Its tests run with bun test sdk/; bun run build in sdk/ emits dist/.
  • The REST API is described at https://bisque.today/openapi.json; the same tools are available over MCP at https://bisque.today/mcp. How to get a credential: https://bisque.today/auth.md.
  • Reading a public or unlisted presentation needs no credential: GET https://bisque.today/api/presentations/context?url=<watch URL>.

Editing this repo

  • Keep SKILL.md frontmatter valid per agentskills.io: name matches the directory, description says what the skill does and when to use it.
  • Scripts are JavaScript (.mjs) or TypeScript; no Python.
  • Say "presentation", never "deck" or "slideshow", in prose. Trigger lists in a description may carry the words people type.

Where things are

PathWhat it is
skills/present/Author, narrate locally, publish
skills/watch/Read a presentation's transcript and context
skills/video/Export a published presentation to MP4
.claude-plugin/Plugin manifest for plugin-aware agents
cowork/The same skill for agents in a hosted sandbox that cannot narrate locally; publishes through the MCP connector

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