agentleFS
Sign inStart free
calebnewtonusccalebnewtonusc/Chewbacca/skills/asa/SKILL.md

asa

Skill8 starsChanged 3 months agoMITView on GitHub

Answer from the A2A Spring 2026 course, 108 hours of workshops on building a business out of AI agents. Use when the user asks what the course said about something, references a week or module by number, asks how Callan or Carter taught a thing, or asks for the course's take on prompting, agent architecture, sales, marketing, operations, finance or building an AI employee. Also use when writing a new Chewbacca skill, to check whether the course already solved that problem.

The file

We split this skill into the rules it gives an agent

1 rule. About 0 are common, 0 are distinctive, and 1 is 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.

  • 1

    Very specific

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

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

    Not authority. The course is one group's opinion, recorded in 2026, and some of it is dated or is a pitch for the next program.

    line 55

≈ “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

asa

108 hours of recorded workshops from the A2A Spring 2026 course, indexed and searchable. 79 transcripts, 1.3 million words, published by the course as PDFs rather than reconstructed from audio, so speaker turns are real.

Never load a transcript

A single workshop runs 20,000 to 57,000 words. Loading one costs more than most answers are worth and crowds out everything else in the session. Search returns a passage and an offset; widen only the passage you need.

asa modules                                   # what exists
asa search "cold email sequence"              # ranked passages, 20 max
asa search "agent" --module week-3            # one module
asa show 09-week-3-ai-sales-department/01-workshop.md --at 48210

asa lives at asa/bin/asa.

Read the notes first

asa/notes/ holds a distilled file per module: what it teaches, the named frameworks with their steps, the prompting patterns, the architecture, and what is worth porting into Chewbacca. A note is a few thousand words against a transcript's fifty thousand, so start there and go to the transcript only when the note is thinner than the question.

asa/INDEX.md lists every module and session with its runtime and length.

Module map

Weeks 0 through 12 run in order, each with a workshop, office hours and three breakout rooms. Week 0 covers the AI architect mindset. Week 1 covers prompts, skills and AI workspaces. Weeks 2 through 5 and 8 through 9 each build one department: marketing, sales, operations, customer success, leadership, finance. Week 6 builds apps and dashboards. Week 7 is the unfair advantage. Week 10 is the business brain capstone. Week 11 covers scheduled tasks. Bonuses cover Notion, Claude design, Claude Code, HIPAA and SEO.

What this corpus is good for

Answering what the course actually taught, with a citation. Checking a framework's real steps before repeating a half-remembered version. Deciding whether a new Chewbacca skill is already solved here.

What it is not

Not authority. The course is one group's opinion, recorded in 2026, and some of it is dated or is a pitch for the next program. When it conflicts with the user's own rules in ~/.claude/rules/, his rules win. Say which source a claim comes from rather than blending them.

The transcripts are paid material and stay on this machine. Quote a sentence to make a point, never a passage, and never republish them.

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