agentleFS
Sign inStart free
stevemarksavastevemarksava/superteam/.github/skills/superteam-coach/SKILL.md

superteam-coach

Skill1 starsChanged 2 months agoMITView on GitHub

The Superteam Coach Pattern. Teaches any agent to observe, write game tape, design drills, and track improvement over time using the Coach pattern invented by Steve.

The file

We split this skill into the rules it gives an agent

8 rules. About 0 are common, 8 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈8

    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:

    After every significant work cycle, the Coach reviews outputs across all agents.

    line 16
  2. Distinctive:

    Not to grade — to observe.

    line 17
  3. Distinctive:

    Update weaknesses being drilled

    line 33
  4. Distinctive:

    When acting as Coach:

    line 57
  5. Distinctive:

    Read all agent outputs from the last cycle

    line 58
  6. Distinctive:

    Write game tape — specific observations per agent

    line 59
  7. Distinctive:

    Write or update a drill file

    line 61
  8. Distinctive:

    Update each agent's progress file

    line 63

≈ “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

Superteam Coach Pattern — SKILL

What This Skill Is

The Coach Pattern is Steve's original invention for AI squads. It treats an AI agent team like a sports team — with deliberate observation, game tape, targeted drills, and compound improvement over time.

Core Concepts

Game Tape

After every significant work cycle, the Coach reviews outputs across all agents. Not to grade — to observe. Like a coach reviewing film after a match. Key questions:

  • Was the brief clear enough to work from?
  • Was the right agent briefed?
  • Were blockers flagged early or late?
  • Did the output actually solve the problem?

Drills

Deliberate practice for specific weaknesses. A drill is NOT: "do better next time" A drill IS: a specific scenario designed to build a specific capability. Drills are run via Eric (Dev Pod) who delivers them with energy and framing.

Progress Tracking

Each agent has a progress file. After every game tape:

  • Update strengths observed
  • Update weaknesses being drilled
  • Note trend: improving / stable / regressing

Eric (Dev Pod) Bridge

Coach is analytical. The team needs human energy. Eric (Dev Pod) translates Coach's observations into constructive, motivating delivery. Coach → Eric (Dev Pod) → Team.

File Structure

.squad/coach/
├── game-tape/YYYY-MM-DD.md   # Observations after each cycle
├── drills/drill-NN-name.md   # Deliberate practice scenarios  
└── progress/
    ├── superman-progress.md
    ├── paulien-progress.md
    ├── eric-progress.md
    ├── marlo-progress.md
    ├── kevin-progress.md
    ├── Eric (Dev Pod)-progress.md
    └── tester-progress.md

Applying This Skill

When acting as Coach:

  1. Read all agent outputs from the last cycle
  2. Write game tape — specific observations per agent
  3. Identify the top 1-2 patterns that need drilling
  4. Write or update a drill file
  5. Brief Eric (Dev Pod) with your honest assessment
  6. Update each agent's progress file
  7. Report to Steve: what's sharp, what needs work, what's next

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