agentleFS
ajstars1ajstars1/founder-stack/learn/SKILL.md

learn

Skill1 starsChanged 17 days agoMITView on GitHub

Tutor for the founder-stack frameworks (GTM, branding, marketing, sales, customer discovery). One concept at a time, applied to your venture, with spaced-repetition quizzes. Use for "teach me…", "quiz me…", "next lesson", "what's due", "explain <framework>".

195 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use add-anydoc, add-clidash and 10 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • TomGranotSkill

    add-anydoc

    Add local office-document-to-Markdown conversion to NanoClaw agent containers with the pinned Firecrawl AnyDoc CLI. Use when agents need to read attached Word, PowerPoint, Excel, OpenDocument, RTF, EPUB, CSV, or text-based PDF files without uploading them to a hosted parser.

    Also in 5 projects that use this

  • TomGranotSkill

    add-clidash

    Add clidash — a zero-dependency, read-only web dashboard that derives its tabs and tables at runtime from any CLI that lists resources as JSON. Ships pre-wired for NanoClaw's ncl CLI (agent groups, sessions, channels, users, roles), plus message-activity charts, a log tail, and a read-only file viewer for group skills/CLAUDE.md/profiles.

    Also in 5 projects that use this

  • seek888Skill

    open-gstack-browser

    Launch GStack Browser — AI-controlled Chromium with the sidebar extension baked in. Opens a visible browser window where you can watch every action in real time. The sidebar shows a live activity feed and chat. Anti-bot stealth built in. Use when asked to "open gstack browser", "launch browser", "connect chrome", "open chrome", "real browser", "launch chrome", "side panel", or "control my browser". Voice triggers (speech-to-text aliases): "show me the browser".

    Also in 11 projects that use this

  • Saqlain-811Skill

    ios-sync

    Regenerate the iOS debug bridge against the latest upstream gstack templates. (gstack)

    Also in 6 projects that use this

  • MicrosoftSkill

    add-codex

    Use Codex (CLI + AppServer) as the full agent provider — planning, tool orchestration, native compaction, MCP tools, session resume — in place of the Claude Agent SDK. ChatGPT subscription or OPENAI_API_KEY. Per-group via agent_provider. Distinct from using OpenAI as an MCP tool (where Claude remains the planner).

    Also in 6 projects that use this

  • MicrosoftSkill

    add-deltachat

    Add DeltaChat channel integration via @deltachat/stdio-rpc-server. Native adapter — no Chat SDK bridge. Email-based messaging with end-to-end encryption.

    Also in 6 projects that use this

  • +5 more from TomGranot
  • +1 more from microsoft

The file

We split this skill into the rules it gives an agent

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

  • 0

    Common

    Most of the 170 edited versions we read keep these.

  • 2

    Distinctive

    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:

    Teach it in 250 words or fewer: Read only that playbook. Cover:

    line 29
  2. Distinctive:

    Make them use it: Ask one application question about their own business, then wait.

    line 33
  3. Very specific:

    Deep read (optional): if the business-books MCP is connected, the learner can study an original chapter.

    line 47

“Common” is measured: kept by at least 6 in 10 of the 170 edited versions of this file we could read. “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

Learn

A tutor built on learning science: short lessons, retrieval practice, spaced review, and every concept applied to the learner's own business. The lessons come from the founder-stack playbooks.

State

  • Progress lives in ~/.founder-stack/progress.md. Create it from the format below if it's missing.
  • The curriculum is in curriculum.md. Read only the path for the domain being studied.
# Learning progress
| concept | playbook | status | last | next | note |
|---|---|---|---|---|---|
| Competitive alternatives | gtm/positioning | learning | 2026-10-20 | 2026-10-23 | confused alternatives with competitors |

Status goes new → learning → solid. Review intervals are 1 → 3 → 7 → 21 → 60 days. A miss resets the interval to 1 day.

Session loop

  1. Reviews first. For each concept whose next date is today or earlier, ask one question, then wait. Mix the two kinds: recall ("what are the three…") and transfer ("your rival just cut prices by 30%; which move does the playbook suggest, and why?"). Grade the answer against the playbook in one or two lines. Ask at most 3 reviews per session.
  2. Pick the next concept. Take the learner's request, or the next new item in the curriculum.
  3. Teach it in 250 words or fewer. Read only that playbook. Cover:
    • what the idea is, in plain words, credited [Author];
    • why it works;
    • how it plays out in the learner's venture (read discovery/00-CONTEXT.md if it exists).
  4. Make them use it. Ask one application question about their own business, then wait. Give feedback against the playbook's method and rules of thumb. For central concepts, ask for a teach-back: "explain it as you'd explain it to a new teammate."
  5. Update progress. Advance or reset the interval, and write a one-line note on what they got wrong.
  6. Close. Tell them what's due next time. If an answer produced a real business decision, offer to log it in the ledger through /founder-stack.

Rules

  • One question at a time. Never lecture past 250 words. Never give the answer before they try.
  • Quiz from the playbooks, never from memory of the books. If a playbook doesn't cover something, say so.
  • Be specific about the gap ("you named the alternative but not the budget it comes from") rather than generic ("good try").
  • Deep read (optional): if the business-books MCP is connected, the learner can study an original chapter. Use get_toc and read_section, then summarise it, pull out 3 key ideas, and ask 3 questions. Cite pages here, because this is where page numbers matter.

Commands

teach me <domain|playbook|framework> · quiz me on <domain> · next lesson · what's due · deep-read <book> <chapter> (MCP only) · my progress

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.