agentleFS
Sign inStart free
junho5400junho5400/cramcode/.claude/skills/teach/SKILL.md

teach

Skill1 starsChanged 4 months agoMITView on GitHub

Run a cramcode worked-example teaching session on the recommended (or requested) problem — interview-style derivation from brute force to optimal, then log exposure evidence. Use after /next, or when the user asks to be taught a problem or topic.

193 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use setup-pstack, principle-explain-the-number 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.
  • bnemaSkill

    setup-pstack

    Configure which Pi models pstack uses per role. Detects available provider/model specs and writes pstack's user configuration. Use for /setup-pstack, "configure pstack models", or changing pstack model choices.

    Also in 22 projects that use this

  • ianclearySkill

    principle-explain-the-number

    Apply before you trust, report, or act on a number you measured: a speedup, a regression, a throughput, a latency, or an eval result. Find what limits it, and rule out that it measured something other than the work you think.

    Also in 25 projects that use this

  • jaydubya818Skill

    poteto-mode

    Use when non-trivial work should follow the smallest rigorous Jstack workflow.

    Also in 27 projects that use this

  • eryzerzSkill

    make-bot-ui

    Use when building a custom UI (page, dashboard, buttons) that should wake a Grok Bot over a webhook, when the user must provide a webhook sender key, or when exposing that UI on Tailscale.

    Also in 17 projects that use this

  • jaydubya818Skill

    principle-never-block-on-the-human

    Apply when safe reversible implementation details can proceed inside scope.

    Also in 36 projects that use this

  • ianclearySkill

    poteto-help

    Guides users through pstack setup, /poteto-mode, and picking the skill, playbook, or principle for a task. Type /poteto-help with a question.

    Also in 12 projects that use this

  • +6 more from jaydubya818

The file

We split this skill into the rules it gives an agent

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

  • 0

    Common

    Most of the 161 edited versions we read keep these.

  • 1

    Distinctive

    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. Distinctive:

    Follow PROTOCOL.md § "Teach protocol" exactly.

    line 8
  2. Very specific:

    Write evidence to memory/.staging/evidence.json:

    line 33
  3. Very specific:

    Run python3 scripts/log_episode.py and show the confidence deltas.

    line 37

“Common” is measured: kept by at least 6 in 10 of the 161 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

/teach — the worked example

Follow PROTOCOL.md § "Teach protocol" exactly. Compressed here:

Before teaching, load context (all three, always):

  1. The plan: use the current /next recommendation, or the user's requested problem. Resolve the problem via curriculum/problems/<topic>.json.
  2. The KCs: read curriculum/topics/<topic>.json — the target KCs' insight, signals, pitfalls are your teaching script.
  3. The learner: read memory/profile.json. Adapt (more prediction checkpoints for approach-first strugglers; extra emphasis where an observation names a recurring bug that this problem's pitfalls touch).

Teach in interview shape: paraphrase the problem (never verbatim; link the URL) → model the clarifying questions → brute force WITH complexity → ask the user to spot the bottleneck and wait for their answer → deliver the insight, quoting the KC's insight line → implement cleanly, flagging each KC pitfall at the line where it bites → close with complexity and the takeaway list.

Show, don't just describe. For spatial/stateful algorithms (pointers, windows, stacks, trees, DP tables, graph traversals) build a stepper visual at the insight step — frames spec per PROTOCOL.md § Visuals, rendered via python3 scripts/visualize.py. The frames ARE the derivation: brute-force waste → the insight fixing it → the invariant holding. Skip in phone/cloud sessions (no browser).

Then, immediately:

  1. Write evidence to memory/.staging/evidence.json:
    • type: "teach", the problem slug, verdicts = every KC you actually taught, each {"verdict": "exposed"} — teach sessions can never claim more than exposure, regardless of how well the checkpoints went.
  2. Run python3 scripts/log_episode.py and show the confidence deltas.
  3. Offer the paired test problem: "ready to try <test problem> yourself? (/test)" — same KCs, fresh problem, per the pairing in the curriculum.

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