agentleFS
Sign inStart free
Slava-codeSlava-code/college-kb/.claude/skills/exam-prep/SKILL.md

exam-prep

Skill0 starsChanged 30 days agoMITView on GitHub

Use when the student says "help me prep for the DEMO 101 midterm", "make a study plan for exam 2", "what's on the final", or asks for an exam countdown; builds an exam-prep silo page from the course page, notes, and materials.

9 other projects use a version of this.

Adopted by

Most recently taken up by

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 6 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. Very specific:

    If the LMS module is installed and configured on this machine (modules/lms-canvas/README.md.

    line 14
  2. Distinctive:

    If you fan out to subagents for anything, they read local files and use web search/fetch only.

    line 16
  3. Very specific:

    Link and remind: Add one line to the course page's Compiled Truth linking the prep page.

    line 25

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

exam-prep

AGENTS.md is canonical; this is the procedure. Write with the kb-write rules. The prep page is a silo next to the course page: exam-specific planning never gets folded into the course page beyond one link.

  1. Policy first. Read the course page's AI-use and collaboration policy and follow it. This skill organizes facts, coverage, and a schedule from the student's own materials. It does not write answers to graded or take-home work, and it does not produce exam content the policy forbids.
  2. Gate and orient. CLAUDE.local.md hostname match; git pull --rebase on the first write when a remote exists. Read school/courses/README.md, the course page, its course-notes pages, linked sources, and schema/templates/exam-prep.md (DEMO: school/courses/demo-101-midterm-1-prep.md). Check whether school/courses/<course-slug>-<exam>-prep.md (e.g. demo-101-midterm-1-prep, demo-101-final-prep) already exists; update it rather than starting a second one.
  3. Gather (read-only).
    • Exam facts from the course page: date, time, room, length, format, allowed materials (formula sheet, calculator), coverage, weight.
    • If the LMS module is installed and configured on this machine (modules/lms-canvas/README.md; python3 scripts/canvas-due.py --json for upcoming items): the exam's assignment entry and recent announcements, to confirm date, room, and coverage.
    • The local course workspace named in CLAUDE.local.md, if any: past exams, practice sets, review sheets. Do not copy them into the repo; cite them by name, or file one in raw/school/ with a manifest entry if the student wants it kept.
    • If you fan out to subagents for anything, they read local files and use web search/fetch only; no browser driving.
  4. Write school/courses/<course-slug>-<exam>-prep.md from the template (type: exam-prep, status: active):
    • Exam facts: each with [Source: ...]; conflicts recorded side by side.
    • Coverage map: topic → lectures, readings, notes pages (wikilinks), and practice problems.
    • Past-exam pattern (if past exams exist): points or question count per topic, recurring question types.
    • Formula sheet plan (only if one is allowed): what goes on it, size limit.
    • Countdown plan: concrete dated study blocks from today to the exam in REMINDER_TIMEZONE, weakest topics first, with a final review day and a buffer.
    • Questions for office hours: open items to ask the instructor or TA.
    • Timeline: - YYYY-MM-DD — prep page created and later dated updates.
  5. Link and remind. Add one line to the course page's Compiled Truth linking the prep page. Add the exam (and, if the student wants, study blocks) to reminders/YYYY.md as status: proposed-only · scheduler_ref: none unless they ask for real reminders.
  6. Check and commit. python3 scripts/kb-lint.py && python3 scripts/wikilink-check.py && python3 scripts/reminder-ledger-check.py; commit school: add <course-slug>-<exam>-prep (and reminders: schedule ... or reminders: record ... separately). Push only if asked or kb.autopush is on.
  7. After the exam (when the student reports it): add a Timeline line (how it went, score when known, with source), set status: resolved (the allowed statuses are in schema/templates/README.md), and record lessons for the next exam. The page stays; gardening may propose archiving it at term end.

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