agentleFS
mementomori-comementomori-co/maker-mastery/.claude/skills/curriculum/SKILL.md

curriculum

Skill2 starsChanged 25 days agoMITView on GitHub

Use when the maker asks where the learning stands or what to study next. Reads CURRICULUM.md and the knowledge indexes, then reports progress per domain and the next three topics; writes nothing.

3 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

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:

    Read CURRICULUM.md; count [x] and [ ] per category and per domain.

    line 13

≈ “Common” is an estimate: at least 1 in 5 of the 372,429 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

Overview

Report progress from CURRICULUM.md and the index.md in each knowledge\ category, filtered to $ARGUMENTS when given. Read-only: no file is written; the output is the reply. A tick in CURRICULUM.md is changed only by the librarian when a note is filed.

When to use

Session-start reviews, "what next", before choosing a /research-topic. Not for ticking boxes (librarian via /file) and not for build planning.

Steps

  1. Read CURRICULUM.md; count [x] and [ ] per category and per domain. Cross-check every [x] against a note listed in that category's knowledge\<NN-category>\index.md; report a tick with no note as "tick without note" (never silently accept it).
  2. List the unticked lines for the lowest-progress categories, printing and slicing categories first, then the categories the maker's active projects need (ask if unknown).
  3. Pick the next three topics: each an unticked curriculum line with its category and a one-line question that /research-topic can take verbatim.
  4. Reply:
    # Curriculum status <YYYY-MM-DD>
    | domain | categories | ticked / total | notes on disk |
    Ticks without a note: <none | item: expected note path>
    Next 3: 1. <category> - <question> . 2. ... . 3. ...   (rule that picked them: <priority order>)
    NEEDS MAKER: <numbered, when a priority choice is the maker's>
    This reply goes straight to the owner: use the name, marker and closing parts from OWNER_PROFILE.md (CLAUDE.md, "Who you work for").

Common rationalizations

RationalizationReality
"The box is ticked, so it is known."Ticks seeded from memory turn out wrong. A tick needs a note listed in the category index.
"Tick it now, the note is nearly done."Only the librarian ticks, only after check_note.py PASS.
"Next topic: whatever is interesting."Name the priority rule that picked each topic.

Red flags

  • A progress number not derived from counting the file.
  • A next topic not tied to a curriculum line.
  • Any write to CURRICULUM.md.

Verification

  • Counts per domain quoted from CURRICULUM.md.
  • Every [x] reconciled with a category index.md.
  • Three next topics, each tied to a curriculum line.
  • No file modified.

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.