agentleFS
erikunhaerikunha/vault-of-loci/.agents/skills/dependency-check/SKILL.md

dependency-check

Skill0 starsChanged 5 days agoMITView on GitHub

Check the prerequisites of a concept against the ledger before the learner moves on, say in one line which prerequisite is missing, and work on that one first; use it before the learner starts a new concept, and it writes a file, so run it only when asked.

10 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

7 rules. 0 are common, 6 are distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 8 edited versions we read keep these.

  • 6

    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:

    Run the check and read it.

    line 12
  2. Very specific:

    Read the map. The script reads the "Needs first" column of the concept map of each track (10_Tracks/<NN>_<Track>/practice/Concept_Map.md) …

    line 18
  3. Distinctive:

    If there is a gap, say in one line which prerequisite is missing.

    line 30
  4. Distinctive:

    If the answer is wrong, or the learner asks to try again, use the hint ladder one step at a time: hint, strong hint, partial example, …

    line 47
  5. Distinctive:

    Ask for confidence from 1 to 5 before the reveal.

    line 49
  6. Distinctive:

    Run the check again when the prerequisite is done, and say whether the new concept is ready.

    line 61
  7. Distinctive:

    Never rewrite the concept map of the track.

    line 62

“Common” is measured: kept by at least 6 in 10 of the 8 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

Tutor mode: the learner attempts first and without notes. The agent never writes the learner's notes or answers. Hints come one step at a time and only after an attempt: hint, strong hint, partial example, answer. Confidence from 1 to 5 is asked before the reveal. The agent never grades an attempt the learner did not confirm.

  1. Run the check and read it.
python3 -I 90_System/Scripts/dependency_check.py
  1. Read the map. The script reads the "Needs first" column of the concept map of each track (10_Tracks/<NN>_<Track>/practice/Concept_Map.md) and the edges of the canvases in 30_Maps, then joins them with the ledger. For each concept it prints the prerequisites and the state of each one: never studied, never tested, only tested with help, only graded by the agent, mistake not recovered, not tested for N days or ok, and the next step each state asks for. A concept with a gap is not ready.
python3 -I 90_System/Scripts/dependency_check.py --target <name>
python3 -I 90_System/Scripts/dependency_check.py --json
  1. If there is a gap, say in one line which prerequisite is missing. Then work on that prerequisite first and leave the new concept for later. Do not move on to the new concept while a gap is open.
  2. Work the prerequisite the way the record asks for it. The state names the next step, and the states are not the same problem:
    • never studied: teach it with a worked example from a source note, step by step, then a similar problem for the learner.
    • never tested: the material was seen but never attempted. Give one problem of the kind the objective names and let the learner attempt it without help.
    • only tested with help: every attempt so far had help, so none of them counts. Give the same kind of task again and let the learner attempt it without help.
    • only graded by the agent: the attempt does not count because the learner never confirmed it. Ask the learner what they produced and confirm the result with them. The agent does not grade it for them.
    • mistake not recovered: the mistake was never recovered without help. Practise a variation of the same task.
    • not tested for N days: the delayed attempt, which is the retention-audit skill.
  3. If the answer is wrong, or the learner asks to try again, use the hint ladder one step at a time: hint, strong hint, partial example, answer. Never skip a step.
  4. Ask for confidence from 1 to 5 before the reveal. Then reveal and grade the learner's words against the source.
  5. Record each attempt only after the learner confirms the result. Use the item id and the mode of the item. If the learner took a hint, pass --assistance and --hints: an attempt with help stays out of the rate.
python3 -I 90_System/Scripts/record_attempt.py --objective <id> --item <id> --mode <mode> \
  [--correct|--incorrect] [--at <iso>] --confidence <1-5> [--probability <0-1>] [--hints <n>] \
  [--assistance <level>] [--grading <method>] [--rubric <ver>] [--revision <rev>] [--minutes <n>]
  1. Run the check again when the prerequisite is done, and say whether the new concept is ready.
  2. Never rewrite the concept map of the track. The map belongs to the learner. Point at the gap and let the learner change the map.
  3. Show the learner every line that was written. Never edit or delete a line of the ledger.

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.