agentleFS
erikunhaerikunha/vault-of-loci/.agents/skills/schedule-review/SKILL.md

schedule-review

Skill0 starsChanged 5 days agoMITView on GitHub

Run the ranked review plan for the day from the learning ledger, tell the learner which items are worth another try and why, work through them one by one with the hint ladder and confidence check, and record every confirmed attempt in the ledger. Use when the learner asks for the ranked plan of what to try today. Writes a file, so only run when asked.

The file

We split this skill into the rules it gives an agent

5 rules. About 0 are common, 5 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈5

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Run the plan for today and read it.

    line 17
  2. Distinctive:

    Ask the learner how many of the items to do.

    line 32
  3. Distinctive:

    When the plan says catch-up mode, the queue is over the cap, so no new cards are added until the queue is under it.

    line 33
  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 45
  5. Distinctive:

    Ask for confidence from 1 to 5 before the reveal.

    line 47

≈ “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

Tutor mode: the learner attempts first. The agent never writes the learner's notes, answers or guesses. Hints come one step at a time and only after an attempt. Confidence from 1 to 5 is asked before any reveal. The agent never grades an attempt the learner did not confirm.

This skill answers "what should I study today". It does not answer "what is due for a delayed test", which is retention_audit.py. The two sound alike and give different answers: the plan below is a ranking for the day, and the audit names the objective that passed a 7, 30 or 90 day horizon with no attempt without help. If the learner asked about a delayed test, use the other skill.

  1. Run the plan for today and read it. The plan says which items are worth another try and why, in the order to do them.
python3 -I 90_System/Scripts/schedule_review.py
  1. Tell the learner the items in the order of the plan, each with the reason the plan gives. Say in one line that the priority is a ranking for the day and not a probability of remembering, and that the measured numbers live in retention_report.py.
python3 -I 90_System/Scripts/retention_report.py
  1. Ask the learner how many of the items to do. A day is 10 to 20 reviews with about 2 new cards. When the plan says catch-up mode, the queue is over the cap, so no new cards are added until the queue is under it. To plan one objective only, or to see the plan as data:
python3 -I 90_System/Scripts/schedule_review.py --objective <id>
python3 -I 90_System/Scripts/schedule_review.py --cap 15 --new 2
python3 -I 90_System/Scripts/schedule_review.py --json
  1. For each item, in the order of the plan, read the source note and ask the question. Wait for the learner's answer. Say nothing about the content before the answer: no excerpt, no summary, no hint.
  2. 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.
  3. Ask for confidence from 1 to 5 before the reveal. Then reveal and grade the learner's words against the source and the rubric.
  4. Record the attempt only after the learner confirms the result. Use the item id and the mode from the plan. 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 --confidence <1-5> [--hints <n>] [--assistance <level>] [--grading <method>] \
  [--rubric <ver>] [--revision <rev>] [--minutes <n>] [--at <iso>] [--probability <0-1>]
  1. Show the learner the line that was written and the item left in the plan. 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.