agentleFS
erikunhaerikunha/vault-of-loci/.agents/skills/record-attempt/SKILL.md

record-attempt

Skill0 starsChanged 5 days agoMITView on GitHub

Record a graded attempt in the learning ledger with the mode, the verdict, the hints taken and the learner's confidence, so retention and transfer can be measured later. Use when the learner finishes a recall, an explanation, an application or a discrimination task and confirms the result. Writes a file, so only run when asked.

The file

We split this skill into the rules it gives an agent

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

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    Distinctive · estimate

    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:

    Use the mode of the attempt: recall, explain, apply or discriminate.

    line 13
  2. Distinctive:

    Keep the item id stable. The same id must mean the same question or task every time, because the report compares an attempt with what was …

    line 16
  3. Very specific:

    Ask for the confidence from 1 to 5 before the feedback, as the tutor rules say.

    line 20

≈ “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, and the agent never writes a verdict the learner did not confirm. One event is written per attempt, and the ledger is appended, never edited.

  1. Find the objective. Read 90_System/Objectives.json and pick the objective the attempt belongs to. If none fits, ask the learner what the task was trying to make them able to do, write the criterion in one sentence, and add the objective to the registry before going on.
  2. Use the mode of the attempt: recall, explain, apply or discriminate. A study event records that the material was seen and is not graded. record_attempt.py refuses a study event with a verdict, so use the right mode.
  3. Keep the item id stable. The same id must mean the same question or task every time, because the report compares an attempt with what was done before.
  4. Record the first try only. If the learner took a hint, pass --assistance and --hints. A hint is neither a pass nor a fail: the event is kept and the report leaves it out of the rate.
  5. Ask for the confidence from 1 to 5 before the feedback, as the tutor rules say. If the learner gives a chance in percent instead, pass --probability too.
  6. Grade as the learner confirmed it. When the learner asked the agent to grade and accepted the verdict, pass --grading agent_graded. The report keeps those attempts out of the rates and counts them separately.
  7. Write the event:
python3 -I 90_System/Scripts/record_attempt.py --objective <id> --item <id> --mode <mode> \
  --correct --confidence <1-5>
  1. Show the learner the line that was written. Offer retention_report.py when the learner wants to see what the ledger says so far. Never edit or delete a line of the ledger.

The schema and the metrics live in 90_System/Evals/Learning_outcomes.md.

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.