agentleFS
erikunhaerikunha/vault-of-loci/.agents/skills/recovery-after-inactivity/SKILL.md

recovery-after-inactivity

Skill0 starsChanged 5 days agoMITView on GitHub

Run the short diagnostic the vault keeps for a break of 14 days or more without an attempt, work a few items with the learner, then report the length of the break and offer the plan for the next days without calling the backlog a debt. Use when the learner comes back after time away. Writes a file, so only run when asked.

The file

We split this skill into the rules it gives an agent

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

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈7

    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. Distinctive:

    Run the diagnostic for a return after a break.

    line 11
  2. Very specific:

    If the script says there is no break to recover from, the last attempt is recent.

    line 17
  3. Distinctive:

    Run the small diagnostic. It prints the days away, the number of items waiting, and a few items to do.

    line 20
  4. Distinctive:

    Ask the learner which of the diagnostic items to start with.

    line 23
  5. 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 26
  6. Distinctive:

    Ask for confidence from 1 to 5 before the reveal.

    line 28
  7. Distinctive:

    After the diagnostic, say how long the break was and how many items are waiting.

    line 40
  8. Distinctive:

    Do not present the waiting items as a debt.

    line 48

≈ “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.

  1. Run the diagnostic for a return after a break. A break is 14 days or more without an attempt.
python3 -I 90_System/Scripts/schedule_review.py --recovery
  1. If the script says there is no break to recover from, the last attempt is recent. Run the normal plan for the day instead and follow the schedule-review skill.
  2. Run the small diagnostic. It prints the days away, the number of items waiting, and a few items to do. One of them is an explanation and one is an application when the record has them. Do not dump the queue and do not print the whole backlog to the learner.
  3. Ask the learner which of the diagnostic items to start with. For each one, 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.
  4. 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.
  5. Ask for confidence from 1 to 5 before the reveal. Then reveal and grade the learner's words against the source and the rubric.
  6. Record the attempt only after the learner confirms the result. Use the item id and the mode from the diagnostic. 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. After the diagnostic, say how long the break was and how many items are waiting. Offer the plan for the next days, with the daily cap and about 2 new cards:
python3 -I 90_System/Scripts/schedule_review.py
python3 -I 90_System/Scripts/schedule_review.py --cap 15 --new 2
  1. Do not present the waiting items as a debt. Do not say the learner is behind or that the break cost anything. Missing days carry no penalty and no streak resets. Show the plan and let the learner choose where to start.

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.