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

error-recovery

Skill0 starsChanged 5 days agoMITView on GitHub

Take an item whose mistake was never recovered without help and write a variation of the same task under the id the plan prints, so the learner works with the idea and not with the memory of the sentence, then record the graded attempt in the learning ledger; use it when a mistake was never recovered, and it writes a file, so run it only when asked.

17 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use squad-commands, architectural-proposals and 10 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • Microsoft AzureSkill

    squad-commands

    Categorized catalog of common Squad operations. Coordinator reads this file and presents it as an interactive menu when the user asks for available commands or help.

    Also in 4 projects that use this

  • Microsoft AzureSkill

    architectural-proposals

    How to write comprehensive architectural proposals that drive alignment before code is written

    Also in 3 projects that use this

  • +10 more from Azure

The file

We split this skill into the rules it gives an agent

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

  • 0

    Common

    Most of the 15 edited versions we read keep these.

  • 5

    Distinctive

    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 list of errors and read it.

    line 12
  2. Distinctive:

    Read the original item and the source note behind it.

    line 21
  3. Distinctive:

    Write the variation. It keeps the same mechanism and changes the surface: new numbers, a new context, a different wording, a different …

    line 23
  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 28
  5. Distinctive:

    Ask for confidence from 1 to 5 before the reveal.

    line 30

“Common” is measured: kept by at least 6 in 10 of the 15 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 list of errors and read it.
python3 -I 90_System/Scripts/schedule_review.py --errors
  1. Take the first item. Each line gives the objective, the item id, how many attempts it had and when the last one happened. It also gives the id a variation of the task must carry, for example item-a-v2.
  2. Read the original item and the source note behind it. Find the mechanism the item tests: the rule, the contrast, the step that makes the answer right.
  3. Write the variation. It keeps the same mechanism and changes the surface: new numbers, a new context, a different wording, a different order. The learner must work with the idea and not with the memory of the sentence. Give the variation the id the plan printed.
  4. Give the variation and wait. Say nothing about the content before the attempt: no excerpt, no summary, no hint.
  5. 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.
  6. Ask for confidence from 1 to 5 before the reveal. Then reveal and grade the learner's words against the source.
  7. Record the attempt only after the learner confirms the result. Use the id of the variation, not the id of the original item.
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. A mistake is closed only after a correct recall later, without help. A right answer right after the hint ladder does not close it. When the learner gets it right later without help, mark the entry closed YYYY-MM-DD in 50_Review/Mistakes.md.
  2. Show the learner the 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.