agentleFS
SirjanSinghSirjanSingh/oahelper-mcp/skills/revise-mistakes/SKILL.md

revise-mistakes

Skill2 starsChanged 28 days agoMITView on GitHub

Re-test the user on OA questions and MCQs they previously got wrong or needed hints for, using the practice log kept by the oahelper skills, with simple spaced repetition. Use when the user says "revise my mistakes", "what did I get wrong", "redo my weak questions", "review before the OA", or "spaced repetition".

The file

We split this skill into the rules it gives an agent

2 rules. About 0 are common, 1 is distinctive, and 1 is 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.

  • 1

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    If it does not exist, say there is nothing to revise yet and suggest mcq-drill or oa-mock to start one.

    line 17
  2. Distinctive:

    After each item, give the one idea that was missing last time.

    line 40

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 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

Revise mistakes

Part of oahelper-mcp by Sirjan Singh.

The log is library/_progress.md, a table written by oa-mock, mcq-drill and solve-coach:

| date | company | ref | title | topic | result |

If it does not exist, say there is nothing to revise yet and suggest mcq-drill or oa-mock to start one.

1. Pick what is due

Take the latest row per ref. Due when:

Latest resultDue after
wrong, not-solved, too-slow1 day
solved-with-hints3 days
correct after a previous miss7 days
correct twice in a rowretired, skip

Sort due items oldest first. Default session: up to 10 items, or what the user asks for. Filter by company or topic if the user names one.

2. Re-test

  • Load each item from its saved file in library/<co>/questions/ (no network).
  • MCQ: ask it fresh without the earlier answer, then mark it.
  • Coding: give the statement and ask for the approach in a few lines plus complexity. Full code only if the user wants. Judge the approach, not the syntax.
  • After each item, give the one idea that was missing last time.

3. Close

Append a new row per item with today's date and the new result. Then report:

Revised <n>: <k> now correct, <m> still weak
Still weak: <topics>
Next due: <date> (<count> items)

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.