agentleFS
rikilamadridrikilamadrid/pathfinder/skills/quiz-me/SKILL.md

quiz-me

Skill1 starsChanged 45 days agoMITView on GitHub

Assess understanding of a recently taught feature using varied, evidence-based questions and targeted feedback.

18 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

11 rules. 0 are common, 9 are distinctive, and 2 are very specific to this project.

  • 0

    Common

    Most of the 17 edited versions we read keep these.

  • 9

    Distinctive

    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 this skill after teach-feature, or when the user wants to test understanding of a feature or concept.

    line 9
  2. Distinctive:

    Only the implementation or tests needed to verify answers

    line 17
  3. Distinctive:

    Create 5 questions by default.

    line 24
  4. Distinctive:

    Ask one question at a time.

    line 45
  5. Distinctive:

    Ask one targeted follow-up only when it will diagnose a meaningful gap.

    line 51
  6. Distinctive:

    Do not reveal all answers before the learner responds.

    line 54
  7. Distinctive:

    Do not use a percentage unless every question had a clear scoring basis.

    line 65
  8. Very specific:

    Update context/learning/progress.md with demonstrated evidence.

    line 69
  9. Distinctive:

    Do not change product code.

    line 102
  10. Distinctive:

    Do not inflate the quiz to cover the whole stack.

    line 103
  11. Distinctive:

    Do not treat one quiz as proof of mastery.

    line 104

“Common” is measured: kept by at least 6 in 10 of the 17 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

Quiz Me

Use this skill after teach-feature, or when the user wants to test understanding of a feature or concept.

The goal is retrieval and diagnosis, not entertainment and not a long exam.

Read First

  1. The relevant lesson in context/learning/lessons/
  2. context/current-ticket.md
  3. Only the implementation or tests needed to verify answers
  4. context/learning/progress.md

Skip any of these that does not exist. Pathfinder creates these files only when a workflow first needs them, so their absence is normal and is not an error. Do not create them just to satisfy this list.

Quiz Shape

Create 5 questions by default. Mix at least three formats:

  • Predict what happens
  • Explain why a decision was made
  • Trace data or event flow
  • Find or diagnose a bug
  • Choose between architectural alternatives
  • Identify an accessibility or performance risk
  • Interpret a focused code excerpt
  • Explain how a test proves behavior

Avoid:

  • pure trivia
  • questions answerable only by memorizing file names
  • five multiple-choice questions
  • ambiguous questions without a defensible answer
  • testing concepts not present in the lesson or code

Delivery

Ask one question at a time.

After each answer:

  1. Mark it as correct, partially correct, or incorrect.
  2. Explain the key point concisely.
  3. Ask one targeted follow-up only when it will diagnose a meaningful gap.
  4. Continue to the next question.

Do not reveal all answers before the learner responds.

Scoring

At the end, report:

  • Strong understanding
  • Partial understanding
  • Gaps to reinforce
  • One recommended next action

Do not use a percentage unless every question had a clear scoring basis.

Progress Update

Update context/learning/progress.md with demonstrated evidence.

The file does not ship. If it is missing, create it with this header, then add the entry:

# Learning Progress

Demonstrated understanding, not feature completion.

## Confidence Scale

- `introduced` — explained once; no evidence of recall yet
- `practiced` — answered or applied with help
- `independent` — applied correctly without meaningful help
- `transferable` — applied correctly in a different context
- `review-needed` — misunderstanding or weak recall was observed

## Concepts

| Concept | Confidence | Evidence | Last reviewed |
| --- | --- | --- | --- |

This block is the scale's only definition. The other learning skills read it from the file rather than restating it.

Record one confidence value per concept, and record uncertainty honestly. A correct answer with heavy hints is practiced, not independent. Passive reading is never independent.

Scope

  • Do not change product code.
  • Do not inflate the quiz to cover the whole stack.
  • Do not treat one quiz as proof of mastery.

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.