agentleFS
sandochesandoche/agentic-code-unpacked/skills/review-quiz/SKILL.md

review-quiz

Skill1 starsChanged 4 days agoMITView on GitHub

Create an offline comprehension quiz with architecture diagrams, scored answers, and source-linked explanations for a PR, branch, codebase, or selected code.

The file

We split this skill into the rules it gives an agent

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

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈3

    Distinctive · estimate

    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:

    Test understanding of architecture, actual behavior, execution flow, failure cases, and extension points.

    line 10
  2. Distinctive:

    Read the bundled source and delivery guide, then capture the target using this installed skill's runtime.

    line 24
  3. Distinctive:

    Follow the quiz workflow and content schema.

    line 25

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 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

Review Quiz

Test understanding of architecture, actual behavior, execution flow, failure cases, and extension points. Include diagram questions when the source supports them. Default to eight meaningful questions, with fewer when evidence is insufficient.

Use

/review-quiz pr https://github.com/owner/repo/pull/123 --draft
/review-quiz docs auth --files src/auth.ts --questions 12
/review-quiz codebase

Accept natural language and the harness's native invocation syntax. Interpret PR URLs as pr, named branches as branch, selected files or pasted code as a named docs target, and the whole current repository as codebase.

Generate

  1. Read the bundled source and delivery guide, then capture the target using this installed skill's runtime. Resolve script paths from the skill folder.
  2. Follow the quiz workflow and content schema. Ground answers and recommendations in source evidence. Honor the requested question count without inventing trivia.
  3. Render and inspect the offline quiz, including scoring, explanations, and reset. Return the HTML path and any evidence shortfall.

Dependencies are set up automatically. The agent handles scripts and content JSON. Use available tools and direct source when graph tools are unavailable. PR comments require requested live delivery; --draft always stays local.

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.