agentsclimarketplace
Sign in

Merge quiz

Skill hiendinhngoc/unknowns/skills/merge-quiz

Pre-merge comprehension gate that quizzes the USER on the riskiest parts of the branch diff. Use before merging or opening a PR, or when the user says "merge quiz", "am I ready to merge", or "quiz me on this diff".From its SKILL.md

Install
npx -y skills add hiendinhngoc/unknowns --skill merge-quiz

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

2 things to look at

  • 9 stars9 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
  • runs commandsInstructs the agent to run 4 commands, including `git rev-parse --verify` and 3 more.

What its file declares

Copied from the file, not written here

The file declares its own license as MIT. That is the author’s claim about this one file, and it is not the same thing as the license GitHub reports for the repository, which is listed with the other numbers below.

SKILL.md

3.5 KB, 767 tokens by cl100k_base, as published. Nobody here has run it

Merge Readiness Quiz

Before shipping, verify the HUMAN understands what's being merged. The quiz tests the user, not Claude.

Process

  1. Resolve the base deterministically. Prefer, in order: the base explicitly named by the user; the current branch's configured upstream; the remote default branch from refs/remotes/origin/HEAD; then an existing local main or master. Verify the candidate with git rev-parse --verify before using it. If no candidate exists, ask for a base ref and stop.
  2. Gather the material.
    • Diff: git diff <base>...HEAD. If it is empty, also check git diff <base>..HEAD, tracked worktree changes, and relevant untracked files reported by git status --short. State exactly which material was selected. If all are empty, stop because there is nothing to quiz.
    • Exclude generated files (lockfiles, *.pbxproj, build outputs, vendored code) from quiz material — churn there is noise, not comprehension risk.
    • Deviation log: prefer files for the current branch/task slug. If task identity is unavailable, include only deviation files changed in the diff; do not sweep unrelated logs by date.
  3. Pick the 3–5 riskiest spots. If the diff is too small for 3 real questions, ask fewer and say why. First name what "dangerous" means in THIS codebase's domain — auth/money/deletion/migrations in a backend; lifecycle, state loss, and accessibility regressions in a UI app; loss/duplication/ ordering in a pipeline. Then prioritize: behavior changes on those paths, deviations from the plan, error handling changes, anything irreversible.
  4. Quiz one question at a time using AskUserQuestion (or plain-text multiple choice if this agent has no such tool). If no interactive user is available, output the quiz and stop without answering for them. Each question:
    • Cites the exact file:line it's about
    • Asks about consequences, not trivia: "what happens if X is null here?", "why did we bypass Y?", "what breaks if this runs twice?"
    • Offers 3-4 plausible answers (one correct, distractors that reflect real misunderstandings)
    • Has one correct answer backed by the exact diff hunk or file:line; if no evidence exists in the diff, do not ask that question
  5. On a wrong or unsure answer: explain the correct answer immediately, quoting the exact diff hunk verbatim so the user can dispute it — the quiz grades the user against the agent's reading of the diff, and that reading can be wrong. If the user disputes with evidence, concede the question, correct the score, and flag the spot as review-carefully either way.
  6. Produce the merge-readiness note (paste-ready for the PR description):
## Merge readiness
- Quiz: N/M correct
- Review carefully: <file:line — why, for each missed question; or "nothing flagged">
- Deviations from plan: <one line each, from the deviation log; or "none">

Rules

  • Never skip the quiz because the diff "looks simple" — simple diffs hide the best surprises. But never pad with fake-risk questions.
  • Questions must be answerable from the diff the user supposedly reviewed; no gotchas about untouched code.

What ships with it: 1 file

191 B alongside SKILL.md

agents/

Gives 1 of the 12 instructions most study practice skills give in 767 tokens

Counted across 85 of the 97 authors here whose files we hold, read 2026-09-06

  • Ask one question at a timehere, and in 17 of 85
  • Give immediate feedback after each answerin 7 of 85
  • Write five to eight quiz questionsin 6 of 85
  • Ask one question per messagein 4 of 85
  • Wait for each answer before continuingin 4 of 85
  • Wait for the user's answer before feedbackin 4 of 85
  • Present multiple-choice via AskUserQuestion with exactly four optionsin 4 of 85
  • Treat pass as merge-readyin 2 of 85
  • Present one word at a timein 2 of 85
  • Verify a story project exists before startingin 2 of 85, across 1 file
  • Clarify the revision pass type firstin 2 of 85, across 1 file
  • Read chapter and continuity context before editingin 2 of 85, across 1 file

Said here and by no other author read

  • Verify base ref with git rev-parse
  • Gather diff material with empty-diff fallbacks
  • Exclude generated files from quiz material
  • Pick the 3-5 riskiest diff spots
  • Cite exact file and line per question
  • Ask about consequences, not trivia

Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.

Keep looking

Skills are one crate of 325,949. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.