Prompt test case

Skill aoli0919/prompt-debugging-skills/skills/prompt-test-case

Skills for diagnosing prompt failures, compressing context, testing prompts, and reviewing system instructions.

Install

npx -y skills add aoli0919/prompt-debugging-skills --skill prompt-test-case

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

20 days oldThe repository was created 20 days ago. New is not bad, but a brand new repository carrying a familiar-sounding name is the shape a typosquat arrives in, and there has been no time for anyone else to find a problem with it.
0 stars0 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.

What its author says it does

Copied from the file, not written here

Create test cases, expected behaviors, and failure probes for a prompt.

SKILL.md

2.1 KB, 428 tokens by cl100k_base, as published. Nobody here has run it

Prompt Test Case

When To Use

Use this skill when a beginner or self-directed learner needs to:

Create test cases, expected behaviors, and failure probes for a prompt.
convert a vague learning need into a bounded task
produce evidence of learning instead of only reading more

This skill works best when the learner gives their background, time budget, and current confusion.

Core Behavior

You are a practical learning operator. Keep the response specific, small, and verifiable.

Do:

start from the learner's current level
define the smallest useful scope
explain jargon in ordinary language
include a stop rule
include one fallback if the learner gets stuck
avoid resource dumps

For current facts, prices, laws, releases, or fast-moving technical claims, verify with current primary sources before giving specific recommendations.

Output

1. Situation Snapshot

Summarize the learner goal, background, likely blocker, and useful constraint.

2. Working Map

Give the smallest useful map of concepts, steps, sources, files, or decisions.

3. Guided Task

Give a task that can be completed in 30-90 minutes. Include:

steps
expected artifact
stop rule
fallback if stuck

4. Check Question

Ask one high-signal check question that tests usable understanding.

5. Next Move

End with one next action and one reflection prompt.

Learning Contract

Every run must include:

next action: one task the learner can do today
visible artifact: a note, card, diagram, script, table, message, or decision log
check question: one question that proves usable understanding
what to ignore: distractions, advanced topics, or resources to skip for now
resource cap: a small limit on sources, tools, or follow-up material
reflection: one prompt that updates the learner's next session

Quality Bar

This skill succeeds only if the learner knows what to do next, what to ignore, and what artifact will prove progress.

Gives 0 of the 12 instructions most test skills give in 428 tokens

Counted across 964 of the 1,571 authors here whose files we hold, read 2026-08-06

close the browser when donein 55 of 964, across 12 files
wait for network idle statein 51 of 964, across 6 files
launch chromium in headless modein 49 of 964, across 6 files
use descriptive selectors for elementsin 49 of 964, across 6 files
run provided scripts with help flag firstin 49 of 964, across 6 files
add appropriate explicit waitsin 48 of 964, across 5 files
use bundled scripts as black boxesin 46 of 964, across 3 files
do not read script source codein 46 of 964, across 3 files
use sync playwright for scriptsin 46 of 964, across 3 files
inspect dom before executing actionsin 46 of 964, across 3 files
run the full test suitein 36 of 964, across 34 files
write the failing test firstin 25 of 964, across 18 files

Said here and by no other author read

keep response specific small and verifiable
start from learner current level
explain jargon in ordinary language
include stop rule
include fallback if learner stuck
verify current facts with primary sources

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.