Skip to main content
affpapa.org
RU EN
skill CX Codex

test-prompt — Claude Code skill: test prompts before you ship

Runs your prompt scenario with and without the prompt on a subagent, so you can see exactly what the instruction changes.

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓ 
npx skills add NeoLabHQ/context-engineering-kit --skill test-prompt -a claude-code
Open on GitHub

What test-prompt does

The skill borrows the RED-GREEN-REFACTOR cycle from test-driven development. First you run a scenario with no prompt loaded and write down how the agent behaves on its own. Then you draft an instruction aimed at those failures and rerun the same scenario with it. The last pass tightens weak spots and checks the result on a fresh subagent.

It covers slash commands, hooks, skills, subagent instructions and prompts for production models. A subagent starts clean, with no chat history, so only the prompt under test affects the outcome. For rules meant to hold under pressure, the scenario adds it: a looming deadline, fatigue, working code you would hate to throw away.

The skill expects test-driven-development and prompt-engineering as background. The process uses the Task tool with general-purpose, and the subagent must not see the prompt being tested — otherwise the baseline run proves nothing.

What it helps with

  • record how an agent fails without the instruction
  • draft a prompt that targets the failures you observed
  • test a slash command on a fresh subagent before release
  • find loopholes an agent uses to dodge a rule
  • compare two prompt versions on the same scenario

Example prompts for the agent

  • Run the commit scenario without my command and log what the agent gets wrong
  • Test this skill on a subagent, first without it and then with it
  • Tighten the hook prompt and recheck it on a new subagent

How to install test-prompt

1Skills CLI (Vercel)

npx skills add NeoLabHQ/context-engineering-kit --skill test-prompt -a claude-code

2Manually: put the files in place

~/.claude/skills/test-prompt/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/test-prompt/

Step by step, with commands for each platform: How to install skills in Claude Code: five ways

Questions about test-prompt

How do I install test-prompt in Claude Code?

Run npx skills add NeoLabHQ/context-engineering-kit --skill test-prompt -a claude-code, then check ~/.claude/skills/test-prompt/SKILL.md.

What does test-prompt do?

It checks a prompt with a RED-GREEN-REFACTOR loop: a baseline run without the prompt, a run with it, then cleanup and a recheck on a subagent.

What background do I need?

The skill builds on test-driven-development for the cycle and prompt-engineering for the optimization techniques.

Similar skills

All skills for Agent setup: memory, context, orchestration →
setup-matt-pocock-skills Matt Pocock This skill configures a repository for Matt Pocock's engineering skills by setting its issue tracker, triage labels, and domain docs layout. Run it before using the other skills. 1,052,851installs ask-matt Matt Pocock Routes you to the right Matt Pocock skill or flow for the task at hand. Use it when you need a starting point for a feature, prototype, incoming issue, or hard bug. 766,587installs to-tickets Matt Pocock Turns a plan, spec, or conversation into small end-to-end tickets with explicit blockers. Use it to agree on the work breakdown before tickets go to a tracker. 711,230installs writing-plans Jesse Vincent This skill turns requirements for a multi-step task into an implementation plan before code changes begin. It helps when another engineer needs exact files, interfaces, and checks. CX Codex 282,859installs caveman-review JuliusBrussee Turns code review comments into one line per finding: location, problem, fix. Useful when a diff or PR needs a fast pass without the filler. CX Codex +1 411,800installs caveman-compress JuliusBrussee Compresses CLAUDE.md, todo lists, and other prose files into a shorter format while retaining a readable backup. CX Codex +1 411,500installs

From the same set64

create-skill Helps create or update skills with TDD, using subagent scenarios to test an instruction before it is revised. CX Codex +1 1,200installs create-ideas This skill makes the model return six candidate answers with probabilities: three likely ones and three pulled from the tails of the distribution. CX Codex +1 1,200installs cause-and-effect Runs structured Ishikawa diagram investigations on development bottlenecks. Pinpoints root causes across technical and team factors. CX Codex +1 1,200installs fix-tests This skill tracks down failing tests after logic changes or refactoring and guides fixes until the suite passes. CX Codex +1 1,200installs test-skill Tests agent skills before deployment using a TDD cycle with pressure scenarios. Reveals when an assistant bypasses rules and invents excuses. CX Codex +1 1,200installs tree-of-thoughts Runs a hard task through three parallel agents, a pruning vote and a synthesis pass. Useful when the right approach isn't obvious up front. CX Codex +1 1,200installs create-rule A skill that walks you through writing a rule file in .claude/rules/ so your agent stops repeating the same mistake. CX Codex +1 1,200installs launch-sub-agent Dispatches a focused sub-agent with isolated context, automated model routing, and mandatory self-critique verification. CX Codex +1 1,200installs

Project sponsors

Companies that keep this analytics open
Gold sponsor
Nutra.Club

Impressions, clicks and code copies — open statistics. We keep the numbers public for the same reason NeBlask itself is public. Become a sponsor