Skip to main content
skill CX Codex

prompt-engineer-toolkit · borghei — Claude Code skill for prompt testing

The prompt-engineer-toolkit Claude Code skill tests production prompts and scores model outputs. Use it to compare revisions, investigate regressions, and gate prompt changes before release.

LicenseRef-MIT-Commons-Clause 106 installs ★ 1,183 updated 2026-11-08

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓
npx skills add borghei/Claude-Skills --skill prompt-engineer-toolkit -a claude-code
Open on GitHub

What prompt-engineer-toolkit does

The skill treats prompts as versioned artifacts: build an evaluation suite, inspect prompt text, compare revisions, and score model responses. The toolkit includes prompt_analyzer.py, prompt_diff.py, and eval_scorer.py.

Evaluation cases compare actual outputs with contains, regex, or exact expectations. Set a score threshold with --fail-under; the scorer exits with code 1 when results fall below it. The analyzer and diff use text heuristics, so they cannot tell whether a prompt succeeds at its task. The evaluation suite does that.

What it helps with

  • catch regressions in a revised production prompt
  • compare two prompt versions and flag risky edits
  • score model outputs against an evaluation suite
  • spot vague wording and unnecessary prompt instructions

Example prompts for the agent

  • Analyze assets/prompt_v1.txt and flag vague wording or unnecessary instructions.
  • Compare assets/prompt_v1.txt with assets/prompt_v2.txt and report risky changes.
  • Score the outputs in assets/sample_eval_suite.json using --fail-under 0.9.

How to install prompt-engineer-toolkit

1Skills CLI (Vercel)

npx skills add borghei/Claude-Skills --skill prompt-engineer-toolkit -a claude-code

2Manually: put the files in place

~/.claude/skills/prompt-engineer-toolkit/SKILL.md

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

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

Questions about prompt-engineer-toolkit

How do I install prompt-engineer-toolkit in Claude Code?

Run npx skills add borghei/Claude-Skills --skill prompt-engineer-toolkit -a claude-code. The skill file is at ~/.claude/skills/prompt-engineer-toolkit/SKILL.md.

What does prompt-engineer-toolkit do?

It helps test prompts, compare revisions, and score model responses against an evaluation suite. It also checks prompt text for common wording issues.

How does it check that a prompt change meets the baseline?

Run eval_scorer.py with --fail-under <baseline>. The new version must meet or exceed that score without adding failures on format checks.

Similar skills

All skills for AI and ML →

prompt-engineer-toolkit by other authors comes first.

prompt-engineer-toolkit Alireza Rezvani prompt-engineer-toolkit is a Claude Code skill that tests, compares, and versions marketing prompts against structured cases. It checks prompt quality before rollouts or model changes. CX Codex +1 623installs prompt-engineer https://github.com/Jeffallan prompt-engineer is a Claude Code skill that designs, refactors, and tests prompts for language models. It builds few-shot patterns, chain-of-thought flows, and JSON output schemas. CX Codex +1 6,100installs prompt-engineering giuseppe-trisciuoglio The prompt-engineering skill helps write, debug, and test LLM prompts. Use it for few-shot examples, system prompts, reasoning workflows, and reusable templates. CX Codex +1 4,200installs prompt-engineering-patterns Seth Hobson The prompt-engineering-patterns skill helps design, test, and refine prompts for LLM applications. Use it for reusable templates, few-shot examples, and structured responses. CX Codex +1 23,418installs prompt-governance Alireza Rezvani prompt-governance manages production prompts as versioned code, builds automated eval pipelines, and prevents quality regressions across AI deployments. CX Codex +1 40installs prompt-optimize Seth Hobson prompt-optimize — a slash command that reviews your prompt and rewrites it with chain-of-thought, few-shot examples and a self-critique pass. CX Codex +1 ★ 42,780repo stars senior-prompt-engineer Alireza Rezvani senior-prompt-engineer — a skill for systematic prompt optimization via eval sets, RAG quality measurement, and agent validation. Works with any model, uses only stdlib Python. CX Codex +1 970installs

From the same set120

The whole set →
social-content social-content is a Claude Code skill that drafts platform-specific social posts and content calendars. Set the platform, goal, and format to shape the result. CX Codex +1 110installs ci-cd-pipeline-builder The ci-cd-pipeline-builder Claude Code skill builds and checks CI/CD pipelines from a project's stack. It helps configure tests, dependency caches, and deployment stages. CX Codex +1 108installs pricing-strategy The pricing-strategy skill helps shape SaaS tiers, research price points, and plan price increases. Use it when building a pricing model or diagnosing an existing one. CX Codex +1 107installs pci-dss-specialist pci-dss-specialist is a Claude Code skill for assessing PCI DSS compliance and mapping the cardholder data environment. It activates for payment security reviews, scoping, and SAQ or ROC preparation. CX Codex +1 106installs nis2-directive-specialist The nis2-directive-specialist skill supports NIS2 scope checks, cybersecurity control reviews, supply-chain analysis, and incident-reporting readiness for covered entities. CX Codex +1 105installs chief-of-staff chief-of-staff scores how complex a founder's question is, then sends it to one or more C-suite advisors or runs a board meeting. Useful when departments disagree. CX Codex +1 104installs brainstorm-experiments The brainstorm-experiments skill for Claude Code and Codex turns a product hypothesis into a low-cost experiment with a pass threshold set in advance. It selects a method for a new idea or an existing feature. CX Codex +1 104installs analytics-tracking analytics-tracking is a Claude Code skill that builds and audits GA4 and GTM setups, structures event taxonomies, and troubleshoots broken conversions. CX Codex +1 104installs

Project sponsors

Companies that keep this analytics open