How to Install the Prompt Engineer Claude Plugin (Cowork & Code)
Step-by-step installation guide for the Prompt Engineer Claude plugin from The AI Career Lab — works in both Claude Cowork (chat) and Claude Code (terminal). Eval rubrics, synthetic test cases, SKILL.md audits, and regression reports as native slash commands.
Don't want to install anything? You don't have to. The free web tools for prompt engineers on The AI Career Lab give you the same pre-built workflows in your browser — five runs a day on a free account, no terminal, no install. Create a free account if you'd rather skip straight to the tools.
The Prompt Engineer Claude plugin from The AI Career Lab is the fastest way to turn Claude into a PE-aware co-worker. It bundles 4 pre-built slash commands and 2 auto-activating skills that already know what working prompt engineers actually do — eval rubrics with observable criteria, synthetic test cases that look like production traffic, SKILL.md audits with severity-tagged findings, and regression reports that lead with the decision.
The plugin works in both runtimes Claude offers:
- Claude Cowork — the chat product at claude.ai. The easiest path. No terminal, no install of anything else. Requires a paid Claude plan (Pro, Max, Team, or Enterprise).
- Claude Code — the terminal CLI. Particularly useful for prompt engineers since Claude Code can read your SKILL.md files, prompt repository, and eval datasets directly. Requires Node.js + npm.
What this plugin gives you
A normal Claude session is a blank chat window. A plugin replaces that with slash commands — pre-built shortcuts that contain the structure, formatting rules, and PE conventions for a specific task.
In this plugin you get:
/eval-rubric— builds an eval rubric with 4-8 observable criteria, scoring approach, edge cases, and a run plan/synthetic-cases— generates 30-100 synthetic test cases split into happy path, edge cases, and adversarial/skill-audit— audits a SKILL.md or prompt artifact for frontmatter validity, injection surface, and quality/length issues/regression-report— writes a regression report with decision in paragraph 1, per-criterion deltas, subgroup notes, and failure mode analysis
Which runtime should you use?
Use Claude Cowork if:
- You already use claude.ai for chat work
- You prefer a graphical interface to a terminal
- You don't want to install anything else on your machine
- You have a paid Claude plan (Pro, Max, Team, or Enterprise)
Use Claude Code if:
- You're already in a terminal alongside your prompt repo
- You want Claude to read your actual SKILL.md, prompt template files, or eval CSV directly
- You're on a free Claude account (Claude Code plugin install does not require a paid plan)
For prompt engineers specifically, Claude Code has a strong advantage: it can read your repo. You can run /skill-audit and have Claude read the actual file rather than re-paste it.
Path A: Install in Claude Cowork (easiest, no command lines)
- Open claude.ai in your browser and sign in.
- Make sure you're on a paid plan (Pro, Max, Team, or Enterprise). The plugin marketplace is gated to paid plans.
- Open the plugin settings and click Add marketplace.
- In the modal, paste this into the URL field:
alexclowe/awesome-claude-cowork-plugins- Click Sync. Claude Cowork pulls the marketplace catalog from the public alexclowe/awesome-claude-cowork-plugins repo.
- Browse the marketplace. Find the Prompt Engineer plugin and click Install.
Path B: Install in Claude Code (terminal CLI, two commands)
One-time Claude Code setup
- Install Claude Code. Open a terminal and run:
npm install -g @anthropic-ai/claude-codeIf you don't have npm, install Node.js first.
- Sign in once. Run
claudein your terminal and follow the sign-in flow.
Install the plugin
Inside Claude Code, run these two commands:
/plugin marketplace add alexclowe/awesome-claude-cowork-plugins
/plugin install prompt-engineer@awesome-claude-cowork-pluginsTo verify, type /help and you should see the new commands listed alongside Claude Code's built-ins.
Your first command
For most prompt engineers, the highest-leverage starting point is the eval rubric — every team has prompts shipping without one:
/eval-rubricWhen you run it, Claude asks for the prompt or skill's purpose, success criteria, known failure modes, scoring approach, and eval data available. The output is a rubric with 4-8 observable criteria, each with measurement approach, scoring rubric, examples, and thresholds.
Commit the rubric to your repo. Every future change runs against it. That's the discipline that turns "looks better on my demo set" into "passes the eval threshold."
First 4 workflows to try after install
- Eval rubric —
/eval-rubricin the plugin, or /tools/prompt-engineer-eval-rubric on the web. Run this for a production prompt you maintain - Synthetic test cases —
/synthetic-casesin the plugin, or /tools/prompt-engineer-synthetic-cases on the web. Run this to build a starter eval set - Skill audit —
/skill-auditin the plugin, or /tools/prompt-engineer-skill-audit on the web. Run this on any skill before publishing - Regression report —
/regression-reportin the plugin, or /tools/prompt-engineer-regression-report on the web. Run this on the next non-trivial prompt change
Skills you get for free
This plugin also includes Claude Skills that activate automatically when you're working on relevant tasks:
- Observable Criteria Discipline — when generating eval criteria, refuses to default to subjective quality scales and pushes back on "Helpful: 1-5" criteria in favor of binary or categorical observable behaviors
- Subgroup Regression Detection — when summarizing eval results, automatically calls out subgroup deltas separately from topline numbers rather than hiding them in the average
The first time the observable-criteria skill auto-activates and refuses to produce a 1-5 subjective scale criterion when you asked for one, you'll see the difference between using Claude generically and using Claude as a PE co-worker.
Where to go from here
- Claude Cowork playbook for prompt engineers — the full setup guide with the five high-leverage prompt structures
- Free web tools for prompt engineers — same workflows, browser-based, no install required
- Best AI Tools for Prompt Engineers in 2026 — the broader landscape including Claude, eval platforms (Braintrust, LangSmith, Langfuse, Promptfoo), tracing tools, and red team tooling
- AI for Prompt Engineers guide — the working playbook for shipping prompts that survive production
Common issues
I don't see the "Add marketplace" option in Claude Cowork. You need to be on a paid plan. If you're on a free plan, install via Claude Code instead — it's free.
The marketplace sync failed in Claude Cowork. Double-check the URL field has exactly alexclowe/awesome-claude-cowork-plugins — a GitHub owner/repo format, no https://, no trailing slash.
The slash commands aren't showing up after install. Start a new chat (Cowork) or type /help (Claude Code). If you see the built-in commands but not the new ones, the install didn't complete — re-run the install.
I want to use this without installing anything. Use the free web tools instead. Same workflows, browser-based, no install or paid plan.
Ready to try it without installing
Create your free AI Career Lab account and try the prompt engineer tools today. No credit card required.
Save hours every week with the AI Career Lab — All 7 AI Cowork Vaults
All seven profession-specific AI Cowork Vaults — 315 skills total. Works on Claude Cowork and Microsoft 365 Copilot Cowork.
Related Guides
AI for Prompt Engineers: Ship Prompts and Skills That Survive Production
How working prompt engineers are using AI in 2026 — eval rubrics that catch real regressions, synthetic test cases that look like production traffic, SKILL.md audits, and regression reports with the decision up front.
Best AI Tools for Prompt Engineers in 2026
A curated list of the best AI tools for working prompt engineers in 2026 — eval platforms, observability, prompt versioning, skill audit, and the structured-writing layer for rubrics, test cases, audits, and regression reports.
How to Install the AI Compliance Officer Claude Plugin (Cowork & Code)
Step-by-step installation guide for the AI Compliance Officer Claude plugin from The AI Career Lab — works in both Claude Cowork (chat) and Claude Code (terminal). Risk classification, regulatory update triage, QMS drafting, and agent eval harness as native slash commands.