Claude CoWork for Recruiters
A practical guide to using Claude as your AI co-worker in your recruiting workflow — from setup to daily use.

What is Claude CoWork?
Claude CoWork is the practice of using Claude as a persistent, knowledgeable co-worker embedded in your daily recruiting workflow. This is not about asking a chatbot to rewrite a job posting once. It is about configuring Claude with your company context, hiring standards, and communication style so that every interaction produces output you can use immediately.
Claude-native prompts. The prompts in this guide use Claude's native XML tag structure (
<context>,<instructions>,<avoid>) for more precise, consistent output. These tags help Claude parse your intent with less ambiguity.
Think of Claude as a recruiting coordinator who never drops the ball, remembers every role you are working on, and can draft candidate outreach, job descriptions, or interview scorecards in seconds. This guide walks you through setting up Claude specifically for recruiting, the five workflows that save the most time, and the prompting techniques that separate generic output from production-ready content.
Install the Recruiter Plugin
This guide works on three Claude surfaces. The plugin is the fastest path on two of them. Pick whichever you use:
If you're on Cowork (desktop or mobile app)
Claude Cowork is Anthropic's agentic workspace — Claude completes work autonomously and returns finished deliverables. The Recruiter plugin packages the workflows below as native skills and slash commands.
- Open the Cowork plugin directory in your desktop app.
- Filter by Cowork, search for "Recruiter", and click Install.
- The plugin's slash commands and ambient skills are now available in any Cowork task.
If you don't see the plugin in the directory yet, install via custom marketplace: paste
https://github.com/alexclowe/awesome-claude-cowork-pluginsin your Cowork plugin settings.
If you're on Claude Code (CLI)
Install from your terminal:
claude plugin add alexclowe/awesome-claude-cowork-plugins/recruiterThe plugin's slash commands and skills load on next session.
If you're on Claude.ai (web chat only)
Plugins aren't directly installable on the web chat surface. You have two options:
- Use the prompts in this guide directly in a Claude Project (covered in the next section). Same outputs, more typing.
- Upload the plugin's skills as a zip via Settings → Features → Custom Skills (Pro/Max/Team/Enterprise plans). Higher friction; only worth it if you want the auto-activating skills, not the slash commands.
What the plugin gives you (any surface)
| Slash command | What it does |
|---|---|
/job-description |
Generate inclusive, compelling job descriptions with role requirements and DEI-friendly language |
/candidate-outreach |
Draft personalized sourcing emails, InMail messages, and follow-up sequences |
/interview-scorecard |
Create structured interview scorecards with competencies and behavioral questions |
/offer-letter |
Draft offer letters and offer comparison matrices for candidates |
Auto-activating skills (no command needed — Claude applies them when relevant):
- Talent Acquisition — Sourcing strategy, candidate evaluation, employment law awareness, and structured hiring processes
- Employer Branding — Compelling role marketing, candidate experience, DEI-inclusive language, and EVP communication
The plugin works standalone for one-off tasks. Pair it with the surface-specific setup below for persistent context across every task — that combination is the full Claude CoWork setup.
Setting Up Claude for Recruiting Work
Surface note: The Project setup below is for claude.ai web users. Cowork users have their own task-context mechanism (set context once when starting a Cowork task). Claude Code users get the plugin's ambient skills automatically — no Project setup needed. The workflows themselves are surface-agnostic — paste the prompts wherever you're working. The key to getting consistently useful output is using Claude Projects. A Project lets you set custom instructions that persist across every conversation.
Step 1: Create a Recruiting Project. In Claude, click "Projects" and create one called something like "My Recruiting Desk."
Step 2: Set your custom instructions. In the Project settings, add:
You are my recruiting assistant. Here is my context:
<business-profile>
- Name: [Your Name], [Your Company/Agency]
- Industry focus: [Tech / Healthcare / Finance / Generalist]
- Typical roles: [Software Engineers, Sales, Executive, etc.]
- Communication tone: [Professional and direct / Warm and personable]
- ATS: [Greenhouse / Lever / Workday / etc.]
</business-profile>
<rules>
- All content must comply with EEO guidelines. Never include language that discriminates based on age, gender, race, religion, disability, or any protected class.
- Use inclusive language. Avoid coded terms like "digital native" or "culture fit."
- Match my voice: [paste a sample outreach message].
</rules>Step 3: Upload reference documents. Add your best outreach templates, job description frameworks, and your company's EVP to the Project knowledge base.
Step 4: Start every session inside this Project.
Your Top 5 Workflows with Claude
1. Candidate Outreach Emails
<task>Write a candidate outreach email for a passive candidate on LinkedIn.</task>
<context>
- Role: Senior Backend Engineer (Python, AWS)
- Company: Acme Corp, Series B fintech startup, 120 employees
- Candidate: Jane — currently at BigCorp for 3 years, built their payment processing system
- Selling points: engineering-led culture, greenfield microservices migration, competitive equity
</context>
<instructions>
- Reference something specific about her background
- Lead with the opportunity, not the company pitch
- Keep it under 100 words, end with a low-pressure CTA
</instructions>
<avoid>
- Generic flattery ("I was impressed by your profile")
- Buzzwords like "rockstar" or "ninja"
</avoid>Before Claude: 10-15 minutes per personalized outreach email. After Claude: 2 minutes to paste context, 1 minute to review and send.
2. Job Descriptions
<task>Write a job description for this role.</task>
<context>
- Title: Product Marketing Manager, Remote (US-based)
- Reports to VP of Marketing, salary $120K-$145K
- Must-haves: 4+ years B2B SaaS product marketing, product launch experience
- Nice-to-haves: fintech experience, analytics tools proficiency
</context>
<instructions>
- Open with a 2-3 sentence hook about the role's impact
- Separate must-haves from nice-to-haves, max 6 requirements
- Include salary range, use inclusive gender-neutral language
</instructions>
<avoid>
- Laundry lists of 15+ requirements
- "Young and energetic team" or unnecessary degree requirements
</avoid>Before Claude: 45-60 minutes drafting and formatting. After Claude: 5 minutes to input specs, 5 minutes to refine.
3. Interview Scorecards
<task>Create an interview scorecard for a technical screen.</task>
<context>
- Role: Senior Backend Engineer (Python, AWS), 45-minute technical screen
- Assess: system design thinking, Python proficiency, cloud architecture, communication
</context>
<instructions>
- 5 evaluation criteria with behavioral anchors on a 1-4 scale
- Include one sample question per criterion
- Add an overall recommendation section
</instructions>
<avoid>Subjective criteria like "culture fit" or "gut feel."</avoid>Before Claude: 30-40 minutes building a scorecard per role. After Claude: 3 minutes to specify the role, 5 minutes to customize.
4. Offer Letters
<task>Draft an offer letter for the selected candidate.</task>
<context>
- Candidate: Michael Chen, Product Marketing Manager
- Start: April 14, 2026 | Base: $135,000 | Equity: 5,000 options (4yr/1yr cliff)
- Signing bonus: $10,000 | Benefits: medical/dental/vision, 401k 4% match, unlimited PTO
- Manager: Sarah Kim, VP of Marketing | Location: Remote (US)
</context>
<instructions>
- Professional, welcoming tone, clearly state all compensation components
- Include next steps (background check, 5-business-day response deadline)
- Keep it to one page
</instructions>
<avoid>Implying guaranteed employment duration or future compensation promises.</avoid>Before Claude: 20-30 minutes adapting a template. After Claude: 3 minutes to input terms, 5 minutes to review.
5. Boolean Search Strings
<task>Build Boolean search strings for this sourcing project.</task>
<context>
- Target: Senior Frontend Engineers, React + TypeScript
- Location: San Francisco Bay Area or Remote
- Preferred backgrounds: fintech, e-commerce, high-growth startups
- Platforms: LinkedIn Recruiter, GitHub
</context>
<instructions>
- One optimized Boolean string per platform
- Include title variations ("frontend" OR "front-end" OR "front end")
- Explain the logic behind each string briefly
</instructions>
<avoid>Overly restrictive strings or nesting more than 3 levels of parentheses.</avoid>Before Claude: 15-20 minutes building and testing search strings. After Claude: 2 minutes to describe the target, 2 minutes to test and adjust.
Prompt Engineering Tips for Recruiters
1. Always specify the audience. "Write outreach for a passive senior engineer" produces very different output than "write for an entry-level candidate." Tell Claude who you are targeting and where they are in the funnel.
2. Include your company's selling points. Claude cannot know what makes your company special unless you tell it. Always include 2-3 specific reasons a candidate should care.
3. Set word limits aggressively. Candidates skim. Keep outreach under 100 words, JDs under 600, scorecards to one page.
4. Provide examples of your voice. Paste a previous outreach message and say "Match this tone." This saves more revision time than any other technique.
5. Ask for variants. "Give me 3 versions with different hooks" for outreach. A/B testing dramatically improves response rates.
6. Use Claude to pressure-test your requirements. Paste a JD and ask: "Which requirements might discourage qualified diverse candidates from applying?"
Privacy & Compliance
EEO compliance is non-negotiable. Never ask Claude to generate content that screens or describes candidates based on protected characteristics. Review all job descriptions and outreach for coded language that could imply bias — "recent graduate" (age proxy) or "native English speaker" (national origin proxy) should never appear.
Verify salary and benefit details. Claude drafts based on what you provide, but it cannot check HR systems. Always confirm compensation figures, equity terms, and benefit details with your HR or finance team before sending any offer letter.
Candidate data privacy. Do not paste candidates' full resumes, Social Security numbers, or sensitive personal information into Claude. Use role-relevant summaries: "5 years at BigCorp, built payment systems" rather than uploading entire application files.
Audit your outputs. Periodically review AI-generated content to ensure it aligns with your company's DEI commitments and applicable employment laws in your jurisdiction.
Going Further
Ready to build on this foundation? Check out these resources:
- Browse our full collection of recruiting prompt packs and cheat sheets for ready-to-use templates
- Run an AI readiness audit for your recruiting practice to identify your biggest opportunities
- Explore AI-powered tools built specifically for recruiters to automate even more of your workflow