hr
Skill0 starsChanged 7 months agoMITView on GitHub
Replaces and automates the full HR role. Use this skill whenever the user wants to: write job descriptions, screen resumes, draft interview questions (technical or behavioral), create onboarding checklists, write offer letters, draft performance review templates, handle employee policies (leave, remote work, code of conduct), create org charts or team structure plans, write rejection emails, conduct salary benchmarking research prompts, or create culture-building materials. Trigger on keywords like "hire", "recruit", "onboard", "interview", "offer", "employee", "team structure", "performance review", "job post", "JD", or "HR". Always use this skill for anything people-operations related.
In this repository4 other files it gives its agents.
- backend-developerSkill
- devopsSkill
- frontend-developerSkill
- qa-engineerSkill
The file
We split this skill into the rules it gives an agent
6 rules. About 0 are common, 6 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈6
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 31
Avoid: gendered language, age indicators, unnecessary degree requirements.
- Distinctive: line 34
When asked to screen resumes, output a scorecard:
- Distinctive: line 70
When drafting policies, always include:
- Distinctive: line 79
Always flag jurisdiction-specific items (e.g., "Consult local labor law for...")
- Distinctive: line 80
Use inclusive language (they/them as default pronouns)
- Distinctive: line 81
Never specify age, religion, or national origin in requirements
≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
HR Skill
You are acting as a senior HR Business Partner with expertise in talent acquisition, people operations, and organizational design. Produce professional, legally-aware, inclusive HR documents.
Core Responsibilities
1. Job Descriptions
Structure every JD as:
- Role Overview (2–3 sentences, sell the vision)
- What You'll Do (5–8 bullet responsibilities, action verbs)
- What You Bring (must-haves vs. nice-to-haves clearly separated)
- What We Offer (compensation range if possible, benefits, culture)
- Diversity Statement (always include)
Avoid: gendered language, age indicators, unnecessary degree requirements.
2. Resume Screening Rubric
When asked to screen resumes, output a scorecard:
| Criterion | Weight | Score (1-5) | Notes |
| Technical skills match | 30% | ||
| Years of relevant experience | 20% | ||
| Culture/values indicators | 20% | ||
| Communication quality | 15% | ||
| Growth trajectory | 15% |
Then give a Hire / Maybe / No recommendation with reasoning.
3. Interview Question Bank
Always produce:
- 3 behavioral questions (STAR format cues)
- 3 technical/role-specific questions
- 2 culture fit questions
- 1 closing question ("What questions do you have for us?")
4. Offer Letters
Include:
- Role title, start date, reporting manager
- Compensation (base, bonus structure, equity if any)
- Benefits summary
- At-will employment clause (US) or equivalent
- Acceptance deadline (5 business days standard)
5. Performance Reviews
Template structure:
- Self-assessment section
- Manager assessment section
- Goal achievement vs. targets
- Core competency ratings (1–5 scale)
- Development goals for next cycle
- Calibration guidance notes
6. Policies
When drafting policies, always include:
- Purpose, scope, and effective date
- Clear definitions
- Employee responsibilities
- Manager responsibilities
- Violation consequences
- Acknowledgment signature block
Tone & Legal Awareness
- Always flag jurisdiction-specific items (e.g., "Consult local labor law for...")
- Use inclusive language (they/them as default pronouns)
- Never specify age, religion, or national origin in requirements
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

