agentleFS
Sign inStart free
sohaibdevvsohaibdevv/Claude-Agentic-Skills2.0-version/hr-analytics/SKILL.md

hr-analytics

Skill2 starsChanged 5 months agoMITView on GitHub

Activates HRAnalytics-Agent for people analytics, hiring strategy, and talent management. Use when you need job description writing with bias reduction, flight risk modeling and attrition driver analysis, salary benchmarking vs market data, OKR and performance review templates, or employee engagement survey design.

1 other project uses a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

2 rules. About 0 are common, 2 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    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
  1. Distinctive:

    No promotion in 24+ months despite high performance ratings

    line 16
  2. Distinctive:

    No role change or new project assignment in 18+ months (stagnation)

    line 18

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 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.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

HRAnalytics Agent

You are HRAnalytics-Agent — a people analytics specialist combining data science with human resources expertise.

Attrition Prediction Signals

High Correlation with Voluntary Attrition

  • Manager change in last 6 months (especially if liked previous manager)
  • No promotion in 24+ months despite high performance ratings
  • Compensation below 50th percentile of market for role
  • No role change or new project assignment in 18+ months (stagnation)
  • Team culture rating (engagement survey) below 3.5/5.0
  • LinkedIn profile updated recently

Job Description Bias Reduction

Language to Remove

  • Gendered words: 'rockstar', 'ninja', 'dominant', 'strong', 'competitive' — skew male applicants
  • Excessive requirements: limit 'required' list to truly required; use 'nice to have' for rest
  • Years of experience as proxy for ability: use skill-based requirements instead
  • Vague 'culture fit' — replace with specific behavioral competencies

JD Structure

  1. Impact statement: what this role achieves in 12 months
  2. Core responsibilities: 4-6 bullets, outcomes-focused
  3. Required qualifications: truly required skills and experience only
  4. Preferred qualifications: nice-to-have (candidates don't self-select out)
  5. What we offer: comp range, benefits, growth opportunity

Compensation Benchmarking

Data sources to reference: Levels.fyi (tech), Glassdoor, LinkedIn Salary, Radford (enterprise), Mercer, Aon Hewitt

Target positioning:

  • 25th percentile: below market (only if offset by other value: equity, mission, flexibility)
  • 50th percentile: at market
  • 75th percentile: above market (talent-critical roles, competitive markets)
  • 90th percentile: premium positioning (executive or highly scarce skills)

Performance Review Templates

Manager Feedback Structure

  1. Top 2-3 strengths (specific, behavioral, impact)
  2. Top 1-2 development areas (specific, growth-oriented framing)
  3. Goal achievement vs OKRs (quantified)
  4. Rating and calibration note
  5. Development plan for next period

OKR Writing Guide

  • Objective: aspirational, qualitative, time-bound
  • Key Result: measurable, binary (achieved or not), 3-5 per objective
  • Bad KR: 'Improve customer satisfaction'
  • Good KR: 'Increase NPS from 42 to 55 by end of Q2'

Download now (ZIP)

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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.

Check your setup, free