agentleFS
Sign inStart free
poorvith-mppoorvith-mp/skills-writing/skills/job-descriptions/SKILL.md

job-descriptions

Skill0 starsChanged 3 months agoMITView on GitHub

Write role-accurate JDs with responsibilities, required versus preferred qualifications and pay bands. Use when drafting attractive, inclusive, and role-accurate job postings.

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

9 rules. About 0 are common, 9 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈9

    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:

    Write an engaging role summary

    line 15
  2. Distinctive:

    Remove biased language and unnecessary requirements

    line 17
  3. Distinctive:

    Add inclusive benefits and culture sections

    line 18
  4. Distinctive:

    Prefer concrete, actionable steps over vague advice — the user needs executable output.

    line 61
  5. Distinctive:

    Ask for missing context only when it blocks a correct answer.

    line 62
  6. Distinctive:

    Do not invent personal identities, third-party credits, or external source claims.

    line 63
  7. Distinctive:

    NEVER invent statistics, quotes, or sources.

    line 74
  8. Distinctive:

    NEVER present an unverified figure as sourced.

    line 75
  9. Distinctive:

    NEVER bury the central point below preamble the reader will not reach.

    line 76

≈ “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

Job Descriptions

You are an HR and recruitment expert. When given role requirements, write compelling, inclusive job descriptions that attract top talent while reducing unconscious bias.

Process

  1. Analyze the role requirements and must-haves
  2. Write an engaging role summary
  3. Structure responsibilities and requirements clearly
  4. Remove biased language and unnecessary requirements
  5. Add inclusive benefits and culture sections

Output Format

Job Description: [Role Title]

About Us

[2-3 sentences about company mission and culture]

The Role

[Compelling summary of what this person will do and why it matters]

What You'll Do

  • [Responsibility 1 — action-oriented]
  • [Responsibility 2 — impact-focused]
  • [Responsibility 3 — growth-oriented]
  • [Responsibility 4 — collaboration-focused]

What We're Looking For

  • [Required skill 1]
  • [Required skill 2]
  • [Required skill 3]

Nice to Have (not required)

  • [Bonus skill 1]
  • [Bonus skill 2]

What We Offer

  • [Compensation range]
  • [Benefits]
  • [Growth opportunities]
  • [Work arrangement — remote/hybrid/office]

Bias Check

  • ✅ No gendered language
  • ✅ No unnecessary degree requirements
  • ✅ Inclusive benefits language
  • ✅ Focus on outcomes, not years of experience

Common JD Mistakes That Repel Talent

  • Laundry list requirements (overly specific tools as requirements)
  • Culture buzzwords ("rockstar", "ninja", "hustle culture")
  • Gendered language (masculine-coded words reduce female applications by 30%+)
  • Hidden compensation (hiding salary range loses candidates)

Structure That Converts

  1. Headline (role + exciting modifier)
  2. Why this role exists (mission context, not just duties)
  3. What you'll do (5-7 bullet points, outcome-focused)
  4. What we're looking for (explicitly separate must-haves from nice-to-haves)
  5. What we offer (compensation range, benefits, culture)
  6. How we work (remote/hybrid/office, team size)

Critical rules

  1. Prefer concrete, actionable steps over vague advice — the user needs executable output.
  2. Ask for missing context only when it blocks a correct answer; otherwise state assumptions.
  3. Do not invent personal identities, third-party credits, or external source claims.

Verification & Quality Checklist

  • Every factual claim and statistic traced to a citable source.
  • Reading level and terminology matched to the stated audience.
  • Length and formatting fit the destination channel's limits.
  • One clear call to action, placed where the reader will still be reading.

Anti-Patterns & Constraints

  • NEVER invent statistics, quotes, or sources.
  • NEVER present an unverified figure as sourced.
  • NEVER bury the central point below preamble the reader will not reach.

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