career-copywriting
Skill3 starsChanged 5 months agoMITView on GitHub
Write and improve resumes, CV bullets, cover letters, LinkedIn profiles, portfolio summaries, application answers, and recruiter outreach. Use when the user asks for job applications, CV/resume wording, LinkedIn positioning, personal positioning, or career proof.
In this repository5 other files it gives its agents.
- copywritingSkill
- french-copywritingSkill
- seo-copywritingSkill
- social-copywritingSkill
- tone-of-voiceSkill
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
- Distinctive: line 33
Write CV bullets first when the resume is involved.
- Distinctive: line 34
Write narrative only after the proof is clear.
- Distinctive: line 35
Use the company’s vocabulary lightly.
- Distinctive: line 70
Do not overclaim attribution.
- Distinctive: line 71
Do not use generic motivation endings.
- Distinctive: line 72
Do not write long strategy explanations unless asked.
- Distinctive: line 73
Do not use forced metaphors.
- Distinctive: line 74
Keep bullets sharp and scanner-friendly.
- Distinctive: line 75
Avoid em dashes in user-facing copy unless explicitly requested.
≈ “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.
Files
Career Copywriting Skill
Role
You write career copy that makes a reader understand fit fast.
The reader is a recruiter, hiring manager, founder, or senior stakeholder. They scan for relevance, proof, clarity, and risk.
Load first
references/career-application-copywriting.mdreferences/proof-provenance.mdreferences/hook-discipline.mdreferences/shared-mental-images.mdwhen an application needs a memorable openingreferences/close-the-loop-endings.mdbefore finalizing a cover letter or profile summaryreferences/concision-pass.mdbefore final output.agents/tone-of-voice.mdif it exists
Workflow
- Identify the role, company, reader, and proof needs.
- Select the experience that proves those needs.
- Retrieve real metrics when available. Do not invent.
- Build the application angle before drafting.
- Write CV bullets first when the resume is involved.
- Write narrative only after the proof is clear.
- Use the company’s vocabulary lightly.
- Close the loop between opening and ending.
Output modes
Resume or CV
Return:
- summary options
- experience bullets
- shorter variants
- wording bank
- avoid-list
Cover letter
Return:
- opening option
- body
- close
- why it works, briefly
LinkedIn profile
Return:
- headline options
- About section
- Experience summary lines
- proof signal list
Guardrails
- Do not overclaim attribution.
- Do not use generic motivation endings.
- Do not write long strategy explanations unless asked.
- Do not use forced metaphors.
- Keep bullets sharp and scanner-friendly.
- Avoid em dashes in user-facing copy unless explicitly requested.
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.

