resume-writer
Skill12 starsChanged 5 months agoMITView on GitHub
Writes and rewrites high-impact resumes and CVs that pass ATS screening and win recruiter attention — translating raw work history into quantified, outcome-driven bullet points, choosing the right format, and tailoring to a target role. Use this skill when a user asks to "write my resume", "fix my CV", "make my resume ATS-friendly", "tailor my resume to this job", "turn my experience into bullet points", or wants help with a professional summary, skills section, or resume formatting.
We split this skill into the rules it gives an agent
1 rule. 0 are common, 1 is distinctive, and 0 are very specific to this project.
0
Common
Most of the 5 edited versions we read keep these.
1
Distinctive
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 18
Ask only for what's missing.
“Common” is measured: kept by at least 6 in 10 of the 5 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Resume Writer
Overview
This skill turns a messy work history into a focused, quantified, ATS-passable resume tailored to a specific target role. It optimizes for two readers at once: the applicant tracking system (keyword match, parseable structure) and the human recruiter who skims for ~7 seconds before deciding.
Keywords: resume, CV, curriculum vitae, ATS, job application, bullet points, professional summary, work experience, achievements, cover, career change, recruiter.
When to use vs. not
Use this to write, rewrite, restructure, or tailor a resume. This skill does not fabricate experience, invent metrics, or guarantee an interview — every claim must trace back to something the user actually did. When the user has no numbers, help them estimate honestly ("supported ~40 customers/week"), never invent precise figures.
Inputs to gather first
Ask only for what's missing; infer the rest:
- Target role + a job description (the single most important input — it drives keywords and emphasis).
- Work history: companies, titles, dates, and what they actually did/achieved.
- Education, certifications, key skills/tools.
- Seniority & career stage (student/new-grad, IC, manager, executive, career-changer).
- Region/format norms (US 1-page no-photo vs. EU CV vs. academic CV — see
references/format-by-region.md).
Workflow
- Pick the format. Reverse-chronological by default. Use functional/hybrid only for career changers or large gaps — and warn that ATS and recruiters distrust purely functional resumes. See
references/format-by-region.md. - Mine the job description. Extract the role's must-have keywords, tools, and outcomes. These become the vocabulary the resume must mirror (ATS matches on exact terms).
- Write the headline + summary. A 1-line title and a 2–3 line summary stating who they are, their strongest proof, and what they're targeting. No "results-oriented team player" filler.
- Rewrite every bullet with the impact formula.
Action verb + what you did + quantified result/context. Lead with the outcome when it's strong. Seereferences/bullet-formulas.mdand the verb bank. - Quantify relentlessly. Money, %, time, scale, frequency, or rank. If no hard number exists, use scope ("across 3 teams", "for a 12k-user platform").
- Order by relevance, not just recency. Within each role, put the bullets that match the target job first. Trim bullets older/irrelevant roles to 1–2 lines.
- Build the skills section from real, demonstrated skills that also appear in the JD. Group them (Languages / Tools / Domains). Don't list skills you can't defend in an interview.
- Tighten for ATS. Standard section headings, no tables/columns/text-boxes/images for the parsed version, real bullet characters, common fonts,
.docxor text-based PDF. Seereferences/ats-rules.md. - Cut to length. 1 page for <10 yrs experience, 2 pages otherwise (academic/EU CVs differ). Remove the objective, references-on-request, and anything pre-dating ~15 years unless pivotal.
- Proofread + tailor check. Consistent tense (past for past roles, present for current), parallel structure, zero typos. End with a gap analysis: which JD requirements the resume still doesn't address, and how the user might.
Decision framework
| If the candidate… | Then… |
| Has a linear career in one field | Reverse-chronological, lead with experience |
| Is a new grad / student | Education + projects + internships up top, skills prominent |
| Is changing careers | Hybrid: summary + transferable-skills block, reframe old bullets toward the new target |
| Has employment gaps | Use years not months, add a brief context line, lead with strongest content |
| Is senior/executive | Lead with scope, P&L, team size, strategic outcomes; 2 pages OK |
Worked example
See examples/before-after.md for a vague bullet turned into a quantified, ATS-aligned one, plus a full summary rewrite.
Best Practices
- Tailor per application. One generic resume loses to ten targeted ones. Mirror the JD's language.
- Lead with outcomes, not duties. "Cut onboarding time 40%" beats "responsible for onboarding."
- One idea per bullet, 1–2 lines max. Recruiters skim.
- Strong verbs, no first person. "Led," "shipped," "reduced" — never "I was responsible for."
- Keep a master resume with everything, then cut down per role.
Common Pitfalls
- Inventing or inflating metrics — a single caught lie sinks the candidacy. Estimate honestly instead.
- Duty-listing instead of achievement-showing.
- Fancy templates with columns/graphics that ATS parsers scramble.
- Buzzword soup ("synergistic," "go-getter") with no evidence.
- Same resume for every job — no keyword match, no tailoring.
- Typos and inconsistent tense/formatting — instant credibility loss.
Other versions11 projects use a version of this.
Word for word · 2
- jaskirat1616/grok-skills★ 22100% same
- JayRHa/AgentSkills★ 12100% same
Edited · 0
None found.
Wrote their own version · 9
- jerry-ai-dev/MODULAR-RAG-MCP-SERVER★ 1.2ksame name
- DetectHensenberg/RAG4JZDQ★ 8same name
- SkillMedev/resume-toolkit★ 2same name
- henggeer/Skills★ 1same name
- scoobydont-666/shared-claude-skills★ 1same name
- silence94108/skills★ 1same name
- anhvu3594/claude-skills★ 0same name
- RagavRida/resume-writer★ 0same name
- rishb0/resume-harness★ 0same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository75 other files it gives its agents.
- 0-templateSkill
- ab-test-analyzerSkill
- adr-authorSkill
- api-designerSkill
- api-docs-writerSkill
- aws-cost-optimizerSkill
- bash-script-hardeningSkill
- blog-post-writerSkill
- book-summarizerSkill
- changelog-keeperSkill
- chart-chooserSkill
- code-reviewerSkill
- competitive-analysisSkill
- concept-explainerSkill
- cover-letter-writerSkill
- cron-schedulerSkill
- data-pipeline-architectSkill
- debug-detectiveSkill
- decision-matrixSkill
- dependency-upgraderSkill
- dockerfile-proSkill
- email-composerSkill
- error-handling-patternsSkill
- event-plannerSkill
- flashcard-generatorSkill
- gdpr-data-mapperSkill
- gift-advisorSkill
- github-actions-builderSkill
- git-workflowSkill
- habit-builderSkill
- incident-postmortemSkill
- interview-prepSkill
- job-description-writerSkill
- json-schema-authorSkill
- kubernetes-manifest-authorSkill
- language-tutorSkill
- meal-plan-builderSkill
- meeting-summarizerSkill
- mermaid-diagram-builderSkill
- nginx-config-proSkill
- observability-setupSkill
- okr-writerSkill
- pandas-data-cleaningSkill
- people-dataSkill
- performance-profilerSkill
- personal-budget-plannerSkill
- presentation-builderSkill
- project-plannerSkill
- prompt-engineerSkill
- proofreaderSkill
- public-speaking-coachSkill
- rag-pipeline-designerSkill
- readme-generatorSkill
- refactoring-guideSkill
- regex-architectSkill
- release-notes-writerSkill
- salary-negotiatorSkill
- secrets-managerSkill
- secure-code-reviewSkill
- secure-password-policySkill
- The first 60 shown.
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.

