Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsBlogPro
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Authors
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges
  • Chrome Extension
  • Skill Manager

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

ProTermsPrivacyRefunds
Back to skills

Resume Writer

ASecurity

Draft, tailor, and polish resumes for specific roles using achievement-based bullets and recruiter conventions.

2 stars
0 votes
0 copies
0 views
Added 9/29/2026
ai-agentsgokubernetes

Security Analysis

A100/100

Scanned 9/29/2026

$npx -y skills add aicodedecode/awesome-muse-skills --skill resume-writer --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Resume Writer?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Resume Writer
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/aicodedecode-resume-writer/badge)](https://www.skillsdirectory.com/skills/aicodedecode-resume-writer)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
Files
SKILL.md
---
name: resume-writer
description: Draft, tailor, and polish resumes for specific roles using achievement-based bullets and recruiter conventions.
category: career
---

## Overview

A strong resume is not a biography — it is a sales document engineered to win a 6-second scan and
pass an Applicant Tracking System (ATS). This skill guides you through building a resume from raw
career facts to a tailored, one-page (or two-page, for 10+ years) document that speaks the
employer's language. The core philosophy: every line must earn its place by showing impact, not just
activity.

## When to use

- Drafting a resume from scratch or rebuilding a stale one

- Tailoring a master resume to a specific job description

- Rewriting vague responsibility bullets into achievement bullets

- Reformatting for ATS compatibility or international conventions (CV vs resume)

- Preparing multiple versions (tech, product, leadership) for different target roles

## Core concepts

- - **Master resume vs target resume.** Keep one long master resume with every role, project, and
  metric. For each application, clone it and cut/reorder to match the target job — never send the
  uncut master.
- - **The XYZ formula.** Every bullet: "Accomplished X (measurable result), as measured by Y, by
  doing Z (action)." Numbers beat adjectives. "Improved retention 22%" beats "improved retention
  significantly."
- - **The 6-second scan test.** Recruiters scan an F-pattern: name/title, current role, then the
  first words of each bullet. Front-load keywords and results at the start of lines.
- - **ATS parsing rules.** Single-column layout, standard section headers (Experience, Education,
  Skills), no tables/text boxes/images, standard fonts, and save as PDF unless the posting says
  otherwise.
- - **Skills vs tools.** "Skills" section should mirror the job description's keywords (languages,
  frameworks, methodologies) — this is what the ATS matches and what the recruiter ctrl-F's for.
- - **Reverse-chronological is default.** Functional/resume hybrids look like you're hiding
  something. Only use alternatives for career gaps or pivots, and do so deliberately.

## Practical workflow

1. 1. **Intake.** Collect: target job posting(s), full work history (dates, titles, companies), key
   projects with any metrics, education, certifications, and relevant skills. If the user is vague,
   ask for the job posting first — everything flows from the target.
2. 2. **Extract keywords.** Pull 10-15 hard requirements from the posting (tech stack, domain,
   seniority signals). Map each to something in the user's history.
3. 3. **Draft the header.** Name, one-line professional title targeting the role, location (city,
   not street address), phone, email, LinkedIn URL. No photo, no birth date, no "references
   available on request."
4. 4. **Write the summary (3 lines max).** Only for senior roles or pivots: years of experience +
   domain + 1-2 headline achievements. Junior candidates should skip it and go straight to
   experience.
5. 5. **Rewrite experience bullets.** For each role: 3-6 bullets, strongest first. Convert every
   duty into an achievement using the XYZ formula. Add scale cues (team size, budget, users,
   revenue) even when exact numbers are fuzzy — "team of 6" is better than nothing.
6. 6. **Prune and tailor.** Cut anything irrelevant to the target. If the posting is senior IC, cut
   management fluff; if it's a leadership role, elevate team-scale results. Aim for one page under
   10 years of experience.
7. 7. **ATS pass.** Check: one column, standard fonts, no graphics, keyword density matches the
   posting, dates are consistent (MM/YYYY or YYYY).
8. 8. **Final polish.** Read the resume backwards (bottom-up) to catch typos. Verify every number is
   defensible in an interview — "I read the resume" questions are the first interview filter.

## Common pitfalls

- - **Listing duties instead of results.** "Responsible for the deployment pipeline" says nothing.
  "Cut deploy time from 45 min to 8 min by migrating to containerized CI" gets interviews.
- - **Inflating titles or metrics.** Recruiters and background checks catch this. Stretch phrasing
  is fine; invented numbers are not.
- - **Keyword stuffing without evidence.** An ATS may rank you higher, but a human will ask "you
  list Kubernetes — what did you actually build with it?" Only claim what you can discuss.
- - **Two-page resume for 3 years of experience.** Ruthless editing is a signal of seniority. One
  page until you genuinely need two.
- - **Generic objective statements.** "Seeking a challenging role where I can utilize my skills"
  wastes the most valuable real estate on the page. Delete it.
- - **Forgetting the job posting link.** A resume written without the posting is decoration. Always
  anchor to a real target.

Attribution

aicodedecodeaicodedecode
View sourceSee grades on GitHubMore from aicodedecode →
SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Related Skills

Caveman

Terse caveman voice: answer first, fluff gone, every technical fact kept. Use for /caveman, "caveman mode", "talk like caveman", "be brief", "less tokens". Stays on until "stop caveman" or "normal mode".

1100021 votes

Hyperplan

Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...

698621 votes

Writing Skills

Create and manage Claude Code skills in HASH repository following Anthropic best practices. Use when creating new skills, modifying skill-rules.json, understanding trigger patterns, working with hooks, debugging skill activation, or implementing progressive disclosure. Covers skill structure, YAML frontmatter, trigger types (keywords, intent patterns), UserPromptSubmit hook, and the 500-line rule. Includes validation and debugging with SKILL_DEBUG. Examples include rust-error-stack, cargo-dep...

3931 votes

Mcp Code Execution

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

3421 votes

catchup

Recovers the conversation and failed tool calls of a previous Codex, Amp, Claude Code, Antigravity, Cline, Copilot CLI, Cursor, DeepSeek Harness, Grok Build, Kimi, OpenCode, Pi Agent, or ZCode session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", asks to recover/summarize a previous session before continuing, or asks to diagnose or report a catchup failure. Do NOT use for the current conversation, git history, or any non-agent log.

741 votes
View all in ai-agents →