com um clique
tailor-resume
Tailor your resume for a specific job posting
Instalar com Codex ou Claude Copie este prompt, cole no Codex, Claude ou outro assistente e deixe que ele revise a página da skill e instale para você.
Menu
Tailor your resume for a specific job posting
Instalar com Codex ou Claude Copie este prompt, cole no Codex, Claude ou outro assistente e deixe que ele revise a página da skill e instale para você.
Baseado na classificação ocupacional SOC
Analyze images, websites, and Figma files to extract their design and generate a `design.md` with token system, component inventory, and reconstruction notes. Use this skill whenever the user wants to understand, document, replicate, or audit the design of something visual: a screenshot, a URL, a Figma link, a Pinterest reference, a mockup, a competitor's site, a component, a dashboard, a landing page. Also when they ask 'extract the design system from X', 'document the style of Y', 'analyze this visually', 'convert this image into tokens', 'help me replicate this design', 'what palette does this site use', 'how is this built'. Also for single elements: 'copy this navbar', 'recreate this illustration', 'give me a prompt to regenerate this graphic' — element mode outputs a focused element.md, with token-grounded image-model prompts when the element is visual art. If the user brings any visual source and wants to understand it at a design level — this skill should activate.
Code review automation for TypeScript, JavaScript, Python, Go, Swift, Kotlin, C#, .NET, Java, C, C++, Rust, Ruby, PHP, and Dart/Flutter. Analyzes PRs for complexity and risk, checks code quality for SOLID violations and code smells, generates review reports. Use when reviewing pull requests, analyzing code quality, identifying issues, generating review checklists.
Fill out a job application on Greenhouse, Lever, or Workday
Define what content a product needs, how it should be structured, and who owns it.
Write a tailored cover letter for a specific job posting
Craft-first interface design for dashboards, admin panels, SaaS apps, tools, settings pages, data interfaces, and interactive products. Use when designing, building, reviewing, auditing, or refining product UI where visual craft, layout hierarchy, tokens, states, visual direction, or design-system consistency matter. Not for marketing pages, landing pages, campaigns, or brand-only work.
| name | tailor-resume |
| description | Tailor your resume for a specific job posting |
| argument-hint | job URL |
Priority hierarchy: See
references/priority-hierarchy.mdfor conflict resolution.
Create compelling, tailored resumes that make it obvious you're the right candidate for a specific job.
scripts/
tailor-resume.md # Resume tailoring subagent prompt
The profile template is at references/profile.md.
Resolve the data directory using references/data-directory.md.
Resolve the data directory, then check prerequisites per references/prerequisites.md. Resume is required; profile is strongly recommended. If the user proceeds without a profile, set a flag to present all assumptions for verification (see Step 3a below).
If $ARGUMENTS is a URL, continue to Step 1.
Otherwise, ask for a job URL.
Accept a job URL from the user (from $ARGUMENTS or by asking).
Use Claude in Chrome MCP tools to fetch the job posting per references/browser-setup.md.
Parse and extract:
Create a job folder at DATA_DIR/jobs/[company-slug]-[date]/ and save the parsed job posting to posting.md.
If the page can't be loaded or parsed, ask the user to paste the job description directly.
Before writing, map the candidate's experience to the job:
Level match: Confirm the candidate's experience level matches the role. A VP-level candidate applying for a Director role should lean on strategic impact. A Director applying for VP should emphasize scope and leadership growth.
Requirement mapping: For each job requirement, identify the strongest evidence from the work history profile:
Gap identification: Note any requirements where the candidate has no clear match. These should NOT be fabricated - instead, find adjacent experience that demonstrates capability.
Keyword alignment: Identify the job posting's language and terminology to mirror in the resume.
Compelling narrative: Determine the 2-3 sentence story of why this person is the obvious choice. What's the throughline?
Create the tailored resume following these principles:
Structure:
Bullet point principles:
Level-matching:
Writing rules (CRITICAL — target Flesch score above 90):
Strict accuracy rules (CRITICAL):
What NOT to do:
Before showing the resume to the user, review every line and fix AI-sounding writing. Go sentence by sentence and ask:
Common AI patterns to kill:
Test: After rewriting, re-read the summary and first 3 bullets. If any sentence takes more than one breath to read out loud, it's too long. Shorten it.
Output:
Save the tailored resume to DATA_DIR/jobs/[company-slug]-[date]/resume.md
Present the resume to the user with a brief explanation:
Here's your tailored resume for [Role] at [Company].
**Key changes I made:**
- [What was reordered/emphasized and why]
- [What bullets were rewritten and why]
- [What was added from your work history]
**The narrative:** [2-3 sentence pitch for why you're the right person]
The resume is saved to: DATA_DIR/jobs/[folder]/resume.md
If no work history profile was available, present the user with a list of every assumption made:
Before we finalize, here are the assumptions I made. Please correct
any that are wrong:
1. [Company] - I assumed [X]. Is that right?
2. [Role scope] - I described your scope as [Y]. Accurate?
3. [Business model] - I framed this as [Z]. Correct?
...
Wait for the user to verify or correct before finalizing. Apply all corrections to the resume AND save them to DATA_DIR/profile.md so they persist.
Ask if the user wants to adjust anything:
Apply changes and re-save.
Every time the user corrects a factual detail, update DATA_DIR/profile.md immediately:
This prevents the same mistakes on future resumes. If the profile is still a blank template, create a new one with whatever the user has told you so far. Use the structure from references/profile.md but fill in only what you know for certain.
Structure user-facing output with these sections: