DC

dongjuliana1998-creator/ai-resume-workflow

Data science & ML

This page was translated automatically. Technical details may differ from the original. View the original

21 stars Quality 40 Trend 18

Reusable AI resume tailoring workflow: JD analysis, fact interview, evidence library, HTML/PDF and ATS QA

Overview

JD analysis → evidence gaps → targeted interviews → fact databases → content blueprints → resume text → HTML/PDF → ATS/visual quality inspection → finalization and version records Copy the entire ai-resume-workflow folder to Codex's skills directory: Keep the SKILL.md and agents/openai.yaml positioned relative to each other. After reopening or refreshing Codex, simply say "Customize resume based on this JD" to trigger it. Import the entire folder from WorkBuddy's "Custom Skill" entry, or upload SKILL.md as a skill description as required. If the platform only accepts single files, just upload SKILL.md; agents/openai.yaml is Codex's interface metadata and does not affect core processes. - For new positions, analyze JD and evidence gaps first, then start writing resumes; - Each round can ask up to 3 key questions, and after answering, receive a receipt for inbound and outbound entries; - New numbers are marked as evidence pending supplementation; speculation cannot be written as results; - Styles can only change presentation, not facts; - Only when users explicitly say "finalized" will the version be marked as "Confirmed Submission".

Overview (machine translated)

This is a reusable Chinese resume workflow skill, covering:

JD 分析 → 证据缺口 → 针对性访谈 → 事实库 → 内容蓝图 → 简历文字 → HTML/PDF → ATS/视觉质检 → 定稿与版本记录

Insert Codex

Copy the entire ai-resume-workflow folder into Codex’s skills directory:

If CODEX_HOME is not set, the following is usually used:

Keep the relative positions of SKILL.md and agents/openai.yaml. After reopening or refreshing Codex, simply say “Customize resume based on this JD” to trigger it.

Put in WorkBuddy

Import the entire folder from WorkBuddy’s “Custom Skill” entry, or upload SKILL.md as a skill description as required. If the platform only accepts single files, just upload SKILL.md; agents/openai.yaml is Codex’s interface metadata and does not affect core workflows.

Usage Rules

  • For new positions, first analyze JD and evidence gaps before starting resume writing;
  • Up to 3 key questions can be asked per round, and a receipt for inbound and outbound receipts will be provided after answering;
  • New figures must be marked as evidence pending supplementation; instead, speculation cannot be written as results;
  • Style can only change the presentation, not the facts;
  • Only when the user explicitly states “finalized” will the version be marked as “Confirmed Delivery.”

Skill will prioritize reusing users’ existing directories; If not available, it can create:

This page was translated automatically. Technical details may differ from the original.

Recommended Tools

Try a different keyword or remove a filter.

Install

npx skillfish add dongjuliana1998-creator/ai-resume-workflow
New to MCP? Start with the mcpskill.org guide →