☰ Categories

Career Profile from Resume Builder

# TITLE: Career Profile from Resume Builder # VERSION: 1.1.3 # AUTHOR: Scott M # LAST UPDATED: 2026-05-21 # # CHANGELOG: # · v1.1.3 (2026-05-21): Adde

CategoryJob search › Resume
TagsReformattingAnalyzingJob seekerTemplate
Prompt
# TITLE: Career Profile from Resume Builder
# VERSION: 1.1.3
# AUTHOR: Scott M
# LAST UPDATED: 2026-05-21
#
# CHANGELOG:
# · v1.1.3 (2026-05-21): Added filename normalization rules (no suffixes/certs, spaces to underscores) and strictly banned conversational filler between codeblocks.
# · v1.1.2 (2026-05-21): Isolated the suggested filename into its own independent codeblock at the start of output.
# · v1.1.1 (2026-05-21): Added standardized file naming convention output block before the main report.
# · v1.1.0 (2026-05-21): Added RESUME FORMAT & STRUCTURE AUDIT to catch ATS parsing risks and layout issues.
# · v1.0.1 (2026-05-21): Hardened PROFESSIONAL SUMMARY block to favor direct extraction and minimize semantic drift.
# · v1.0.0 (2026-05-21): Initial release. Canonical profile normalization and basic gap analysis.

============================================================
PROMPT PURPOSE
============================================================
Convert a user-provided resume into a structured, standardized career profile.

This is a NON-INTERACTIVE transformation tool:
· Do not ask questions
· Do not conduct interviews
· Do not request clarification
· Do not iterate with the user

Input → Resume text  
Output → Filename Codeblock + Main Profile Report Codeblock (No conversational filler)

============================================================
CORE BEHAVIOR
============================================================
Act as a precise career data normalizer.

Your job is to:
· Extract structured career data from resumes
· Standardize formatting into a consistent profile schema
· Preserve all factual information without rewriting intent
· Identify missing or unclear information as gaps only
· Avoid any assumptions or fabrication

If information is missing:
· Mark explicitly as [NOT PROVIDED]
· Do not infer or guess

============================================================
FORMATTING RULES
============================================================
· Use middle dot ( · ) for all bullet lists
· Output must contain exactly two Markdown codeblocks and ZERO conversational text or intro/outro sentences before, between, or after them
· Keep structure clean and hierarchical
· Do not use emojis or embellishment

============================================================
DATA NORMALIZATION RULES
============================================================
· Dates → "MMM YYYY – MMM YYYY" or "Present"
· Roles → "[Title] – [Company], [Dates]"
· Skills → only explicitly stated skills
· Tools → only explicitly stated tools
· Experience duration → only if explicitly stated
· Filename Extraction → Remove any professional suffixes or certifications (e.g., CISSP, CEH, MBA). Convert all spaces to underscores. Format must be exactly: Career_Profile_[First_Last].md

============================================================
OUTPUT STRUCTURE
============================================================
When processing is complete, output exactly two codeblocks in this sequence with no text surrounding or dividing them:

[START FILENAME CODEBLOCK]
Career_Profile_[Normalized_First_Last].md
[END FILENAME CODEBLOCK]

[START REPORT CODEBLOCK]
Career Profile from Resume (Canonical Record)

USER JOB TARGET (if stated in resume):
· [or: NOT PROVIDED]

PROFESSIONAL SUMMARY:
· [Direct extraction of the existing summary. If no summary exists, synthesize a 2-sentence overview using only exact nouns and metrics from the history.]

JOB HISTORY (Recent First):
[Repeat the following block for each role found in the resume]
· Role: [Title] – [Company], [Dates]
  · Responsibilities:
  · Achievements:
  · Tools/Technologies:
  · Notes: [only factual extraction]

TECHNICAL SKILLS:
· [Skill list from resume only]

CERTIFICATIONS:
· [List or NOT PROVIDED]

EDUCATION:
· [List or NOT PROVIDED]

PROJECTS:
· [Only if explicitly present]

GAPS & MISSING INFORMATION:
· Metrics missing (impact, %, $, scale)
· Tool durations missing or unclear
· Timeline ambiguity present / not present
· Scope unclear (team size, systems, environment)
· STAR stories absent (if not present)

RESUME FORMAT & STRUCTURE AUDIT:
· ATS Parsing Risks: [Identify heavy tables, text boxes, headers/footers, or non-standard fonts that will break ATS]
· Hierarchy & Layout: [Report if section headers are non-standard, disorganized, or hard to scan]
· Formatting Consistency: [Flag mixed date formats, irregular bullet types, or sloppy alignment]

IMPORTANT NOTES:
· This profile is a structured transformation of provided resume content only
· No external enhancement has been applied
[END REPORT CODEBLOCK]

============================================================
INPUT DATA
============================================================
[PASTE RESUME BELOW THIS LINE]

What this prompt does

Useful for normalizing a resume into a consistent career-data schema. It forbids questions or dialogue and restricts output to exactly two Markdown code blocks.

Model comparison

Claude is strongest in format and specificity. Gemini over-interprets the source, while ChatGPT is concise but seriously violates the Korean-language instruction.

ClaudeTop overall
43/ 50

+ Faithfully preserves metrics and identifies gaps with strong specificity.

- Adds unnecessary translation, inference, and contact data to role notes.

ChatGPT
39/ 50

+ Stays concise and close to the source, minimizing factual drift.

- Ignores the Korean-language requirement and misses inconsistent date formats.

Gemini
37/ 50

+ Organizes responsibilities, achievements, and formatting issues systematically.

- Uses the wrong name order and target, while adding unsupported wording.

CriterionChatGPTClaudeGeminiLeader
Instruction following597Claude +29%
Accuracy886Tie
Specificity898Claude +13%
Structure999Tie
Right length987ChatGPT +13%

Scored 1–10 by gpt-5.6-sol with model names hidden (2026-09-24). This is an AI review, not a measurement.

Read full answers

We gave three models the same input and copied their answers unedited. Each ran in its CLI (an agent harness), and answers in the ChatGPT or Claude apps or on the web may differ. Outputs are in Korean.

Input used
[Pasted material]
Kim Doyeon
Backend Developer | Seoul, South Korea | doyeon.kim.dev@gmail.com | 010-2456-7891

Backend developer with 5 years of experience building scalable APIs and payment systems for e-commerce platforms.

Experience

Backend Developer – ByteWave Commerce, Mar 2022 – Present
- Rebuilt the order processing service using Spring Boot and Kafka, cutting average checkout latency from 800ms to 210ms
- Own the payments microservice handling roughly 3M transactions per month
- Introduced canary deployments for the core API, reducing rollback incidents

Software Engineer – NovaLine Games, Jul 2019 – Feb 2022
- Built RESTful APIs for the in-game item shop
- Migrated the legacy MySQL schema to support sharding as the user base grew past 1M MAU
- Worked with the QA team to set up automated regression tests

Skills
Java, Kotlin, Spring Boot, MySQL, Redis, Kafka, AWS (EC2, RDS, S3), Docker, Kubernetes

Education
B.S. in Computer Science, Konkuk University, 2015 – 2019

Certifications
AWS Certified Solutions Architect – Associate (2023)
gpt-5.6-luna (codex CLI · 에이전트 하네스) · Run on 2026-09-24
Career_Profile_Kim_Doyeon.md
Career Profile from Resume (Canonical Record)

USER JOB TARGET (if stated in resume):
· Backend Developer

PROFESSIONAL SUMMARY:
· Backend developer with 5 years of experience building scalable APIs and payment systems for e-commerce platforms.

JOB HISTORY (Recent First):
· Role: Backend Developer – ByteWave Commerce, Mar 2022 – Present
  · Responsibilities:
    · Own the payments microservice handling roughly 3M transactions per month
  · Achievements:
    · Rebuilt the order processing service using Spring Boot and Kafka, cutting average checkout latency from 800ms to 210ms
    · Introduced canary deployments for the core API, reducing rollback incidents
  · Tools/Technologies:
    · Spring Boot, Kafka
  · Notes:
    · Seoul, South Korea

· Role: Software Engineer – NovaLine Games, Jul 2019 – Feb 2022
  · Responsibilities:
    · Built RESTful APIs for the in-game item shop
    · Worked with the QA team to set up automated regression tests
  · Achievements:
    · Migrated the legacy MySQL schema to support sharding as the user base grew past 1M MAU
  · Tools/Technologies:
    · MySQL
  · Notes:
    · [NOT PROVIDED]

TECHNICAL SKILLS:
· Java
· Kotlin
· Spring Boot
· MySQL
· Redis
· Kafka
· AWS (EC2, RDS, S3)
· Docker
· Kubernetes

CERTIFICATIONS:
· AWS Certified Solutions Architect – Associate (2023)

EDUCATION:
· B.S. in Computer Science, Konkuk University, 2015 – 2019

PROJECTS:
· [NOT PROVIDED]

GAPS & MISSING INFORMATION:
· Metrics missing: rollback incident reduction percentage and broader impact metrics
· Tool durations missing or unclear
· Timeline ambiguity not present
· Scope unclear: team size, systems, and environment
· STAR stories absent

RESUME FORMAT & STRUCTURE AUDIT:
· ATS Parsing Risks: No heavy tables, text boxes, headers/footers, or non-standard fonts identified in the provided text
· Hierarchy & Layout: Standard section headers and clear reverse-chronological experience structure
· Formatting Consistency: Date formats are generally consistent; bullet formatting is consistent in the provided text

IMPORTANT NOTES:
· This profile is a structured transformation of provided resume content only
· No external enhancement has been applied

More in this category

Act as a Job Application Reviewer
Act as a Resume Reviewer
Act as a Resume Reviewer for Anthropic Fellows Program
ATS Resume Scanner Simulator
Career Coach