Resume builder cn

Resume Builder CN

Build truthful, targeted resumes from a reusable personal information library. Default to Chinese unless the user requests English or bilingual output.

Quick Start

Use the smallest workflow that satisfies the user's request.

If the user has no target role yet

Start with candidate intake and master profile construction.

Goal: build career-master-profile.md and identify missing information.

If the user has a target role, JD, job link, screenshot, company, team, or lab

Start with job intelligence and matching before writing.

Goal: produce job analysis, matching matrix, evidence selection, and a targeted resume.

If the user already has a resume

First inspect the existing resume, diagnose structure and evidence quality, then decide whether role research is needed.

If the user only wants critique

Do not generate a full resume package.

Output diagnosis, missing information, and prioritized revision suggestions.

If the user explicitly asks for deliverable files

Generate Markdown or HTML first. Generate PDF only when explicitly requested or when final delivery requires it.

Choose the Workflow

User Input	Start From	Main Workflow	Default Output
"帮我看看简历有什么问题"	Resume inspection	Quick diagnosis	diagnosis + revision suggestions
"帮我做一份简历"	Candidate intake	Master profile + resume draft	master profile + resume draft
"我有这个岗位/JD/链接/截图"	Job intelligence	Targeted application package	job analysis + matching matrix + targeted resume + missing info
"根据这个岗位优化我的简历"	Job intelligence, then evidence matching	Targeted rewrite	matching matrix + optimized resume
"帮我生成 PDF/HTML 文件"	Existing resume or targeted draft	File generation and validation	HTML and optional PDF
"做中英双语版本"	Language-specific drafting	Bilingual resume workflow	Chinese version + English version
"帮我准备科研/学术简历"	Candidate classification	Research-oriented resume workflow	academic/research resume draft

Where to Start

Start by reading only the rule files needed for the classified request:

• routing/classification: references/candidate_classification.md;
• all cases: references/intake_schema.md and references/resume_writing_rules.md;
• students/researchers: references/student_academic_rules.md;
• publications and patents: references/publications_and_patents_rules.md;
• experienced candidates/career changers: references/experienced_candidate_rules.md;
• targeted applications: references/job_source_rules.md, references/online_role_research.md, and the matching/evidence rules listed in the critical path;
• layout: references/template_designs.md;
• templates and examples: use assets/templates/ for required output structures and examples/ only as format and quality references;
• content tuning, evidence trace table, bilingual version, photo prompt, and full master profile JSON only when explicitly requested;
• final review: references/output_quality_checklist.md.

Templates and Examples

Use templates in assets/templates/ to standardize output structure. Use examples in examples/ only as format and quality references. Never copy example facts, metrics, institutions, publications, awards, or experience content into a user's resume.

Templates define required sections and fields. Examples demonstrate acceptable reasoning depth, evidence traceability, bullet quality, layout density, and pass/fail quality standards.

When examples conflict with user evidence, job evidence, or non-negotiable rules, follow the user's evidence and the non-negotiable rules.

Mandatory Routing Step: Classify Before Writing

Before writing, rewriting, researching, or generating files, classify both the candidate and the resume scenario using references/candidate_classification.md.

Read references/candidate_classification.md before selecting candidate rules or scenario-specific workflows.

This classification determines:

• which rules to read;
• whether online job research is required;
• whether the output should be a quick diagnosis, generic resume, targeted resume, academic CV, or full deliverable package;
• which personal information should be included or omitted;
• whether ATS compatibility, visual layout, bilingual writing, or photo guidance is relevant.

Classify the candidate:

• student;
• recent graduate;
• research-oriented candidate;
• experienced candidate;
• career changer.

Classify the scenario:

• Chinese resume;
• English resume;
• bilingual resume;
• academic/research CV;
• corporate job resume;
• internship resume.

Critical Path for Targeted Resumes: Job Intelligence and Matching

Run this path whenever the user provides:

• a job URL;
• JD text;
• JD screenshot;
• recruitment poster;
• company, team, lab, department, or research group name;
• target role title;
• request to optimize a resume for a specific position.

Do not draft the targeted resume before this path is completed or explicitly skipped due to lack of sources.

Read these files in order:

1. references/job_source_rules.md
2. references/job_requirement_extraction_schema.md
3. references/candidate_evidence_schema.md
4. references/matching_scoring_rules.md
5. references/experience_selection_rules.md
6. references/traceability_rules.md

The module must preserve this chain:

job source -> requirement -> candidate evidence -> match score -> adoption decision -> resume bullet

Use stable IDs throughout the chain:

• job sources: JS-001, JS-002, ...
• job requirements: RQ-001, RQ-002, ...
• candidate evidence: EV-001, EV-002, ...
• resume bullets: BL-001, BL-002, ...

Each final bullet must include a hidden or separate trace record, for example:

BL-001 -> EV-003, EV-007 -> RQ-002, RQ-005 -> JS-001

Use the scripts as deterministic structuring aids. Their lexical scores are baselines, not substitutes for evidence-aware review.

If scripts are unavailable, perform the same schema transformation manually and clearly state that script validation was not run.

Decision Flow

Choose the smallest mode that satisfies the user request. Do not escalate to a larger deliverable set unless the user explicitly asks for those outputs.

Mode A: Quick Resume Diagnosis

Use when the user only asks for review, critique, or improvement suggestions.

Output: diagnosis, missing information, rewrite suggestions.

Mode B: Resume Rewrite

Use when the user provides an existing resume but no specific target role.

Output: revised resume content, optional Markdown/HTML.

Mode C: Targeted Application Package

Use when the user provides a JD, job link, company/team/lab name, or target role.

Run job intelligence, matching, evidence selection, and traceability.

Output: job-analysis-report.md, matching-matrix.md, targeted-resume.md or targeted-resume.html, and missing-info.md. Generate PDF only when requested.

Mode D: Full Deliverable Package

Use only when the user explicitly asks for files, HTML, PDF, editable templates, or complete package.

Output may include master profile, full master profile JSON, job report, matching matrix, resume HTML/PDF, trace table, content tuning sheet, bilingual version, and photo prompt according to the user's explicit request.

Use and Boundaries

Use for job/internship resumes, industry research resumes, concise academic CVs, resume optimization, bilingual conversion, and role-fit analysis. Photo guidance is auxiliary and should only be used when the user asks for resume/profile photo advice together with a resume task.

Do not use for government identity documents, visa/passport photos, fabricated credentials, deceptive employment histories, or full academic dossiers when the user needs a discipline-specific institutional format that has not been supplied.

Non-Negotiable Rules

• Never invent education, experience, metrics, publications, patents, awards, dates, authorship, skills, or proficiency.
• Mark uncertain content as 待补充 or 需用户确认.
• Keep the complete master profile separate from each targeted resume.
• Trace every resume claim to personal evidence and every selection decision to researched role evidence.
• Ask one coherent topic group at a time unless the user requests a form.
• Preserve accurate technical terminology and publication status.
• For publications and patents, preserve exact authorship role, author/inventor order, status, DOI/patent number, journal/venue, partition/quartile, and verification source. Never upgrade unpublished, submitted, under-review, accepted, or patent-application status without evidence.
• Use action + task + method/tool + result/impact for experience bullets.
• Generate HTML as the primary editable, printable resume; generate Markdown when requested or useful for review; generate PDF only when requested or clearly needed.
• When ATS compatibility is required, generate a plain Markdown or DOCX-friendly version and do not rely on the HTML/PDF visual version as the only deliverable.

Workflow

1. Inspect and diagnose

Read supplied resumes, CVs, transcripts, notes, publications, portfolios, job links, and images before asking questions. Determine candidate type, scenario, output language, missing information, conflicts, and privacy preferences.

Do not ask for all missing information at once. First use available materials to produce:

1. current profile summary;
2. missing critical fields;
3. optional enhancement fields.

Only ask for information that changes the resume decision.

Run scripts/validate_intake.py when structured JSON is available.

2. Collect and normalize information

Follow references/intake_schema.md. Accept free-form conversation and summarize each topic for confirmation. Store complete candidate information only in the current working/output directory, never inside the skill package. Use assets/master_profile_template.md only as a blank template to copy or reference.

Use scripts/normalize_resume_json.py to normalize a JSON intake. Do not place personal data inside the skill directory.

3. Research the target online

For a specific application, follow references/job_source_rules.md and references/online_role_research.md even when the user supplies a JD.

Supported inputs include:

• official or third-party job URLs;
• team, laboratory, research-group, department, or project pages;
• JD screenshots, recruitment posters, official-account screenshots;
• copied JD text, HR descriptions, email text, or user summaries.

For screenshots, use OCR/vision to extract text and retain the screenshot/file as a source description. Never treat an unverified screenshot as an official source.

If online research is unavailable, use the user-provided JD as the primary source, mark source confidence as limited, ask for an official link if needed, and do not invent missing requirements.

Confirm the exact employer, title, location, seniority, requisition, URL, and posting status. Prefer current official employer sources; cross-check official team/product/ research pages and recent comparable roles. Record URLs, publication/access dates, source type, evidence level, and confidence.

Collect principal work activities, expected outputs, stakeholders, mandatory and preferred skills, methods, tools, standards, seniority, and logistical constraints. Separate explicit requirements, tentative requirements, and generic market signals.

3a. Complete publication and patent metadata when needed

When the user provides incomplete publication or patent information and the information is relevant to the resume, search online to complete verifiable metadata.

For publications, search by DOI, exact title, title + first author, journal + year + author, or publisher/Crossref/PubMed/Web of Science records when accessible.

For patents, search by application number, publication number, grant number, exact title, inventor + title keywords, CNIPA, Google Patents, WIPO PATENTSCOPE, USPTO, or other official patent databases.

Only complete fields supported by sources. If sources conflict, preserve the conflict and mark the field 需用户确认.

4. Evaluate fit and select evidence

Normalize sources and extract requirements using the module schemas. Convert the master profile into atomic candidate evidence. Follow references/matching_scoring_rules.md and references/job_matching.md. Map each requirement to candidate evidence IDs, calculate the 0-5 match score, requirement weight, credibility coefficient, and composite score, then identify eligibility or credibility risks. Flag but do not automatically include low GPA, failed courses, unfinished degrees, unexplained gaps, unrelated short experiences, weak low-relevance awards or certificates, unverified claims, exaggerated proficiency, sensitive personal information, or publications listed as accepted/submitted/in preparation without evidence. Omit when unnecessary, reframe truthfully when relevant, and mark 需用户确认 when uncertain.

Rank projects and roles, then classify them as:

• lead: early placement and detailed bullets;
• support: concise complementary evidence;
• omit: retained in the master profile but excluded from this resume.

Use the adoption thresholds from references/experience_selection_rules.md: lead requires a high-priority requirement with composite score >= 16; support covers composite score 8-15 or useful complementary evidence; omit covers composite score < 8, irrelevant, risky, unverifiable, or space-inefficient evidence.

Do not select content solely by prestige. Cover high-priority requirements with the smallest coherent evidence set.

Create a traceability record for every key final bullet using references/traceability_rules.md.

5. Draft for the candidate type

• Students/recent graduates: emphasize education, GPA/rank when favorable and confirmed, research training, projects, methods, publications, patents, competitions, scholarships, and evidence-backed skills.
• Research candidates: emphasize research question, technical route, personal contribution, results, outputs, methods, and reproducibility.
• For research projects, structure bullets around research aim, experimental or computational strategy, personal contribution, key methods/instruments/datasets/models, output, and relevance to the target role.

For publications and patents, follow references/publications_and_patents_rules.md. Rank first-author and co-first-author outputs by target-role relevance before collaborative outputs. Rank collaborative papers by relevance after first-author/ co-first-author work. Use CAS journal partition for Chinese resumes when available, and JCR quartile for English resumes when available. For unpublished work, label status precisely as 手稿准备中, 投稿待审中, 同行评审中, or 已接收. If publication or patent metadata is incomplete, perform online lookup when enough identifying information is provided, and mark unresolved fields as 待补充 or 需用户确认.

• Experienced candidates: emphasize recent relevant roles, results, scope, tools, collaboration, leadership, and quantified impact.
• Career changers: foreground transferable capabilities and adjacent evidence without overstating direct experience.

Generate self-evaluation only as capability + evidence + role relevance. Generate career interests from target role, industry, experience, and capability structure; avoid generic enthusiasm.

6. Apply regional and language rules

Chinese resumes may include gender, political affiliation, native place, date of birth, photo, or address only when the user supplies them or explicitly requests them. Do not infer age from graduation year unless the user asks. Do not include political affiliation unless the user provides it.

English resumes default to no photo, no gender, no age, no marital status, no political affiliation, and no full address. Use city/country only if location relevance matters. Ask before adding protected or market-sensitive personal information.

For research, biotech, chemistry, pharmaceutical, and academic roles, prioritize research outputs over generic self-evaluation.

For bilingual output, create two independently polished versions. Do not produce a literal line-by-line translation that damages terminology or layout. Generate a bilingual version only when explicitly requested.

7. Generate deliverables

Default targeted output:

1. job-analysis-report.md;
2. matching-matrix.md;
3. targeted-resume.md or targeted-resume.html;
4. missing-info.md.

Generate only when explicitly requested:

• content tuning sheet;
• evidence trace table;
• bilingual version;
• photo prompt;
• full master profile JSON.

Use templates in assets/templates/. HTML is the final layout source. Markdown templates are content scaffolds and review formats.

When the user wants to self-edit content, provide a content tuning sheet based on assets/templates/content_tuning_sheet.md. Keep one row per key bullet or section, with editable short/standard/expanded versions, target keywords, evidence IDs, and a user notes column. Do not ask the user to edit only the final PDF.

When the user wants to self-edit layout, also provide an editable tuning copy based on assets/templates/resume_editable_tuning.html. Preserve CSS variables for page padding, font size, line height, list indent, and --content-align so the user can make small adjustments without editing every section.

For Markdown generation from JSON:

python scripts/export_markdown_resume.py --json <profile.json> \
  --template <template.md> --out <resume.md>

For HTML/PDF validation:

python scripts/check_resume.py --html <resume.html>
python scripts/render_pdf.py --in <resume.html> --out <resume.pdf> --paper A4

Inspect the rendered PDF visually.

If PDF rendering fails, provide HTML and Markdown, report the validation or rendering failure, and do not claim the PDF was generated.

8. Handle photo requests

Read references/photo_generation_rules.md only when the user asks for resume/profile photo advice together with a resume task. If the user supplies their own image and requests editing, use image generation/editing tooling with the closest prompt in assets/photo_prompts/.

If no personal photo is supplied, provide a prompt and request an upload; do not generate a specific fake identity. State that generated/edited images are for resumes, professional profiles, or internal display, not official identity documents.

9. Quality check and deliver

Run references/output_quality_checklist.md. Report:

• 信息完整度诊断;
• 缺失信息清单;
• 简历定位与岗位匹配建议;
• 简历正文或文件;
• 可选优化版本;
• 求职照片建议与提示词 when relevant and explicitly requested with a resume task;
• 下一步优化建议.

For targeted applications, present:

• job-analysis-report.md;
• matching-matrix.md;
• targeted-resume.md or targeted-resume.html;
• missing-info.md;

Only add content tuning sheet, evidence trace table, bilingual version, photo prompt, or full master profile JSON when explicitly requested.

Omit irrelevant sections instead of outputting empty headings.

Measurable Quality Gates

Length and Density

For one-page Chinese resumes:

• recommended total length: 700-1200 Chinese characters, excluding contact information;
• each project or experience section should usually contain 2-4 bullets;
• each bullet should usually be 35-80 Chinese characters;
• avoid paragraphs longer than 3 lines in the rendered PDF;
• avoid more than 6 bullets under one single experience unless the user asks for a detailed CV.

For one-page English resumes:

• recommended total length: 450-750 words;
• each bullet should usually be 12-28 words;
• each experience or project entry should usually contain 2-5 bullets;
• avoid dense paragraphs; use bullet-based evidence.

For academic CVs:

• length may exceed one page;
• publication, patent, presentation, and teaching sections may be expanded;
• do not force compression if the target is academic evaluation.

Line Break and Typography

• Do not break inside names, degree names, school names, company names, journal names, project names, method names, chemical/protein names, or technical terms.
• Keep Chinese-English mixed technical terms intact when possible, e.g. LC-MS/MS, chemical proteomics, 蛋白质组学, click chemistry.
• Avoid isolated punctuation at the beginning of a line.
• Avoid single orphan characters at the end of a line in Chinese resumes.
• Avoid manual line breaks inside bullets unless they represent semantic separation.
• For HTML resumes, use CSS for spacing and alignment instead of hard-coded <br>.

Terminology Consistency

• Use one consistent form for each institution, company, laboratory, method, software, instrument, and technical field.
• Do not alternate between full names and abbreviations unless the abbreviation is introduced once.
• Preserve official names for universities, companies, laboratories, journals, degrees, publications, patents, software, and instruments.
• For bilingual resumes, maintain a terminology map with Chinese term, English term, abbreviation, and source or user confirmation.

Acceptance Criteria

A resume deliverable passes quality review only when all required gates are satisfied.

Required Gates

• No fabricated facts.
• All uncertain facts are marked 待补充 or 需用户确认.
• All final key bullets are supported by candidate evidence.
• For targeted resumes, all high-priority job requirements are either covered, marked as gaps, or explicitly excluded.
• No protected or market-sensitive personal information is included against the language/region rules.
• No unresolved placeholders remain.
• Requested files exist and are linked.
• PDF is not claimed unless rendered and visually checked.
• ATS version is parser-friendly when ATS compatibility is required.
• Missing critical information is listed separately from optional enhancement information.

Recommended Gates

• One-page corporate resumes stay within the recommended density range.
• Bullets follow action + task + method/tool + result/impact.
• Terminology is consistent.
• Section order matches candidate type and target role.
• Repeated content is removed.
• Weak or risky content is either omitted, reframed, or marked for confirmation.

Completion Criteria

Complete the task only when all applicable criteria are met:

Classification and Scope

• Candidate stage is classified or marked UNKNOWN.
• Resume scenario is classified.
• Language and market are explicit.
• Workflow mode is selected.
• Missing decision-critical information is listed.

Evidence Integrity

• No fabricated education, experience, metrics, publications, patents, awards, dates, authorship, skills, or proficiency.
• Uncertain facts are marked 待补充 or 需用户确认.
• Risky or unfavorable information is flagged instead of automatically included.
• Master profile and targeted resume remain separate.

Targeted Resume Requirements

• Job source, requirement, candidate evidence, match score, adoption decision, and final bullet are traceable.
• Job sources include URL, access date, source type, freshness, and confidence when online research is used.
• Explicit requirements, tentative requirements, and generic market signals are separated.
• High-priority requirements are covered or listed as gaps.

Content Quality

• Section order matches candidate type and target.
• Experience bullets use action + task + method/tool + result/impact.
• Repeated content is removed.
• Self-evaluation is evidence-based.
• Keywords are included only when supported by evidence.
• Terminology is consistent.

Layout and Format

• No unresolved placeholders remain.
• HTML contains print CSS when HTML is requested.
• PDF is generated only when requested.
• PDF is visually checked before being claimed as complete.
• ATS-compatible version avoids core-content tables, icons, text boxes, multi-column layout, and image-only text when ATS compatibility is required.

Delivery

• Requested files are generated and linked.
• Missing information is split into critical fields and optional enhancement fields.
• Next optimization actions are specific.
• Optional outputs are not generated unless requested.