Resume JD Match — JD定制简历

AI-powered JD-matched resume generator with native Chinese and English support. Collects structured user profile (work history, projects, skills, education),...

Security Scan

The skill's stated purpose (creating JD-matched resumes) and most instructions are coherent, but there are a couple of inconsistencies you should verify before installing — notably a claim of "no network requests" while the skill accepts URLs, and a referenced export script (scripts/export-pdf.ps1) whose contents were not provided for review.

Purpose & Capability

Name/description match the behavior: collecting a structured profile, parsing JDs, generating HTML/PDF resumes, and saving files under workspace/resumes/. No unrelated credentials, binaries, or config paths are requested.

Instruction Scope

Instructions are mostly scoped to profile collection, JD parsing, HTML generation, and local PDF export. However, the SKILL.md says "PDF export uses local headless browser... No network requests," yet the skill also accepts a JD URL as input (which implies fetching remote content) — this is a contradiction that should be clarified. Also the export is performed by scripts/export-pdf.ps1, but that script's contents were not included for review; the behavior of that script (network calls, temp files, external executables invoked) is unknown.

Install Mechanism

Instruction-only skill with no install spec and no code files beyond templates/instructions. Low install risk because nothing is written to disk by an installer. The only runtime writes are the files the skill itself asks to save in workspace/ (profile and resumes).

Credentials

No environment variables, credentials, or config paths are requested. The skill's data needs (personal profile) are proportional to the stated purpose.

Persistence & Privilege

Does not request elevated privileges and is not always-enabled. It persists user-sensitive data locally (resume-profile.md and generated files in resumes/). This is expected but important for privacy — the agent will store personally identifiable information in the workspace by design.

What to consider before installing

This skill appears to be what it claims (a resume/JD matching tool) but there are two things to check before use: (1) Ask or inspect the contents of scripts/export-pdf.ps1 (not provided) to ensure the export runs locally and does not call external endpoints or execute unexpected commands. (2) Confirm how URL inputs are handled — if the agent will fetch remote job-page URLs, understand that network requests will occur despite the SKILL.md's "No network requests" statement. Also: be aware the skill stores sensitive personal data in workspace/resume-profile.md and in resumes/; if you install, keep that workspace private or review/remove the profile file after use. If you can't inspect the export script or get clarity on URL fetching, treat this skill cautiously or run it in a restricted/sandboxed environment.

Resume JD Match — JD 定制简历生成器

Generate polished, JD-matched HTML resume + PDF. Two-phase workflow: collect profile → match JD → generate.

Phase 1: Profile Collection

On first run (no resume-profile.md exists), collect user info. Ask one section at a time, confirm before next. Save to resume-profile.md.

Confirm preferences first:

1. Accent color — hex/name, default #6b4c9a
2. Language — 中文 or English
3. Target region — mainland China (include birth date) or overseas (exclude)

Sections (structured data per section)

1. Personal — name, phone, email, birth date, location, LinkedIn
2. Education — school, degree, major, date, honors
3. Work Experience — per role: company, title, dates, 3-6 bullets (quantify!)
4. Side Projects — per project: name, type, status, role, features/metrics, tech stack
5. Skills — domain + technical tools + languages, grouped
6. Certificates & Awards

On subsequent runs: load profile, ask "Anything to update?"

Phase 2: JD Match & Generate

2.1 Collect JD

Accept pasted text, file, or URL. Parse and confirm with user before proceeding:

• Job title, company, core requirements (3-5), preferred qualifications

2.2 Match Analysis (show user, wait for confirmation)

🎯 Target: [Title] @ [Company]
📊 Match: [High/Medium/Low]
✅ Strong matches: ...
⚠️ Gaps: ...
📝 Strategy: Emphasize / Reframe / Downplay

2.3 Generate HTML Resume

Single self-contained HTML with inline CSS. See references/html-template-guide.md.

Content rules:

• 3 core advantages in top highlight grid → mapped to top JD priorities
• Work experience ordered by JD relevance
• Mirror JD keywords naturally, don't stuff
• Every bullet quantified where possible
• Skills section prioritizes JD-required skills (use tag-highlight class)
• 1-2 pages A4 max

2.4 Export PDF

powershell -File scripts/export-pdf.ps1 -HtmlPath "$htmlPath" -OutputPath "$pdfPath"

If export fails: tell user to open HTML in browser → Ctrl+P.

2.5 Deliver

Save to resumes/: [Name]-[Title].html + [Name]-[Title].pdf

Pre-send checklist:

• Contact info correct
• Dates accurate
• No typos in company/project names
• Achievements not overstated
• PDF formatting correct

File Structure

workspace/
├── resume-profile.md
├── resumes/
└── skills/resume-tailor/
    ├── SKILL.md
    ├── scripts/export-pdf.ps1
    └── references/html-template-guide.md