AI 简历纠错排版大师
v1.0.1智能检测简历逻辑错误，量化项目含金量，自动隐私脱敏并优化排版，助力提升简历专业度与吸引力。
⭐ 0· 66·0 current·0 all-time
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Benign
high confidencePurpose & Capability
Name/description (logic audit, anonymize, beautify) align with the included Python modules: resume_beautifier.py handles DOCX rendering/highlighting and resume_beautifier_pro.py handles diagnosis and anonymization. The presence of requirements.txt (python-docx, pdfplumber) and README claiming PDF generation is slightly inconsistent with the code, which only writes DOCX files; this looks like an incomplete feature rather than malicious mismatch.
Instruction Scope
SKILL.md instructs users to upload resumes for analysis and does not direct the agent to read unrelated files, environment variables, or external endpoints. The code only reads/processes provided text, performs regex-based checks, offers anonymization on demand, and writes DOCX templates/output locally.
Install Mechanism
No install spec is provided (instruction-only), but the package includes Python scripts and requirements.txt. That means dependencies (python-docx) must be installed by the host — the skill itself does not declare how to install them. This is not inherently dangerous but is an operational mismatch to be aware of.
Credentials
The skill requests no environment variables, credentials, or config paths. The code does not attempt to read environment secrets or external auth tokens. It only creates a local 'templates' directory and output DOCX files.
Persistence & Privilege
always:false and no special privileges. The only persistent side effect is creating a local 'templates' folder and saving generated DOCX files — behavior consistent with a document-processing tool and described in README.
Assessment
This skill is coherent with its resume-auditing claim, but before installing: (1) ensure the host Python environment has python-docx installed (requirements.txt is provided but the skill does not auto-install); (2) note that PDF support is claimed in docs but the included code only generates DOCX — treat PDF output as not implemented unless you verify additional code; (3) the tool writes a local 'templates' directory and output files in its working directory — if you are concerned about filesystem clutter, run it in a sandbox or dedicated folder; (4) anonymization runs only when you request it (is_anonymized flag), so avoid uploading sensitive production data unless you intentionally choose the anonymized mode; (5) test with non-sensitive sample resumes to confirm behavior in your environment. Overall the package appears to do what it says and does not request hidden credentials or network access.Like a lobster shell, security has layers — review code before you run it.
latestvk979y3tag50zgmkbhacheasgtd83ykgf
License
MIT-0
Free to use, modify, and redistribute. No attribution required.