HRClaw JD & Resume Scorecard

v0.1.2

Turn job descriptions and PDF resumes into structured hiring decisions, interview questions, and Feishu/DingTalk-friendly output.

1· 122·0 current·0 all-time
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
VirusTotalVirusTotal
Benign
View report →
OpenClawOpenClaw
Benign
high confidence
Purpose & Capability
Name/description (JD -> scorecard, resume -> score) match the files and prompts. Templates, examples, and prompts all implement the stated functionality; the single script is a local demo image generator and is proportionate to a demo asset.
Instruction Scope
SKILL.md and the prompts limit runtime actions to parsing JDs, extracting text from PDFs (and flagging unreadable PDFs as needs_ocr), building scorecards, and producing JSON/markdown. The instructions do not ask the agent to read unrelated files, export environment variables, or send data to unexpected endpoints.
Install Mechanism
No install spec is present (instruction-only) and the only code file is a local demo script that uses Pillow to render images; nothing downloads or extracts remote archives or installs external packages.
Credentials
The skill declares no required environment variables, credentials, or config paths. There are no requests for unrelated secrets or multiple unrelated credentials.
Persistence & Privilege
always is false and the skill does not request permanent presence or system-wide config changes. agents/openai.yaml sets allow_implicit_invocation: true (the platform default) but that is not combined with other risky capabilities.
Assessment
This skill appears coherent and self-contained: it transforms JDs into scorecards and scores resumes, and it does not request credentials or perform network installs. Before installing, consider privacy and operational questions: the skill processes resumes (personal data), so confirm where PDF text extraction / OCR happens (platform-managed or third-party) and whether uploaded resumes are sent off-platform or logged/stored; test with non-sensitive sample resumes first. Also note the demo script requires the Pillow library and local fonts if you run it locally — nothing in the skill will autonomously install packages. Finally, because the source and homepage are unknown, review the included files yourself (especially any code you plan to run) and verify the skill’s behavior meets your compliance and data-retention policies.

Like a lobster shell, security has layers — review code before you run it.

atsvk971cp7hjda8n1wngx58afjztd83wa7ncandidate-screeningvk971cp7hjda8n1wngx58afjztd83wa7ndingtalkvk971cp7hjda8n1wngx58afjztd83wa7nfeishuvk971cp7hjda8n1wngx58afjztd83wa7nhiringvk971cp7hjda8n1wngx58afjztd83wa7nhrclawvk971cp7hjda8n1wngx58afjztd83wa7njd-scorecardvk971cp7hjda8n1wngx58afjztd83wa7njob-descriptionvk971cp7hjda8n1wngx58afjztd83wa7nlatestvk971cp7hjda8n1wngx58afjztd83wa7npdfvk971cp7hjda8n1wngx58afjztd83wa7nrecruitingvk971cp7hjda8n1wngx58afjztd83wa7nresumevk971cp7hjda8n1wngx58afjztd83wa7nresume-screeningvk971cp7hjda8n1wngx58afjztd83wa7nscorecardvk979q9wzqvncy0zestbrycmes183wevz

License

MIT-0
Free to use, modify, and redistribute. No attribution required.

Comments