Interview System Designer
v2.1.1This skill should be used when the user asks to "design interview processes", "create hiring pipelines", "calibrate interview loops", "generate interview que...
⭐ 0· 719·6 current·6 all-time
byAlireza Rezvani@alirezarezvani
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Benign
high confidencePurpose & Capability
Name/description (interview loop design, question banks, calibration) match the included Python tools and reference materials. The three scripts (loop_designer.py, question_bank_generator.py, hiring_calibrator.py) and sample data are coherent with the stated capabilities; no unrelated credentials, binaries, or config paths are requested.
Instruction Scope
SKILL.md instructs the agent to run local Python scripts against JSON inputs (role definitions, interview results). That scope is appropriate for the stated purpose. However the hiring_calibrator expects and uses demographic fields (gender, ethnicity, university_tier, etc.), so the tool will process sensitive personal data — the documentation does not instruct any safe-handling or anonymization steps. SKILL.md does not direct data to external endpoints, but integration notes mention exporting to ATS/analytics systems (which may be implemented in the code or added by users).
Install Mechanism
No install spec is provided (instruction-only install), so nothing is downloaded or installed automatically by the platform. The README claims only Python 3 standard library is required. Because there is no external installer or network-download step in the registry metadata, install risk is low. Note: the repository includes sizeable Python scripts — review them before execution.
Credentials
The skill declares no required environment variables, credentials, or config paths, which is proportionate to its offline/local analysis purpose. The only risk is data sensitivity: the expected input data includes candidate demographic and background fields (gender, ethnicity, university tier, previous company), so supplying real candidate data could expose PII if outputs are shared or exported.
Persistence & Privilege
The skill is not always-enabled and is user-invocable (normal). It does not declare any behavior that would persistently modify other skills or system settings. No elevated privileges are requested.
Assessment
This package is internally consistent and appears to do what it claims, but take the following precautions before using it on real data: (1) Inspect the three Python scripts for any network calls, hidden phone-home behavior, or file-system writes you don't expect; (2) Run the tools first on the provided sample JSONs in an isolated environment; (3) Do not feed real candidate PII/demographics unless you have consent and appropriate data-handling controls — consider anonymizing or removing demographic fields if you only need calibration logic; (4) If you plan to integrate outputs with ATS, calendars, or analytics dashboards, verify how export is implemented and restrict access/permissions appropriately; (5) If you lack internal security review capacity, ask a developer to scan the code for external network requests and unexpected subprocess execution before running in production.Like a lobster shell, security has layers — review code before you run it.
latestvk976ymrga67g8hq91wgzncmpj582mjh3
License
MIT-0
Free to use, modify, and redistribute. No attribution required.