メニュー
Interview Preparation Mode - Generates a strategic "Intelligence Pre-Interview Sheet" by synthesizing the Job Description, Company news, and Candidate history. Use this when preparing for an interview or researching a target role.
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
SOC 職業分類に基づく
CV Building Mode. Guidelines for adding new professional experience, projects, or skills to the cv-data repository.
General project rules and architectural documentation for AGENT_Tasks. Use this when modifying files in AGENT_Tasks, debugging the resume orchestrator, or editing automation scripts.
Guidelines and constraints for JSON Resume generation and rendering. Use this when editing or validating resume data.
Execution mode - Workflow for generating tailored resumes and cover letters based on a Job Description (JD). Use this when the user asks to create a resume for a specific job or provides a position description.
Strict rules for ensuring generated resumes are parsable by Applicant Tracking Systems (ATS).
Protocol for handling resume orchestrator failures. STRICTLY prohibits completion of failed jobs and mandates user-driven corrective actions.
| name | interview-intelligence |
| description | Interview Preparation Mode - Generates a strategic "Intelligence Pre-Interview Sheet" by synthesizing the Job Description, Company news, and Candidate history. Use this when preparing for an interview or researching a target role. |
CRITICAL INSTRUCTION: There are model and runtime-specific variances for agents running in this environment. If you are a Gemini Agent in Gemini CLI, you will use Gemini_Tasks. If you are an OpenAI Agent running under Codex, you will use Codex_Tasks.
This skill prepares the candidate ([Your Name]) for a high-stakes interview by generating a structured Markdown dossier that maps candidate assets to company pains.
.txt file../venv/bin/python3.Run the interview prep orchestrator using the following command:
./venv/bin/python3 AGENT_Tasks/Orchestrator/generate_interview_prep.py --jd <path_to_jd.txt> --company "<Company Name>" --position "<Position Title>"
The orchestrator uses a specific strategy to ensure alignment:
CV-Data and past resumes) to the company's problems.The generated dossier (cv-data/resumes/[Position]-[Company]-Interview-Prep.md) includes:
CRITICAL: After generation, you MUST explicitly restate the absolute file:// URI to the generated PDF on a single line in your final response to the user so it is easily clickable/copyable.
After generation, it is common to:
cv-data/resumes/.pandoc or chrome --headless if a portable version is needed.