メニュー
Use when inspecting simulated interview Agent short-term session state, job-resume binding, question plan progress, answer signals, difficulty, follow-up strategy, or remaining focus.
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
| name | interview-state-tool |
| description | Use when inspecting simulated interview Agent short-term session state, job-resume binding, question plan progress, answer signals, difficulty, follow-up strategy, or remaining focus. |
Use this skill to inspect interview_sessions.report.agent_state. The state story is JobProfile -> CandidateProfile -> QuestionPlan -> AskedQuestions -> AnswerSignals -> EvaluationState -> FollowupStrategy -> SummaryReport.
Current memory boundary:
assistant_memories records.agent_state.session_summary inside the same interview session.Run inside the API container:
docker compose exec api python /app/skills/interview-state-tool/scripts/inspect_interview_state.py --email admin@example.com
Inputs: optional --session-id, optional --user-id or --email. Without --session-id, the latest user session is inspected.
The script emits compact JSON: available, session_id, job_id, resume_id, mode, message_count, has_agent_state, difficulty, remaining_focus, last_followup_strategy, asked_count, and state_keys. It does not expose hidden reasoning or full message transcripts.
Explain where the interview currently is, what focus remains, and why the next follow-up may change. If no state exists, tell the user to start or resume a bound interview session.
python skills/interview-state-tool/scripts/inspect_interview_state.py --self-test
python skills/interview-state-tool/scripts/inspect_interview_state.py --help
docker compose exec api python /app/skills/interview-state-tool/scripts/inspect_interview_state.py --email admin@example.com
docker compose exec api pytest tests/interview/test_interview_short_memory.py -q
Use when inspecting AI assistant file-based long-term memory, session JSONL archives, soft consolidation, Dream updates, or assistant context isolation.
Use when running Agent golden-case evaluation, checking intent accuracy, tool-call accuracy, RAG grounding, job matching, interview follow-up policy, or resume rubric compliance.
Use when reading saved jobs, application status counts, manual follow-up notes, or the user's application tracking state.
Use when inspecting FastAPI routes, controllers, backend service boundaries, repository-backed endpoints, API surface, or route availability.
Use when inspecting or explaining Qingcheng AI chat complexity classification, prompt-template injection, SupervisorAgent routing, selected tool allowlists, or agent planning for a user message.
Use when changing or reviewing the Next.js frontend UI, Tailwind layout, chat/interview pages, resume/job/application screens, or frontend API wrappers.