From career-navigator
Full interview preparation for a specific application or role: company and news context, stage-specific questions (recruiter, hiring manager, technical, panel, executive, final), and story evidence retrieved from StoryCorpus (with ExperienceLibrary fallback), optional voice/STT via interview-coach. Saves a brief under CareerNavigator/interview-prep/ and logs a [prep] note in tracker.json. Also invocable via /career-navigator:prep-interview.
npx claudepluginhub tmargolis/career-navigator --plugin career-navigatorThis skill uses the workspace's default tool permissions.
Require `CareerNavigator/profile.md`, `ExperienceLibrary.json`, and `tracker.json`. If missing:
Guides Payload CMS config (payload.config.ts), collections, fields, hooks, access control, APIs. Debugs validation errors, security, relationships, queries, transactions, hook behavior.
Builds scalable data pipelines, modern data warehouses, and real-time streaming architectures using Spark, dbt, Airflow, Kafka, and cloud platforms like Snowflake, BigQuery.
Builds production Apache Airflow DAGs with best practices for operators, sensors, testing, and deployment. For data pipelines, workflow orchestration, and batch job scheduling.
{user_dir} and gateRequire CareerNavigator/profile.md, ExperienceLibrary.json, and tracker.json. If missing:
Run
/career-navigator:launchfirst to initialize Career Navigator.
Story corpus gate:
CareerNavigator/StoryCorpus.json.mine-stories first.ExperienceLibrary.json fallback and clearly label lower story-specific confidence.From user message or tracker:
application_id if given; else match company + role against tracker.json applications[].Collect if missing:
interview_stage: recruiter | hiring_manager | technical | panel | executive | final (default: infer from wording; recruiter call / phone screen → recruiter).If the mcp-voice MCP exposes speak / listen, use them per agents/interview-coach/AGENT.md. If the user is speaking or pastes a transcript from host STT, pass it as user_audio_transcript in the handoff to interview-coach.
Before invoking interview-coach, run story-retrieval with:
application_id or company + roleinterview_stageUse the returned 8-12 selected stories as the primary interview evidence payload.
Read and follow agents/interview-coach/AGENT.md with:
mode: prepinterview_stage (required)application_id or company + roleinterviewer, JD, interview_date, user_audio_transcriptselected_stories payload from story-retrievalUse the exact agent name interview-coach.
After the coach content is produced:
{user_dir}/CareerNavigator/interview-prep/ exists.applications[].notes an object:{
"date": "YYYY-MM-DD",
"text": "[prep] Interview prep brief saved: CareerNavigator/interview-prep/{filename}.md (stage: {stage})."
}
Update tracker.json in place. If no application matched, skip tracker write but still save the file under interview-prep/ with a clear filename and tell the user to link it via /career-navigator:track-application if needed.
Offer /career-navigator:mock-interview for a voice or text practice session. Do not claim features that are not shipped.